Search Results

CT:VQ software is a non-invasive image post-processing technology, using CT lung images to provide clinical decision support for thoracic disease diagnosis and management in adult patients. It utilizes two non-contrast chest CT studies to quantify and visualize ventilation and perfusion.

Quantification and visualizations are provided as DICOM images. CT:VQ may be used when Radiologists, Pulmonologists, and/or Nuclear Medicine Physicians need a better understanding of a patient's lung function and/or respiratory condition.

CT:VQ is a Software as a Medical Device (SaMD) technology, which can be used in the analysis of a paired (inspiratory/expiratory) non-contrast Chest CT. It is designed to measure regional ventilation (V) and regional perfusion (Q) in the lungs.

The Device provides visualization and quantification to aid in the assessment of thoracic diseases. These regional measures are derived from the lung tissue displacement, the lung volume change, and the Hounsfield Units of the paired (inspiratory/expiratory) chest CT.

The Device outputs DICOM images containing the ventilation output and perfusion output, consisting of a series of image slices generated with the same slice spacing as the expiration CT. In each slice the intensity value for each voxel represents either the value of ventilation or the value for perfusion, respectively, at that spatial location. Additional Information sheet is also generated containing quantitative data, such as lung volume.

Here's a breakdown of the acceptance criteria and the study details for the CT:VQ device, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

The acceptance criteria for CT:VQ are implicitly demonstrated through its strong performance in clinical studies, showing agreement with established gold standards. While explicit numerical acceptance criteria are not provided in a table format within the summary, the narrative describes the goals of the study:

• Consistency/Agreement with Nuclear Medicine Imaging (SPECT/CT): The device's regional ventilation and perfusion measurements should align well with SPECT/CT findings.
• Correlation with Pulmonary Function Tests (PFTs): CT:VQ metrics should statistically correlate with standard PFTs like DLCO and FEV1/FVC ratio.
• Interpretability and Clinical Actionability: The outputs should be clear, understandable, and useful for clinicians.
• Safety and Effectiveness Profile: The device should have a safety and effectiveness profile similar to the primary predicate device.

Table of Acceptance Criteria and Reported Device Performance (as inferred from the text):

Study Details

Here's a breakdown of the specific information requested about the studies:

1. Sample sizes used for the test set and the data provenance:

• Test Set Sample Sizes:
  • Reader Performance Study: n=77
  • Standalone Performance Assessment: n=58 (a subset of the overall clinical studies data)
• Data Provenance:
  • Country of Origin: Not explicitly stated, but the submission is from 4DMedical Limited in Australia, and the FDA clearance is in the US. The description mentions "clinically-acquired data included paired chest CTs acquired on CT scanners across a range of manufacturers and models and at different institutions, across a diverse range of patients." This suggests multi-institutional data, potentially from various geographic locations, but this is not confirmed.
  • Retrospective or Prospective: Not explicitly stated whether the studies were retrospective or prospective. The description "clinical studies were also conducted to demonstrate the safety and efficacy... in the context of clinical care" and comparing with "gold-standard and best practice measures for respiratory diagnosis" often implies retrospective analysis of existing data combined with prospective data collection, but this is not definitive in the text.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Number of Experts: Not explicitly stated for establishing ground truth, although for the Reader Performance Study, "clinicians with expertise in thoracic imaging and pulmonary care" were involved in rating the outputs. The implication is that these experts, along with SPECT/CT and PFT results, contributed to the ground truth.
• Qualifications of Experts: "Clinicians with expertise in thoracic imaging and pulmonary care." No specific number of years of experience or board certifications (e.g., radiologist with 10 years of experience) is provided.

3. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

• Adjudication Method: Not explicitly stated. The summary mentions "Inter-reader variability was not significantly different for CT:VQ than for SPECT," which implies multiple readers, but the method for resolving discrepancies or establishing a final ground truth from multiple readers is not detailed.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• MRMC Study: A "Reader Performance Study" was conducted with n=77 cases, involving "clinicians with expertise in thoracic imaging and pulmonary care." This aligns with the characteristics of an MRMC study.
• Effect Size of Human Reader Improvement with AI vs. without AI assistance: The summary does not provide an effect size or direct comparison of human reader performance with CT:VQ assistance versus without it. The study focused on assessing:
  • Agreement between CT:VQ outputs and SPECT.
  • Interpretability and clinical actionability of CT:VQ outputs.
  • Inter-reader variability of CT:VQ vs. SPECT.
    It does not quantify an improvement in reader accuracy or efficiency due to AI assistance.

5. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

• Standalone Performance: Yes, a "Standalone Performance Assessment" was performed with a subset of 58 cases. The findings indicated strong regional agreement between CT:VQ and SPECT VQ measurements and stronger associations of CT:VQ perfusion metrics with DLCO compared to SPECT.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

• Type of Ground Truth: A combination of established clinical diagnostics was used:
  • Nuclear Medicine Imaging (Single photon emission computed tomography, SPECT/CT): Used as a "gold-standard and best practice measure" for regional ventilation and perfusion.
  • Pulmonary Function Tests (PFTs): Specifically Diffusing capacity of the lung for carbon monoxide (DLCO) and FEV1/FVC ratio, used to correlate with CT:VQ outputs.
  • Clinical Diagnosis/Findings: Implied through "Case Studies further illustrated key advantages of CT:VQ... successfully replicated the diagnostic findings of SPECT."

7. The sample size for the training set:

• Training Set Sample Size: Not explicitly stated in the provided text. The summary only mentions the sample sizes for the clinical validation studies (test sets).

8. How the ground truth for the training set was established:

• Training Set Ground Truth Establishment: Not explicitly stated how the ground truth for the training set was established, as the training set size and characteristics are not detailed. Typically, it would involve similar rigorous processes (e.g., expert annotation, gold-standard imaging modalities, clinical outcomes) as the test set, but this information is absent in this document.

Ask a specific question about this device

The system is intended to produce cross-sectional images of the body by computer reconstruction of x-ray transmission projection data from the same axial plane taken at different angles. The system may acquire data using Axial, Cine, Helical, Cardiac, and Gated CT scan techniques from patients of all ages. These images may be obtained either with or without contrast. This device may include signal analysis and display equipment, patient and equipment supports, components and accessories.

This device may include data and image processing to produce images in a variety of trans-axial and reformatted planes. Further, the images can be post processed to produce additional imaging planes or analysis results.

The system is indicated for head, whole body, cardiac, and vascular X-ray Computed Tomography applications.

The device output is a valuable medical tool for the diagnosis of disease, trauma, or abnormality and for planning, guiding, and monitoring therapy.

If the spectral imaging option is included on the system, the system can acquire CT images using different kV levels of the same anatomical region of a patient in a single rotation from a single source. The differences in the energy dependence of the attenuation coefficient of the different materials provide information about the chemical composition of body materials. This approach enables images to be generated at energies selected from the available spectrum to visualize and analyze information about anatomical and pathological structures.

GSI provides information of the chemical composition of renal calculi by calculation and graphical display of the spectrum of effective atomic number. GSI Kidney stone characterization provides additional information to aid in the characterization of uric acid versus non-uric acid stones. It is intended to be used as an adjunct to current standard methods for evaluating stone etiology and composition.

The CT system is indicated for low dose CT for lung cancer screening. The screening must be performed within the established inclusion criteria of programs/ protocols that have been approved and published by either a governmental body or professional medical society.

This proposed device Revolution Vibe is a general purpose, premium multi-slice CT Scanning system consisting of a gantry, table, system cabinet, scanner desktop, power distribution unit, and associated accessories. It has been optimized for cardiac performance while still delivering exceptional imaging quality across the entire body.

Revolution Vibe is a modified dual energy CT system based on its predicate device Revolution Apex Elite (K213715). Compared to the predicate, the most notable change in Revolution Vibe is the modified detector design together with corresponding software changes which is optimized for cardiac imaging providing capability to image the whole heart in one single rotation same as the predicate.

Revolution Vibe offers an accessible whole heart coverage, full cardiac capability CT scanner which can deliver outstanding routine head and body imaging capabilities. The detector of Revolution Vibe uses the same GEHC's Gemstone scintillator with 256 x 0.625 mm row providing up to 16 cm of coverage in Z direction within 32 cm scan field of view, and 64 x 0.625 mm row providing up to 4 cm of coverage in Z direction within 50 cm scan field of view. The available gantry rotation speeds are 0.23, 0.28, 0.35, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, and 1.0 seconds per rotation.

Revolution Vibe inherits virtually all of the key technologies from the predicate such as: high tube current (mA) output, 80 cm bore size with Whisper Drive, Deep Learning Image Reconstruction for noise reduction (DLIR K183202/K213999, GSI DLIR K201745), ASIR-V iterative recon, enhanced Extended Field of View (EFOV) reconstruction MaxFOV 2 (K203617), fast rotation speed as fast as 0.23 second/rot (K213715), and spectral imaging capability enabled by ultrafast kilovoltage(kv) switching (K163213), as well as ECG-less cardiac (K233750). It also includes the Auto ROI enabled by AI which is integrated within the existing SmartPrep workflow for predicting Baseline and monitoring ROI automatically. As such, the Revolution Vibe carries over virtually all features and functionalities of the predicate device Revolution Apex Elite (K213715).

This CT system can be used for low dose lung cancer screening in high risk populations*.

The provided FDA 510(k) clearance letter and summary for the Revolution Vibe CT system does not include detailed acceptance criteria or a comprehensive study report to fully characterize the device's performance against specific metrics. The information focuses more on the equivalence to a predicate device and general safety/effectiveness.

However, based on the text, we can infer some aspects related to the Auto ROI feature, which is the only part of the device described with specific performance testing details.

Here's an attempt to extract and describe the available information, with clear indications of what is not provided in the document.

Acceptance Criteria and Device Performance for Auto ROI

The document mentions specific performance testing for the "Auto ROI" feature, which utilizes AI. For other aspects of the Revolution Vibe CT system, the submission relies on demonstrating substantial equivalence to the predicate device (Revolution Apex Elite) through engineering design V&V, bench testing, and a clinical reader study focused on overall image utility, rather than specific quantitative performance metrics meeting predefined acceptance criteria for the entire system.

1. Table of Acceptance Criteria and Reported Device Performance (Specific to Auto ROI)

Note: The document does not provide the explicit numerical value for the "pre-established acceptance criteria" or the actual "success rate" achieved for the Auto ROI feature.

2. Sample Size and Data Provenance for the Test Set (Specific to Auto ROI)

• Sample Size: 1341 clinical images
• Data Provenance: "real clinical practice" (Specific country of origin not mentioned). The images were used for "Auto ROI performance" testing, which implies retrospective analysis of existing clinical data.

3. Number of Experts and Qualifications to Establish Ground Truth (Specific to Auto ROI)

• Number of Experts: Not specified for the Auto ROI ground truth establishment.
• Qualifications of Experts: Not specified for the Auto ROI ground truth establishment.

Note: The document mentions 3 readers for the overall clinical reader study (see point 5), but this is for evaluating the diagnostic utility and image quality of the CT system and not explicitly for establishing ground truth for the Auto ROI feature.

4. Adjudication Method for the Test Set (Specific to Auto ROI)

• Adjudication Method: Not specified for the Auto ROI test set.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• Was an MRMC study done? Yes, a "clinical reader study of sample clinical data" was carried out. It is described as a "blinded, retrospective clinical reader study."

• Effect Size of Human Readers Improvement with AI vs. without AI assistance: The document states the purpose of this reader study was to validate that "Revolution Vibe are of diagnostic utility and is safe and effective for its intended use." It does not report an effect size or direct comparison of human readers' performance with and without AI assistance (specifically for the Auto ROI feature within the context of reader performance). The study seemed to evaluate the CT system's overall image quality and clinical utility, possibly implying that the Auto ROI is integrated into this overall evaluation, but a comparative effectiveness study of the AI's impact on human performance is not described.

  • Details of MRMC Study:
    • Number of Cases: 30 CT cardiac exams
    • Number of Readers: 3
    • Reader Qualifications: US board-certified in Radiology with more than 5 years' experience in CT cardiac imaging.
    • Exams Covered: "wide range of cardiac clinical scenarios."
    • Reader Task: "Readers were asked to provide evaluation of image quality and the clinical utility."

6. Standalone (Algorithm Only) Performance

• Was a standalone study done? Yes, for the "Auto ROI" feature, performance was tested "using 1341 clinical images from real clinical practice," and "the tests results in success rates exceeding the pre-established acceptance criteria." This implies an algorithm-only evaluation of the Auto ROI's ability to successfully identify and monitor ROI.

7. Type of Ground Truth Used (Specific to Auto ROI)

• Type of Ground Truth: Not explicitly stated for the Auto ROI. Given the "success rates" metric, it likely involved a comparison against a predefined "true" ROI determined by human experts or a gold standard method. It's plausible that this was established by expert consensus or reference standards.

8. Sample Size for the Training Set

• Sample Size: Not provided in the document.

9. How Ground Truth for the Training Set Was Established

• Ground Truth Establishment: Not provided in the document.

In summary, the provided documentation focuses on demonstrating substantial equivalence of the Revolution Vibe CT system to its predicate, Revolution Apex Elite, rather than providing detailed, quantitative performance metrics against specific acceptance criteria for all features. The "Auto ROI" feature is the only component where specific performance testing (standalone) is briefly mentioned, but key details like numerical acceptance criteria, actual success rates, and ground truth methodology for training datasets are not disclosed. The human reader study was for general validation of diagnostic utility, not a comparative effectiveness study of AI assistance.

Ask a specific question about this device

The Siemens PET/CT systems are combined X-Ray Computed Tomography (CT) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information.

The CT component produces cross-sectional images of the body by computer reconstruction of X-Ray transmission data from either the same axial plane taken at different angles or spiral planes taken at different angles. The PET subsystem images and measures the distribution of PET radiopharmaceuticals in humans for the purpose of determining various metabolic (molecular) and physiologic functions within the human body and utilizes the CT for fast attenuation correction maps for PET studies and precise anatomical reference for the fused PET and CT images.

The system maintains independent functionality of the CT and PET devices, allowing for single modality CT and/or PET diagnostic imaging.

These systems are intended to be utilized by appropriately trained health care professionals to aid in detecting, localizing, diagnosing, staging and restaging of lesions, tumors, disease and organ function for the evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders and cancer. The images produced by the system can also be used by the physician to aid in radiotherapy treatment planning and interventional radiology procedures.

This system can be used for low dose lung cancer screening in high risk populations.*

*As defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

Biograph Trinion PET/CT systems are combined multi-slice X-Ray Computed Tomography and Positron Emission Tomography scanners. This system is designed for whole body oncology, neurology and cardiology examinations. Biograph Trinion PET/CT systems provide registration and fusion of high-resolution metabolic and anatomic information from the two major components of each system (PET and CT). Additional components of the system include a patient handling system and acquisition and processing workstations with associated software.

Biograph Trinion VK20 software is a command-based program used for patient management, data management, scan control, image reconstruction and image archival and evaluation. All images conform to DICOM imaging format requirements.

Biograph PET/CT systems, which are the subject of this application, are substantially equivalent to the commercially available Biograph Trinion VK10 family of PET/CT systems (K233677). Differences compared to the commercially available Biograph Trinion systems include:

• The commercially available SOMATOM go.All and go.Top systems with VB10 (K233650) software have been incorporated into the Biograph Trinion VK20 systems, including commercially available CT features.

• Additional PET axial field of view (FoV) systems allowing for more scalability.

• Additional patient communication and comfort features.

• PET respiratory gating with an external gating device has been implemented.

The Biograph Trinion models may also use the names Biograph Mission, Biograph Wonder, Biograph Ambition and Biograph Devotion for marketing purposes.

The provided FDA 510(k) clearance letter for the Biograph Trinion PET/CT system primarily focuses on demonstrating substantial equivalence to a predicate device and adherence to recognized performance standards. It indicates that "all performance testing met the predetermined acceptance values," but does not provide specific numerical acceptance criteria or reported device performance for an AI/algorithm component, nor does it detail a study proving the device meets AI-specific acceptance criteria. The context suggests the "performance testing" refers to general PET/CT system performance, not AI-driven diagnostic assistance.

Therefore, many of the requested details, particularly those related to a standalone AI algorithm's performance, human-in-the-loop studies, dataset characteristics (sample size, provenance), and ground truth establishment methods for an AI component, are not available in the provided text.

Based on the information available in the document, here's what can be extracted and inferred, with explicit notes where information is missing or not applicable in the context of an AI study.

Acceptance Criteria and Reported Device Performance

The document states that "all performance testing met the predetermined acceptance values." However, it does not specify what those acceptance values were or the precise reported performance metrics beyond this general statement. The tests conducted were primarily related to the physical performance of the PET/CT system as per NEMA NU 2:2024 and NEMA XR 25:2019 standards, not specifically an AI component for diagnostic aid.

Table of Acceptance Criteria and Reported Device Performance (Based on available information for the PET/CT system):

Study Details (Focusing on AI-related aspects where applicable, and general system testing otherwise)

1. Sample size used for the test set and the data provenance:

   • For System Performance (NEMA tests): The document does not specify a "test set" in terms of patient data. NEMA tests typically involve phantom studies rather than patient data. Thus, sample size and data provenance are not applicable in the traditional sense for these tests.
   • For AI Component: The document does not provide any information on a test set (patient cases, images) or data provenance (e.g., country of origin, retrospective/prospective) for validating an AI component for diagnostic assistance. The descriptions are entirely about the physical PET/CT system.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

   • For System Performance: Ground truth for NEMA tests is established by physical measurements and calibration standards, not human experts.
   • For AI Component: This information is not provided in the document as there's no mention of an AI-driven diagnostic aid requiring expert-established ground truth.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

   • For System Performance: Not applicable.
   • For AI Component: This information is not provided in the document.

4. If a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

   • The document does not indicate that an MRMC study was performed for an AI component. The focus is on the substantial equivalence of the PET/CT hardware and software to a predicate device, and compliance with performance standards for the imaging system itself.

5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

   • The document does not detail any standalone algorithm performance testing. The performance testing described is for the integrated PET/CT system's physical and functional characteristics.

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

   • For System Performance: Ground truth for NEMA tests involves physical phantoms and established measurement protocols.
   • For AI Component: This information is not provided in the document.

7. The sample size for the training set:

   • This information is not provided in the document, as there is no mention of an AI model that undergoes a separate training process requiring a distinct training set.

8. How the ground truth for the training set was established:

   • This information is not provided in the document, as there is no mention of an AI model's training set.

Summary of Device and Performance Information from Document:

The provided 510(k) clearance letter for the Biograph Trinion is for a PET/CT imaging system, not an AI-based diagnostic software. The "performance testing" described in the document pertains to the physical and functional aspects of the PET/CT scanner (e.g., spatial resolution, sensitivity, image quality) as measured against industry standards (NEMA NU 2:2024). The clearance is based on proving substantial equivalence to a predicate device and adherence to these well-established performance standards for imaging hardware.

Therefore, the detailed questions regarding AI acceptance criteria, AI test set characteristics, human-in-the-loop studies, and AI ground truth establishment are not addressed in this document because the device being cleared is the imaging system itself, not an AI software component for image analysis or diagnostic support. The document implies that the system can be used for certain clinical applications (like lung cancer screening), but it doesn't describe an automated AI system within the device that requires separate clinical validation with reader studies or large patient datasets.

Ask a specific question about this device

This computed tomography system is intended to generate and process cross-sectional images of patients by computer reconstruction of x-ray transmission data.

The images delivered by the system can be used by a trained staff as an aid in diagnosis, treatment and radiation therapy planning as well as for diagnostic and therapeutic interventions.

This CT system can be used for low dose lung cancer screening in high risk populations*.

*As defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

Siemens intends to update the software version syngo CT VB20 (update) for the following NAEOTOM Alpha class CT systems:

Dual Source NAEOTOM CT scanner systems:

• NAEOTOM Alpha (trade name ex-factory CT systems: NAEOTOM Alpha.Peak; trade name installed base CT systems with SW upgrade only: NAEOTOM Alpha)

For simplicity, the product name of NAEOTOM Alpha will be used throughout this submission instead of the trade name NAEOTOM Alpha.Peak.

• NAEOTOM Alpha.Pro

Single Source NAEOTOM CT scanner system:

• NAEOTOM Alpha.Prime

The subject devices NAEOTOM Alpha (trade name ex-factory CT systems: NAEOTOM Alpha.Peak) and NAEOTOM Alpha.Pro with software version SOMARIS/10 syngo CT VB20 (update) are Computed Tomography X-ray systems which feature two continuously rotating tube-detector systems, denominated as A- and B-systems respectively (dual source NAEOTOM CT scanner system).

The subject device NAEOTOM Alpha.Prime with software version SOMARIS/10 syngo CT VB20 (update) is a Computed Tomography X-ray system which features one continuously rotating tube-detector systems, denominated as A-system (single source NAEOTOM CT scanner system).

The detectors' function is based on photon-counting technology.

In this submission, the above-mentioned CT scanner systems are jointly referred to as subject devices by "NAEOTOM Alpha class CT scanner systems".

The NAEOTOM Alpha class CT scanner systems with SOMARIS/10 syngo CT VB20 (update) produce CT images in DICOM format, which can be used by trained staff for post-processing applications commercially distributed by Siemens and other vendors. The CT images can be used by a trained staff as an aid in diagnosis, treatment and radiation therapy planning as well as for diagnostic and therapeutic interventions. The radiation therapy planning support includes, but is not limited to, Brachytherapy, Particle Therapy including Proton Therapy, External Beam Radiation Therapy, Surgery. The computer system delivered with the CT scanner is able to run optional post-processing applications.

Only trained and qualified users, certified in accordance with country-specific regulations, are authorized to operate the system. For example, physicians, radiologists, or technologists. The user must have the necessary U.S. qualifications in order to diagnose or treat the patient with the use of the images delivered by the system.

The platform software for the NAEOTOM Alpha class CT scanner systems is syngo CT VB20 (update) (SOMARIS/10 syngo CT VB20 (update)). It is a command-based program used for patient management, data management, X-ray scan control, image reconstruction, and image archive/evaluation. The software platform provides plugin software interfaces that allow for the use of specific commercially available post-processing software algorithms in an unmodified form from the cleared stand-alone post-processing version.

Software version syngo CT VB20 (update) (SOMARIS/10 syngo CT VB20 (update)) shall support additional software features compared to the software version of the predicate devices NAEOTOM Alpha class CT systems with syngo CT VB20 (SOMARIS/10 syngo CT VB20) cleared in K243523.

Software version SOMARIS/10 syngo CT VB20 (update) will be offered ex-factory and as optional upgrade for the existing NAEOTOM Alpha class systems.

The bundle approach is feasible for this submission since the subject devices have similar technological characteristics, software operating platform, and supported software characteristics. All subject devices will support previously cleared software and hardware features in addition to the applicable modifications as described within this submission. The intended use remains unchanged compared to the predicate devices.

The provided document describes the acceptance criteria and a study that proves the device meets those criteria for the NAEOTOM Alpha CT Scanner Systems. However, the document primarily focuses on demonstrating substantial equivalence to a predicate device and safety and effectiveness based on non-clinical testing and adherence to standards, rather than detailing a specific clinical performance study with defined acceptance criteria for a diagnostic aid.

Here's a breakdown of the requested information based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not provide a specific table of acceptance criteria with corresponding performance metrics in the way one would typically find for a diagnostic AI device (e.g., sensitivity, specificity, AUC). Instead, it states that:

• Acceptance Criteria for Software: "The test specification and acceptance criteria are related to the corresponding requirements." and "The test results show that all of the software specifications have met the acceptance criteria."
• Acceptance Criteria for Features: "Test results show that the subject devices...is comparable to the predicate devices in terms of technological characteristics and safety and effectiveness and therefore are substantially equivalent to the predicate devices."
• Performance Claim: "The conclusions drawn from the non-clinical and clinical tests demonstrate that the subject devices are as safe, as effective, and perform as well as or better than the predicate devices."

The closest the document comes to defining and reporting on "performance criteria" for a specific feature, beyond basic safety and technical functionality, are for the HD FoV 5.0 and ZeeFree RT algorithms.

2. Sample Size Used for the Test Set and Data Provenance

The document mentions "physical and anthropomorphic phantoms" for HD FoV 5.0 and "homogeneous water phantom" and "phantom with tissue-equivalent inserts," and "dynamic thorax phantom" for ZeeFree RT. It also refers to "retrospective blinded rater studies of respiratory 4D CT examinations performed at two institutions" for ZeeFree RT, but does not specify the sample size (number of cases/patients) or the country of origin for these real-world examination datasets. The data provenance (retrospective/prospective) is stated for the rater study for ZeeFree RT as retrospective, but not for the HD FoV 5.0 rater study (though implied by "retrospective blinded rater study").

3. Number of Experts and Qualifications for Ground Truth

For the HD FoV 5.0 and ZeeFree RT rater studies, the experts were "board-approved radio-oncologists and medical physicists." The number of experts is not specified, nor is their specific years of experience.

4. Adjudication Method for the Test Set

The document explicitly states "retrospective blinded rater study" for HD FoV 5.0 and ZeeFree RT. However, it does not specify the adjudication method (e.g., 2+1, 3+1, none) if there were multiple raters and disagreements.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

The document states that for HD FoV 5.0 and ZeeFree RT, "the performance of the algorithm was evaluated by board-approved radio-oncologists and medical physicists by means of retrospective blinded rater study." This indicates a reader study, which is often a component of an MRMC study.

However, the study described does not appear to be comparing human readers with AI assistance vs. without AI assistance. Instead, for HD FoV 5.0, it's comparing the new algorithm's results to its predecessor, HD FoV 4.0. For ZeeFree RT, it's comparing the reconstruction to "Standard reconstruction" and assessing if it introduces errors or new artifacts. It's an evaluation of the algorithm's output, not necessarily a direct measure of human reader improvement with AI assistance. Therefore, no effect size for human reader improvement with AI vs. without AI assistance is reported because this specific type of comparative effectiveness study was not described.

6. Standalone (Algorithm Only) Performance Study

Yes, standalone (algorithm only) performance was conducted. The bench testing described for both HD FoV 5.0 and ZeeFree RT involves detailed evaluations of the algorithms' outputs using phantoms and comparing them to established standards or previous versions. For example, for ZeeFree RT, the bench test objectives include demonstrating that it "introduces no relevant errors in terms of CT values and noise levels measured in a homogeneous water phantom" and "does not introduce relevant new artefacts." This is an assessment of the algorithm's direct output.

7. Type of Ground Truth Used

The ground truth used primarily appears to be:

• Phantom-based measurements: For HD FoV 5.0 (physical and anthropomorphic phantoms) and ZeeFree RT (homogeneous water phantom, tissue-equivalent inserts, static torso phantom, dynamic thorax phantom). These phantoms have known properties which serve as ground truth for evaluating image quality metrics.
• Expert Consensus/Interpretation: For HD FoV 5.0 and ZeeFree RT, it involved "board-approved radio-oncologists and medical physicists" in "retrospective blinded rater studies." This suggests the experts' interpretations (potentially comparing image features or diagnostic quality) formed a part of the ground truth or served as the primary evaluation method. The text doesn't specify if there was a pre-established "true" diagnosis or condition for these clinical cases, or if the experts were rating image quality or agreement with a reference standard.

8. Sample Size for the Training Set

The document does not specify the sample size for the training set for any of the algorithms or software features. This document is a 510(k) summary, which generally focuses on justification for substantial equivalence rather than detailed algorithm development specifics.

9. How the Ground Truth for the Training Set Was Established

The document does not describe how the ground truth for the training set was established, as it does not provide information about the training set itself.

Ask a specific question about this device

The Marie Imaging System is indicated for the acquisition of CT images and the precise positioning of human patients to facilitate delivery of external beam radiation when integrated with a separate therapy treatment delivery device.

The Marie System is intended to acquire CT images and enable the precise positioning of human patients to facilitate delivery of external beam radiation when integrated with a separate therapy treatment delivery device.

The Marie System is intended to be used by healthcare professionals to image patients in an upright position rather than conventional supine treatments, to enable precise treatment planning and patient positioning for radiotherapy.

Specifically, it is intended to:

• Image the patient to provide image-guided radiation therapy
• Image the patient to acquire images for the purpose of treatment planning
• Immobilize patients in an upright position for upright radiotherapy.

The Marie System is comprised of two major sub-systems: a computed tomography (CT) imaging system that performs pretreatment imaging and treatment simulation in the upright positions and a beam agnostic, patient positioning system that supports the patient in the upright positions.

The Marie Imaging System is used with compatible devices for treatment delivery and patient immobilization. The positioning system is designed with six degrees of freedom of motion and a patient positioning system to provide the desired posture for each cancer site to achieve accurate, reproducible patient setups, while the imaging system acquires helical scans by translating and rotating up the patient.

The provided text solely describes the Leo Cancer Care Marie System as a Computed Tomography X-ray System with its features, safety, and performance details. It outlines the regulatory clearance (FDA 510(k)) based on substantial equivalence to a predicate device (P-ARTIS K160611). It describes the device's characteristics and the non-clinical tests performed to demonstrate its performance and functionality against design and risk management requirements.

Crucially, the provided text does not contain any information about acceptance criteria for AI performance, clinical study design, sample sizes for test or training sets, ground truth establishment using experts, or any MRMC comparative effectiveness studies. The document is a 510(k) clearance summary for a medical device (a CT imaging and patient positioning system), not for an AI diagnostic or assistive software. The "performance testing" section refers to hardware and software system performance, not AI model performance.

Therefore, I cannot answer most of your questions based on the provided input. The questions you've asked are typically relevant for AI/ML-based medical devices or diagnostics that involve image interpretation and require rigorous validation against human expert performance. The Marie System, as described, is a physical imaging system for patient positioning and CT image acquisition, not an AI software.

If this were an AI device, the answers would need to be extracted from sections detailing clinical performance studies, AI model validation, or similar. Since those sections are absent, I am unable to provide the requested information.

Ask a specific question about this device

The uMI Panvivo is a PET/CT system designed for providing anatomical and functional images. The PET provides the distribution of specific radiopharmaceuticals. CT provides diagnostic tomographic anatomical information as well as photon attenuation information for the scanned region. PET and CT scans can be performed separately. The system is intended for assessing metabolic (molecular) and physiologic functions in various parts of the body. When used with radiopharmaceuticals approved by the regulatory authority in the country of use, the uMI Panvivo system generates images depicting the distribution of these radiopharmaceuticals. The images produced by the uMI Panvivo are intended for analysis and interpretation by qualified medical professionals. They can serve as an aid in detection, localization, evaluation, diagnosis, staging, re-staging, monitoring, and/or follow-up of abnormalities, lesions, tumors, inflammation, infection, organ function, disorders, and/or diseases, in several clinical areas such as oncology, cardiology, neurology, infection and inflammation. The images produced by the system can also be used by the physician to aid in radiotherapy treatment planning and interventional radiology procedures.

The CT system can be used for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

The proposed device uMI Panvivo combines a 295/235 mm axial field of view (FOV) PET and 160-slice CT system to provide high quality functional and anatomical images, fast PET/CT imaging and better patient experience. The system includes PET system, CT system, patient table, power distribution unit, control and reconstruction system (host, monitor, and reconstruction computer, system software, reconstruction software), vital signal module and other accessories.

The uMI Panvivo has been previously cleared by FDA via K243538. The main modifications performed on the uMI Panvivo (K243538) in this submission are due to the addition of Deep MAC(also named AI MAC), Digital Gating(also named Self-gating), OncoFocus(also named uExcel Focus and RMC), NeuroFocus(also named HMC), DeepRecon.PET (also named as HYPER DLR or DLR), uExcel DPR (also named HYPER DPR or HYPER AiR)and uKinetics. Details about the modifications are listed as below:

• Deep MAC, Deep Learning-based Metal Artifact Correction (also named AI MAC) is an image reconstruction algorithm that combines physical beam hardening correction and deep learning technology. It is intended to correct the artifact caused by metal implants and external metal objects.

• Digital Gating (also named Self-gating, cleared via K232712) can automatically extract a respiratory motion signal from the list-mode data during acquisition which called data-driven (DD) method. The respiratory motion signal was calculated by tracking the location of center-of-distribution(COD) in body cavity mask. By using the respiratory motion signal, system can perform gate reconstruction without respiratory capture device.

• OncoFocus (also named uExcel Focus and RMC, cleared via K232712) is an AI-based algorithm to reduce respiratory motion artifacts in PET/CT images and at the same time reduce the PET/CT misalignment.

• NeuroFocus (also named HMC) is head motion correction solution, which employs a statistics-based head motion correction method that correct motion artifacts automatically using the centroid-of-distribution (COD) without manual parameter tuning to generate motion free images.

• DeepRecon.PET (also named as HYPER DLR or DLR, cleared via K193210) uses a deep learning technique to produce better SNR (signal-to-noise-ratio) image in post-processing procedure.

• uExcel DPR (also named HYPER DPR or HYPER AiR, cleared via K232712) is a deep learning-based PET reconstruction algorithm designed to enhance the SNR of reconstructed images. High-SNR images improve clinical diagnostic efficacy, particularly under low-count acquisition conditions (e.g., low-dose radiotracer administration or fast scanning protocols).

• uKinetics(cleared via K232712) is a kinetic modeling toolkit for indirect dynamic image parametric analysis and direct parametric analysis of multipass dynamic data. Image-derived input function (IDIF) can be extracted from anatomical CT images and dynamic PET images. Both IDIF and populated based input function (PBIF) can be used as input function of Patlak model to generate kinetic images which reveal biodistribution map of the metabolized molecule using indirect and direct methods.

The provided FDA 510(k) clearance letter describes the uMI Panvivo PET/CT System and mentions several new software functionalities (Deep MAC, Digital Gating, OncoFocus, NeuroFocus, DeepRecon.PET, uExcel DPR, and uKinetics). The document includes performance data for four of these functionalities: DeepRecon.PET, uExcel DPR, OncoFocus, and DeepMAC.

The following analysis focuses on the acceptance criteria and study details for these four AI-based image processing/reconstruction algorithms as detailed in the document. The document presents these as "performance verification" studies.

Overview of Acceptance Criteria and Device Performance (for DeepRecon.PET, uExcel DPR, OncoFocus, DeepMAC)

The document details the evaluation of four specific software functionalities: DeepRecon.PET, uExcel DPR, OncoFocus, and DeepMAC. Each of these has its own set of acceptance criteria and reported performance results, detailed below.

1. Table of Acceptance Criteria and Reported Device Performance

Coefficient of Variation (COV) calculated using uniform cylindrical phantom data on images reconstructed with both uExcel DPR and OSEM methods. | The averaged CR, BV, and CNR of the uExcel DPR images should be superior to those of the OSEM images.

uExcel DPR requires fewer counts to achieve a matched COV compared to OSEM. | Pass.

• NEMA IQ Phantom Analysis: an average noise reduction of 81% and an average SNR enhancement of 391% were observed.
• Uniform cylindrical Analysis: 1/10 of the counts can obtain the matching noise level. |
  | | Qualitative evaluation | uExcel DPR images reconstructed at lower counts qualitatively compared with full-count OSEM images. | uExcel DPR reconstructions with reduced count levels demonstrate comparable or superior image quality relative to higher-count OSEM reconstructions. | Pass.
• 1.72.5 MBq/kg radiopharmaceutical injection conditions, combined with 23 minutes whole-body scanning (4~6 bed positions), achieves comparable diagnostic image quality.
• Clinical evaluation by radiologists showed images sufficient for clinical diagnosis, with uExcel DPR exhibiting lower noise, better contrast, and superior sharpness compared to OSEM. |
  | OncoFocus | Volume relative to no motion correction (∆Volume). | Calculate the volume relative to no motion correction images. | The ∆Volume value is less than 0%. | Pass |
  | | Maximal standardized uptake value relative to no motion correction (∆SUVmax) | Calculate the SUVmax relative to no motion correction images. | The ∆SUVmax value is larger than 0%. | Pass |
  | DeepMAC | Quantitative evaluation | For PMMA phantom data, the average CT value in the affected area of the metal substance and the same area of the control image before and after DeepMAC was compared. | After using DeepMAC, the difference between the average CT value in the affected area of the metal substance and the same area of the control image does not exceed 10HU. | Pass |

2. Sample Sizes Used for the Test Set and Data Provenance

• DeepRecon.PET:

  • Phantoms: NEMA IQ phantoms.
  • Clinical Patients: 20 volunteers.
  • Data Provenance: "collected from various clinical sites" and explicitly stated to be "different from the training data." The document does not specify country of origin or if it's retrospective/prospective, but "volunteers were enrolled" suggests prospective collection for the test set.

• uExcel DPR:

  • Phantoms: Two NEMA IQ phantom datasets, two uniform cylindrical phantom datasets.
  • Clinical Patients: 19 human subjects.
  • Data Provenance: "derived from uMI Panvivo and uMI Panvivo S," "collected from various clinical sites and during separated time periods," and "different from the training data." "Study cohort" and "human subjects" imply prospective collection for the test set.

• OncoFocus:

  • Clinical Patients: 50 volunteers.
  • Data Provenance: "collected from general clinical scenarios" and explicitly stated to be "on cases different from the training data." "Volunteers were enrolled" suggests prospective collection for the test set.

• DeepMAC:

  • Phantoms: PMMA phantom datasets.
  • Clinical Patients: 20 human subjects.
  • Data Provenance: "from uMI Panvivo and uMI Panvivo S," "collected from various clinical sites" and explicitly stated to be "different from the training data." "Volunteers were enrolled" suggests prospective collection for the test set.

3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts

The document does not explicitly state that experts established "ground truth" for the quantitative metrics (e.g., SUV, CNR, BV, CR, ∆Volume, ∆SUVmax, HU differences) for the test sets. These seem to be derived from physical measurements on phantoms or calculations from patient image data using established methods.

• For qualitative evaluation/clinical diagnosis assessment:

  • DeepRecon.PET: Two American Board of Radiologists certified physicians.
  • uExcel DPR: Two American board-certified nuclear medicine physicians.
  • OncoFocus: Two American Board of Radiologists-certified physicians.
  • DeepMAC: Two American Board of Radiologists certified physicians.

  The exact years of experience for these experts are not provided, only their board certification status.

4. Adjudication Method for the Test Set

The document states that the radiologists/physicians evaluated images "independently" (uExcel DPR) or simply "were evaluated by" (DeepRecon.PET, OncoFocus, DeepMAC). There is no mention of an adjudication method (such as 2+1 or 3+1 consensus) for discrepancies between reader evaluations for any of the functionalities. The evaluations appear to be separate assessments, with no stated consensus mechanism.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size of How Much Human Readers Improve with AI vs. Without AI Assistance

• The document describes qualitative evaluations by radiologists/physicians comparing the AI-processed images to conventionally processed images (OSEM/no motion correction/no MAC). These are MRMC comparative studies in the sense that multiple readers evaluated multiple cases.
• However, these studies were designed to evaluate the image quality (e.g., diagnostic sufficiency, noise, contrast, sharpness, lesion detectability, artifact reduction) of the AI-processed images compared to baseline images, rather than to measure an improvement in human reader performance (e.g., diagnostic accuracy, sensitivity, specificity, reading time) when assisted by AI vs. without AI.
• Therefore, the studies were not designed as comparative effectiveness studies measuring the effect size of human reader improvement with AI assistance. They focus on the perceived quality of the AI-processed images themselves.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

• Yes, for DeepRecon.PET, uExcel DPR, OncoFocus, and DeepMAC, quantitative (phantom and numerical) evaluations were conducted that represent the standalone performance of the algorithms in terms of image metrics (e.g., SUV bias, BV, SNR, CNR, CR, COV, ∆Volume, ∆SUVmax, HU differences). These quantitative results are directly attributed to the algorithm's output without human intervention for the measurement/calculation.
• The qualitative evaluations by the physicians (described in point 3 above) also assess the output of the algorithm, but with human interpretation.

7. The Type of Ground Truth Used

• For Quantitative Evaluations:

  • Phantoms: The "ground truth" for phantom studies is implicitly the known physical properties and geometry of the NEMA IQ and PMMA phantoms, allowing for quantitative measurements (e.g., true SUV, true CR, true signal-to-noise).
  • Clinical Data (DeepRecon.PET, uExcel DPR): For these reconstruction algorithms, "ground-truth images were reconstructed from fully-sampled raw data" for the training set. For the test set, comparisons seem to be made against OSEM with Gaussian filtering or full-count OSEM images as reference/comparison points, rather than an independent "ground truth" established by an external standard.
  • Clinical Data (OncoFocus): Comparisons are made relative to "no motion correction images" (∆Volume and ∆SUVmax), implying these are the baseline for comparison, not necessarily an absolute ground truth.
  • Clinical Data (DeepMAC): Comparisons are made to a "control image" without metal artifacts for quantitative assessment of HU differences.

• For Qualitative Evaluations:

  • The "ground truth" is based on the expert consensus / qualitative assessment by the American Board-certified radiologists/nuclear medicine physicians, who compared images for attributes like noise, contrast, sharpness, motion artifact reduction, and diagnostic sufficiency. This suggests a form of expert consensus, although no specific adjudication is described. There's no mention of pathology or outcomes data as ground truth.

8. The Sample Size for the Training Set

The document provides the following for the training sets:

• DeepRecon.PET: "image samples with different tracers, covering a wide and diverse range of clinical scenarios." No specific number provided.
• uExcel DPR: "High statistical properties of the PET data acquired by the Long Axial Field-of-View (LAFOV) PET/CT system enable the model to better learn image features. Therefore, the training dataset for the AI module in the uExcel DPR system is derived from the uEXPLORER and uMI Panorama GS PET/CT systems." No specific number provided.
• OncoFocus: "The training dataset of the segmentation network (CNN-BC) and the mumap synthesis network (CNN-AC) in OncoFocus was collected from general clinical scenarios. Each subject was scanned by UIH PET/CT systems for clinical protocols. All the acquisitions ensure whole-body coverage." No specific number provided.
• DeepMAC: Not explicitly stated for the training set. Only validation dataset details are given.

9. How the Ground Truth for the Training Set Was Established

• DeepRecon.PET: "Ground-truth images were reconstructed from fully-sampled raw data. Training inputs were generated by reconstructing subsampled data at multiple down-sampling factors." This implies that the "ground truth" for training was derived from high-quality, fully-sampled (and likely high-dose) PET data.
• uExcel DPR: "Full-sampled data is used as the ground truth, while corresponding down-sampled data with varying down-sampling factors serves as the training input." Similar to DeepRecon.PET, high-quality, full-sampled data served as the ground truth.
• OncoFocus:
  • For CNN-BC (body cavity segmentation network): "The input data of CNN-BC are CT-derived attenuation coefficient maps, and the target data of the network are body cavity region images." This suggests the target (ground truth) was pre-defined body cavity regions.
  • For CNN-AC (attenuation map (umap) synthesis network): "The input data are non-attenuation-corrected (NAC) PET reconstruction images, and the target data of the network are the reference CT attenuation coefficient maps." The ground truth was "reference CT attenuation coefficient maps," likely derived from actual CT scans.
• DeepMAC: Not explicitly stated for the training set. The mention of pre-trained neural networks suggests an established training methodology, but the specific ground truth establishment is not detailed.

Ask a specific question about this device

The AV Viewer is an advanced visualization software intended to process and display images and associated data in a clinical setting.

The software displays images of different modalities and timepoints, and performs digital image processing, measurement, manipulation, quantification and communication.

The AV Viewer is not to be used for mammography.

AV Viewer is an advanced visualization software which processes and displays clinical images from the following modality types: CT, CBCT – CT format, Spectral CT, MR, EMR, NM, PET, SPECT, US, XA (iXR, DXR), DX, CR and RF.

The main features of the AV Viewer are:
• Viewing of current and prior studies
• Basic image manipulation functions such as real-time zooming, scrolling, panning, windowing, and rolling/rotating.
• Advanced processing tools assisting in the interpretation of clinical images, such as 2D slice view, 2D and 3D measurements, user-defined regions of interest (ROIs), 3D segmentation and editing, 3D models visualization, MPR (multi planar Reconstructions) generation, image fusion and more.
• A finding dashboard used for capturing and displaying findings of the patient as an overview.
• Customized workflows allow the user to create their own workflows
• Tools to export customizable reports to the Radiology Information System (RIS) or PACS (Picture archiving and communication system) in different formats.

AV Viewer is based on the AV Framework, an infrastructure that provides the basis for the AV Viewer and common functionalities such as: image viewing, image editing tools, measurements tools, finding dashboard.

AV viewer can be hosted on multiple platforms and devices, such as Philips AVW, Philips CT/MR scanner console or on cloud.

The provided FDA 510(k) clearance letter for the AV Viewer device indicates that the device has met its acceptance criteria through various verification and validation activities. However, the document does not include detailed quantitative acceptance criteria (e.g., specific thresholds for accuracy, sensitivity, specificity, or measurement error) or comprehensive performance data that would typically be presented in a clinical study report. The submission focuses on demonstrating "substantial equivalence" to a predicate device rather than presenting detailed performance efficacy of the algorithm itself.

Therefore, much of the requested information regarding specific performance metrics, sample sizes for test and training sets, expert qualifications, and detailed study methodologies is not explicitly stated in this 510(k) summary. I will extract and infer what is present and explicitly state when information is missing.

Here's a breakdown based on the provided document:

Acceptance Criteria and Device Performance

The document describes comprehensive verification and validation activities, including "Bench Testing" for measurements and segmentation algorithms. However, specific quantitative acceptance criteria (e.g., "accuracy > 95%") and the reported performance values are not detailed in this summary. The general statement is that "Product requirement specifications were tested and found to meet the requirements" and "The validation objectives have been fulfilled, and the validation results provide evidence that the product meets its intended use and user requirements."

Table of Acceptance Criteria and Reported Device Performance

Note: The quantitative details for the "Acceptance Criteria" and "Reported Device Performance" for measurement accuracy and segmentation accuracy are missing from this 510(k) summary. The document only confirms that these tests were performed and the results were positive.

Study Details Based on the Provided Document:

2. Sample sizes used for the test set and the data provenance (e.g., country of origin of the data, retrospective or prospective)

• Test Set Sample Size: Not explicitly stated. The document mentions "Verification," "Validation," "Expert Test," and "Bench Testing" were performed, implying the use of test data, but no specific number of cases or images in the test set is provided.
• Data Provenance: Not explicitly stated. The document does not specify the country of origin of the data used for testing, nor does it explicitly state whether the data was retrospective or prospective.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts

• Number of Experts: Not explicitly stated. The "Expert Test" mentions "a clinical expert" (singular) was used to test use case scenarios. It does not mention experts establishing ground truth for broader validation.
• Qualifications of Experts: The "Expert Test" mentions "a clinical expert." For intended users, the document states "trained professionals, including but not limited to, physicians and medical technicians" (Subject Device), and "trained professionals, including but not limited to radiologists" (Predicate Device). It can be inferred that the "clinical expert" would hold one of these qualifications, but specific details (e.g., years of experience, subspecialty) are not provided.

4. Adjudication method (e.g., 2+1, 3+1, none) for the test set

• Adjudication Method: Not explicitly stated. The document refers to "Expert test" where "a clinical expert" tested scenarios, implying individual assessment rather than a multi-reader adjudication process for establishing ground truth for a test set.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• MRMC Comparative Effectiveness Study: Not explicitly stated or implied. The document focuses on the device's substantial equivalence to a predicate device and its internal verification and validation. There is no mention of a human-in-the-loop MRMC study to compare reader performance with and without AV Viewer assistance. The AV Viewer is described as an "advanced visualization software" and not specifically an AI-driven diagnostic aid that would typically warrant such a study for demonstrating improved reader performance.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• Standalone Performance Study: The "Bench Testing" section states that it "was performed on the measurements and segmentation algorithms to validate their performance and the correctness of the various measurement functions." This implies a standalone evaluation of these specific algorithms. However, the quantitative results (e.g., accuracy, precision) of this standalone performance are not provided.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)

• Type of Ground Truth: For the "Bench Testing" of measurement and segmentation algorithms, the ground truth would likely be based on reference measurements/segmentations, possibly done manually by experts or using highly accurate, non-clinical methods. For other verification/validation activities, the ground truth would be against the pre-defined product and user requirements. However, explicit details about how this ground truth was established (e.g., expert consensus, comparison to gold standard devices/methods) are not specified.

8. The sample size for the training set

• Training Set Sample Size: Not explicitly stated. The document does not mention details about the training data used to develop the AV Viewer's algorithms. The focus is on validation for regulatory clearance. Since the product is primarily an "advanced visualization software" with general image processing tools, much of its functionality might not rely on deep learning requiring large, distinct training sets in the same way a specific AI diagnostic algorithm would.

9. How the ground truth for the training set was established

• Ground Truth for Training Set: Not explicitly stated. As no training set details are provided, the method for establishing its ground truth is also not mentioned.

Summary of Missing Information:

This 510(k) summary provides a high-level overview of the device's intended use, comparison to a predicate, and the types of verification and validation activities conducted. It largely focuses on demonstrating "substantial equivalence" based on similar indications for use and technological characteristics. Critical quantitative details about the performance of specific algorithms (measurements, segmentation), the size and characteristics of the datasets used for testing, and the methodology for establishing ground truth are not included in this public summary. Such detailed performance data is typically found in the full 510(k) submission, which is not publicly released in its entirety.

Ask a specific question about this device

This computed tomography system is intended to generate and process cross-sectional images of patients by computer reconstruction of X-ray transmission data.

The images delivered by the system can be used by a trained staff as an aid in diagnosis, treatment, and radiation therapy planning as well as for diagnostic and therapeutic interventions.

This CT system can be used for low dose lung cancer screening in high risk populations*.

*As defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

Siemens intends to market a new software version, SOMARIS/10 syngo CT VB20 for the following SOMATOM Computed Tomography (CT) Scanner Systems:

a) Single Source CT Scanner systems (SOMATOM go. Platform):

• SOMATOM go.Now
• SOMATOM go.Up
• SOMATOM go.All
• SOMATOM go.Top
• SOMATOM go.Sim
• SOMATOM go.Open Pro

In this submission, the above listed CT scanner systems are jointly referred to as subject devices by "SOMATOM go. Platform" CT scanner systems.

b) Dual Source CT Scanner system:

• SOMATOM Pro.Pulse

The above listed subject devices with SOMARIS/10 syngo CT VB20 are Computed Tomography X-ray Systems which feature one (Single Source) or two (Dual Source) continuously rotating tube-detector system and function according to the fan beam principle. The SOMATOM go. Platform and the SOMATOM Pro.Pulse with software SOMARIS/10 syngo CT VB20 produce CT images in DICOM format, which can be used by trained staff for software applications, e.g. post-processing applications, commercially distributed by Siemens Healthcare and other vendors as an aid in diagnosis, treatment preparation and therapy planning support (including, but not limited to, Brachytherapy, Particle including Proton Therapy, External Beam Radiation Therapy, Surgery). The computer system delivered with the CT scanner is able to run optional post processing applications.

The provided FDA 510(k) Clearance Letter for the SOMATOM CT Systems focuses heavily on establishing substantial equivalence to predicate devices through comparisons of technological characteristics, hardware, and software. It generally asserts that the device has met performance criteria through verification and validation testing, but it does not provide a detailed "Acceptance Criteria Table" with specific quantitative metrics and reported device performance. Similarly, it describes the types of studies performed (e.g., bench testing, retrospective blinded rater study), but it lacks the specific details requested regarding sample sizes, data provenance, expert qualifications, and effect sizes that would typically be found in a detailed study report.

Therefore, I will extract and synthesize the information that is available in the document and explicitly state where the requested information is not provided.

Understanding the Device and its Changes

The devices under review are Siemens SOMATOM CT Systems (SOMATOM go.Now, SOMATOM go.Up, SOMATOM go.All, SOMATOM go.Top, SOMATOM go.Sim, SOMATOM go.Open Pro, and SOMATOM Pro.Pulse) with a new software version, SOMARIS/10 syngo CT VB20. This new software version builds upon the previous VB10 version cleared in K233650 and K232206.

The submission focuses on modifications and new features introduced with VB20, including:

• Eco Power Mode: New feature for reduced energy consumption during idle times (not supported on go.Now and go.Up).
• Oncology Exchange: New feature for transferring prescription information from ARIA Oncology Information System.
• myExam Contrast: New feature for exchanging contrast injection parameters.
• FAST 3D Camera/FAST Integrated Workflow: Modifications including retrained algorithms, collision indication, and Centerline/Grid Overlay.
• FAST Planning: Extended to detect additional body regions.
• myExam Companion (myExam Compass/myExam Cockpit): Clinical decision trees now available for child protocols.
• HD FoV 5.0: New extended field of view reconstruction algorithm (for go.Sim and go.Open Pro only).
• CT guided intervention – myAblation Guide interface: New interface.
• Flex 4D Spiral: Modifications regarding dynamic tube current modulation.
• ZeeFree RT: New stack artifact reduced reconstruction for respiratory-related examinations (for go.Open Pro only).
• DirectDensity: Modified to include stopping-power ratio (Kernel St).
• DirectLaser: Patient Marking workflow improvement.
• Respiratory Motion management - Open Online Interface: New interface for respiratory gating.
• DirectSetup Notes: Enabled for certain SOMATOM go. Platform systems.

The core argument for clearance is substantial equivalence to predicate devices. This means that, despite modifications, the device is as safe and effective as a legally marketed device (the predicates).

1. Table of Acceptance Criteria and Reported Device Performance

The provided document does not contain a specific table of quantitative acceptance criteria with corresponding reported device performance values. Instead, it describes general acceptance criteria related to verification and validation tests and then provides qualitative statements about the test results demonstrating comparability or improvement over predicate devices.

Here's a summary of the described performance evaluations:

2. Sample Sizes Used for the Test Set and Data Provenance

The document provides very limited, qualitative information:

• FAST 3D Camera: Optimized using "additional data from adults and adolescence patients." No specific number of patients or images mentioned.
• FAST Planning: Evaluated on "patient data." No specific number of patients or images mentioned.
• HD FoV 5.0: Evaluated with "physical and anthropomorphic phantoms."
• Flex 4D Spiral: No specific sample size or data type mentioned for performance assessment.
• ZeeFree RT: Evaluated with "homogeneous water phantom," "phantom with tissue-equivalent inserts," "static torso phantom," and "dynamic thorax phantom." Also, "retrospective blinded rater studies of respiratory 4D CT examinations performed at two institutions." No specific number of phantoms, images per phantom, or patient cases mentioned.
• DirectDensity: Evaluated on "SOMATOM CT scanner models." No specific sample size or data type mentioned.

Data Provenance:

• Country of Origin: Not specified for the patient data used for algorithm optimization/validation.
• Retrospective or Prospective:
  • FAST 3D Camera: Implied retrospective as it uses "additional data."
  • FAST Planning: Implied retrospective as it uses "patient data."
  • HD FoV 5.0: Retrospective for the blinded rater study.
  • ZeeFree RT: Retrospective for the blinded rater study of clinical cases. The phantom tests are by nature not retrospective/prospective.

3. Number of Experts and Qualifications for Ground Truth

• HD FoV 5.0: "board-approved radio-oncologists and medical physicists." The number of experts is not specified.
• ZeeFree RT: "board-approved radio-oncologists and medical physicists." The number of experts is not specified.

For other tests, ground truth appears to be established by phantom measurements or internal engineering verification, rather than human expert reads validating clinical ground truth.

4. Adjudication Method for the Test Set

The document mentions "retrospective blinded rater study" for HD FoV 5.0 and ZeeFree RT. However, it does not specify the adjudication method used (e.g., 2+1, 3+1, none) for these studies. It only states they were "blinded."

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• A Multi-Reader Multi-Case (MRMC) comparative effectiveness study was mentioned for HD FoV 5.0 and ZeeFree RT. Both were "retrospective blinded rater studies."
• Effect Size: The document does not report specific effect sizes (e.g., how much human readers improve with AI vs. without AI assistance). It only states that the purpose of the comparison was to "demonstrate that the HD FoV 5.0 algorithm is as safe and effective as the HD FoV 4.0 algorithm" and for ZeeFree RT that it "enables the optional reconstruction of stack artefact corrected images, which reduce the strength of misalignment artefacts." This implies an assessment of non-inferiority or improvement in image quality, but specific quantitative results for reader performance are not provided in this excerpt.

6. Standalone (Algorithm Only) Performance

The document describes tests for several algorithms (FAST 3D Camera, FAST Planning, HD FoV 5.0, Flex 4D Spiral, ZeeFree RT, DirectDensity) using phantoms and "patient data." These evaluations seem to be focused on the algorithm's performance in generating images or calculations, independent of human interpretation in some cases (e.g., accuracy of FAST 3D Camera, correctness percentage of FAST Planning).

However, it does not explicitly use the term "standalone performance" to differentiate these from human-in-the-loop assessments. The mention of "retrospective blinded rater studies" for HD FoV 5.0 and ZeeFree RT indicates a human-in-the-loop component for that specific evaluation, but the phantom testing mentioned alongside them would be considered standalone.

7. Type of Ground Truth Used

• Phantom Data: For HD FoV 5.0, Flex 4D Spiral, ZeeFree RT, and DirectDensity, physical and/or anthropomorphic phantoms were used, implying the ground truth is precisely known physical characteristics or pre-defined phantom configurations.
• Expert Consensus/Reads: For HD FoV 5.0 and ZeeFree RT, board-approved radio-oncologists and medical physicists performed retrospective blinded rater studies, implying their interpretations/ratings served as a form of ground truth or evaluation metric. It's not explicitly stated if this was against a clinical gold standard (e.g., pathology) or if it was a comparative assessment of image quality and clinical utility.
• Internal Verification: For FAST 3D Camera, FAST Planning, accuracy was assessed, likely against internal system metrics or pre-defined ideal outcomes.

8. Sample Size for the Training Set

The document does not provide any specific information about the sample size used for training the algorithms (e.g., for FAST 3D Camera, FAST Planning, HD FoV 5.0, ZeeFree RT). It only states that FAST 3D Camera was "optimized using additional data" and FAST Planning's algorithm had "product development, validation, and verification on patient data."

9. How the Ground Truth for the Training Set Was Established

The document does not provide any specific information on how the ground truth for the training set was established. It only mentions the data types used for validation/verification (phantoms, patient data from two institutions, expert raters).

Ask a specific question about this device

The Siemens Biograph systems are combined X-Ray Computed Tomography (CT) and Positron Emission Tomography (PET) scanners that provide registration and fusion of high resolution physiologic and anatomic information.

The CT component produces cross-sectional images of the body by computer reconstruction of X-Ray transmission data from either the same axial plane taken at different angles or spiral planes taken at different angles. The PET subsystem images and measures the distribution of PET radiopharmaceuticals in humans for the purpose of determining various metabolic (molecular) and physiologic functions within the human body and utilizes the CT for fast attenuation correction maps for PET studies and precise anatomical reference for the fused PET and CT images.

The system maintains independent functionality of the CT and PET devices, allowing for single modality CT and/or PET diagnostic imaging.

These systems are intended to be utilized by appropriately trained health care professionals to aid in detecting, localizing, diagnosing, staging, and restaging of lesions, tumors, disease, and organ function for the evaluation of diseases and disorders such as, but not limited to, cardiovascular disease, neurological disorders, and cancer. The images produced by the system can also be used by the physician to aid in radiotherapy treatment planning and interventional radiology procedures.

This CT system can be used for low dose lung cancer screening in high risk populations. *

• As defined by professional medical societies. Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365; 395-409) and subsequent literature, for further information.

The Biograph Vision and Biograph mCT PET/CT systems are combined multi-slice X-Ray Computed Tomography and Positron Emission Tomography scanners. These systems are designed for whole-body oncology, neurology and cardiology examinations. The Biograph Vision and Biograph mCT systems provide registration and fusion of high-resolution metabolic and anatomic information from the two major components of each system (PET and CT). Additional components of the system include a patient handling system and acquisition and processing workstations with associated software.

Biograph Vision and Biograph mCT software is a command-based program used for patient management, data management, scan control, image reconstruction and image archival and evaluation. All images conform to DICOM imaging format requirements.

The software for the Biograph Vision and Biograph mCT systems, which are the subject of this application, is substantially equivalent to the commercially available Biograph Vision and Biograph mCT software.

• Somaris Software (cleared in K230421)
  • Upgrade to the latest revision of Somaris Software (Somaris/7 syngo CT VB30) with modified software features:
    • FAST Bolus
    • FAST 4D
    • FAST Applications (FAST Spine, FAST Planning)
    • Automatic Patient Instructions
    • Additional default exam protocols
    • Additional kV setting for Tin Filtration
• PETsyngo software
  • SMART Image Framer (available for Vision 600 and X models only – cleared in K223547)
• Updated computer hardware due to obsolescence issues (cleared in K230421). These changes do not affect system performance characteristics and have no impact on safety or effectiveness.

The Biograph Vision may also use the names Biograph Vision Quantum and Peak for marketing purposes.

Here's an analysis of the provided FDA 510(k) clearance letter for Siemens Biograph Vision and mCT PET/CT Systems, focusing on acceptance criteria and the study that proves the device meets them:

1. Table of Acceptance Criteria and Reported Device Performance

The provided document describes the performance of the updated software (VG85) for the Siemens Biograph Vision and Biograph mCT PET/CT Systems, comparing it to the predicate device (VG80). The "Acceptance Criteria" for the subject device are explicitly stated as "Same" as the predicate device's performance values. This implies that the updated system must perform at least as well as the predicate device across all tested metrics.

Ask a specific question about this device

The Philips iCT CT systems is a Computed Tomography X-Ray System intended to produce images of the head and body by computer reconstruction of x-ray transmission data taken at different angles and planes. These devices may include signal analysis and display equipment, patient and equipment supports, components and accessories. The iCT is indicated for head, whole body, cardiac and vascular X-ray Computed Tomography applications in patients of all ages.

These scanners are intended to be used for diagnostic imaging and for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer*. The screening must be performed within the established inclusion criteria of programs / protocols that have been approved and published by either a governmental body or professional medical society.

*Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

The Philips iCT CT System is a whole-body computed tomography (CT) X-ray system designed for diagnostic imaging. It features a continuously rotating X-ray tube and multi-slice detector gantry, enabling the acquisition of X-ray transmission data from multiple angles and planes. The system reconstructs these data into cross-sectional images using advanced image reconstruction algorithms, supporting a wide range of clinical applications.

The system consists of a gantry, which houses the rotating X-ray tube, detector array, and key imaging subsystems; a patient support couch, which moves the patient through the gantry bore in synchronization with the scan and is available in multiple configurations; an operator console, which serves as the primary user interface for system controls, image processing, and data management; and a Data Measurement System (DMS), which captures X-ray attenuation data to support high-quality image reconstruction.

The provided FDA 510(k) clearance letter for the Philips iCT CT System (K250648) focuses on demonstrating substantial equivalence to a predicate device (K162838) based on hardware and software enhancements.

However, there is no information within this document that describes specific acceptance criteria in terms of algorithm performance metrics (e.g., sensitivity, specificity, AUC) for an AI/ML-driven diagnostic task, nor does it detail a study proving the device meets such criteria in a clinical context.

The document primarily addresses:

• Physical and technical characteristics of the CT system (e.g., spatial resolution, low contrast resolution, noise, scan speeds).
• Safety and performance of system modifications (e.g., OS upgrade, cybersecurity enhancements, new phantom kit) through non-clinical verification and validation activities.
• Substantial equivalence to a predicate device based on these engineering and system-level tests.

The mention of "low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer" refers to a general indication for the CT system itself, not a specific AI/ML diagnostic algorithm for nodule detection or characterization within the system. The note to "refer to clinical literature, including the results of the National Lung Screening Trial" further supports that the clinical efficacy of CT for lung screening is established and not being re-proven by this submission for a new AI feature.

Therefore, I cannot populate the requested table or answer the specific questions about AI/ML study design directly from the provided text, as this information is not present. The document focuses on the CT scanner as the device, not a specific AI-powered diagnostic algorithm within it that would require the detailed studies outlined in your request.

If the "Philips iCT CT System" were to include an AI component with an explicit diagnostic function beyond general image acquisition and display, the FDA submission would typically contain a dedicated section on its performance evaluation, including the types of studies you are asking about. This document does not describe such an AI component or its associated clinical performance study.

Ask a specific question about this device