Search Results

The SIGNA™ Sprint is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan times. It is indicated for use as a diagnostic imaging device to produce axial, sagittal, coronal, and oblique images, spectroscopic images, parametric maps, and/or spectra, dynamic images of the structures and/or functions of the entire body, including, but not limited to, head, neck, TMJ, spine, breast, heart, abdomen, pelvis, joints, prostate, blood vessels, and musculoskeletal regions of the body. Depending on the region of interest being imaged, contrast agents may be used.

The images produced by SIGNA™ Sprint reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance. These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

SIGNA™ Sprint is a whole-body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan time. The system uses a combination of time-varying magnet fields (Gradients) and RF transmissions to obtain information regarding the density and position of elements exhibiting magnetic resonance. The system can image in the sagittal, coronal, axial, oblique, and double oblique planes, using various pulse sequences, imaging techniques and reconstruction algorithms. The system features a 1.5T superconducting magnet with 70cm bore size. The system is designed to conform to NEMA DICOM standards (Digital Imaging and Communications in Medicine).

Key aspects of the system design:

• Uses the same magnet as a conventional whole-body 1.5T system, with integral active shielding and a zero boil-off cryostat.
• A gradient coil that achieves up to 65 mT/m peak gradient amplitude and 200 T/m/s peak slew rate.
• An embedded body coil that reduces thermal and enhance intra-bore visibility.
• A newly designed 1.5T AIR Posterior Array.
• A detachable patient table.
• A platform software with various PSD and applications, including the following AI features:
  • AIRx™ (Cleared in K183231)
  • AIR™ Recon DL (Cleared in K202238)
  • Sonic DL™ (Cleared in K223523)

The provided text is a 510(k) clearance letter and summary for a new MRI device, SIGNA™ Sprint. It states explicitly that no clinical studies were required to support substantial equivalence. Therefore, the information requested regarding acceptance criteria, study details, sample sizes, ground truth definitions, expert qualifications, and MRMC studies is not available in this document.

The document highlights the device's technical equivalence to a predicate device (SIGNA™ Premier) and reference devices (SIGNA™ Artist, SIGNA™ Champion) and relies on non-clinical tests and sample clinical images to demonstrate acceptable diagnostic performance.

Here's a breakdown of what can be extracted from the document regarding testing, and why other requested information is absent:

1. A table of acceptance criteria and the reported device performance

• Acceptance Criteria (Implicit): The document states that the device's performance is demonstrated through "bench testing and clinical testing that show the image quality performance of SIGNA™ Sprint compared to the predicate device." It also mentions "acceptable diagnostic image performance... in accordance with the FDA Guidance 'Submission of Premarket Notifications for Magnetic Resonance Diagnostic Devices' issued on October 10, 2023."
  • Specific quantitative acceptance criteria (e.g., minimum SNR, CNR, spatial resolution thresholds) are not explicitly stated in this document.
• Reported Device Performance: "The images produced by SIGNA™ Sprint reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance. These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis."
  • No specific quantitative performance metrics (e.g., sensitivity, specificity, accuracy, or detailed image quality scores) are provided in this regulatory summary. The statement "The image quality of the SIGNA™ Sprint is substantially equivalent to that of the predicate device" is the primary performance claim.

2. Sample size 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 applicable/Not provided. The document explicitly states: "The subject of this premarket submission, the SIGNA™ Sprint, did not require clinical studies to support substantial equivalence."
• Data Provenance: Not applicable/Not provided for a formal clinical test set. The document only mentions "Sample clinical images have been included in this submission," but does not specify their origin or nature beyond being "sample."

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not applicable. Since no formal clinical study was conducted for substantial equivalence, there was no "test set" requiring ground truth established by experts in the context of an effectiveness study. The "interpretation by a trained physician" is mentioned in the Indications for Use, which is general to MR diagnostics, not specific to a study.

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

• Not applicable. No clinical test set requiring adjudication was conducted for substantial equivalence.

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

• No. The document explicitly states: "The subject of this premarket submission, the SIGNA™ Sprint, did not require clinical studies to support substantial equivalence." While the device incorporates AI features cleared in other submissions (AIRx™, AIR™ Recon DL, Sonic DL™), this specific 510(k) for the SIGNA™ Sprint system itself does not include an MRMC study or an assessment of human reader improvement with these integrated AI features. The focus is on the substantial equivalence of the overall MR system.

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

• No, not for the SIGNA™ Sprint as a whole system. This 510(k) is for the MR scanner itself, not for a standalone algorithm. Any standalone performance for the integrated AI features (AIRx™, AIR™ Recon DL, Sonic DL™) would have been part of their respective clearance submissions (K183231, K202238, K223523), not this one.

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

• Not applicable. No formal clinical study requiring ground truth was conducted for this submission.

8. The sample size for the training set

• Not applicable/Not provided. This submission is for the SIGNA™ Sprint MR system itself, not a new AI algorithm requiring a training set developed for this specific submission. The AI features mentioned (AIRx™, AIR™ Recon DL, Sonic DL™) were cleared in previous 510(k)s and would have had their own training and validation processes.

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

• Not applicable/Not provided. As explained in point 8, this submission does not detail the training of new AI algorithms.

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

Sonic DL is a Deep Learning based reconstruction technique that is available for use on GE HealthCare 1.5T, 3.0T, and 7.0T MR systems. Sonic DL reconstructs MR images from highly under-sampled data, and thereby enables highly accelerated acquisitions. Sonic DL is intended for imaging patients of all ages. Sonic DL is not limited by anatomy and can be used for 2D cardiac cine imaging and 3D Cartesian imaging using fast spin echo and gradient echo sequences. Depending on the region of interest, contrast agents may be used.

Sonic DL is a software feature intended for use with GE HealthCare MR systems. It includes a deep learning based reconstruction algorithm that enables highly accelerated acquisitions by reconstructing MR images from highly under-sampled data. Sonic DL is an optional feature that is integrated into the MR system software and activated through purchasable software option keys.

Here's a breakdown of the acceptance criteria and the study details for Sonic DL, based on the provided FDA 510(k) clearance letter:

Acceptance Criteria and Device Performance for Sonic DL

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly list specific quantitative "acceptance criteria" against which a single "reported device performance" is measured in a pass/fail manner for all aspects. Instead, it presents various performance metrics and qualitative assessments that demonstrate the device's acceptable performance compared to existing standards and its stated claims. For the sake of clarity, I've summarized the implied acceptance thresholds or comparative findings from the quantitative studies and the qualitative assessments.

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

• Quantitative Post Processing Test Set:
  • Sample Size: 15 fully-sampled datasets.
  • Data Provenance: Retrospective, acquired at GE HealthCare in Waukesha, USA, from 1.5T, 3.0T, and 7.0T scanners.
• Clinical Evaluation Studies (Likert-score based):
  • Study 1 (Brain, Spine, Extremities):
    • Number of image series evaluated: 120 de-identified cases.
    • Number of unique subjects: 54 subjects (48 patients, 6 healthy volunteers).
    • Age range: 11-80 years.
    • Gender: 26 Male, 28 Female.
    • Pathology: Mixture of small, large, focal, diffuse, hyper- and hypo-intense lesions.
    • Contrast: Used in a subset as clinically indicated.
    • Data Provenance: Retrospective and prospective (implied by "obtained from clinical sites and from healthy volunteers scanned at GE HealthCare facilities"). Data collected from 7 sites (4 in United States, 3 outside of United States).
  • Study 2 (Brain):
    • Number of additional cases: 120 cases.
    • Number of unique subjects: From 30 fully-sampled acquisitions.
    • Data Provenance: Retrospective, collected internally at GE HealthCare, 1.5T, 3.0T, and 7.0T field strengths.

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

• Quantitative Post Processing: The "ground truth" here is the fully sampled data and the quantitative measurements derived from it. No human experts are explicitly mentioned for establishing this computational 'ground truth'.
• Clinical Evaluation Studies:
  • Study 1: 3 radiologists. Their specific qualifications (e.g., years of experience, subspecialty) are not provided in the document.
  • Study 2: 3 radiologists. Their specific qualifications are not provided in the document.

4. Adjudication Method for the Test Set

The document does not explicitly state a formal adjudication method (like 2+1 or 3+1). For the clinical evaluation studies, it mentions that "three radiologists were asked to evaluate the diagnostic quality of images" and "radiologists were also asked to comment on the presence of any pathology." This suggests individual assessments were either aggregated, or findings were considered concordant if a majority agreed, but a specific arbitration or adjudication process for disagreements is not detailed.

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

• Was an MRMC study done? Yes, the two Likert-score based clinical studies involved multiple readers (3 radiologists) evaluating multiple cases (120 de-identified cases in Study 1 and 120 additional cases in Study 2) for comparative effectiveness against ARC + HyperSense.
• Effect size of human readers improvement with AI vs. without AI assistance: The document states that "Sonic DL 3D images are of diagnostic quality while yielding a substantial reduction in the scan time compared to ARC + HyperSense images." It also noted that "pathology seen in the ARC + HyperSense images can be accurately retained in Sonic DL 3D images." However, it does not quantify the effect size of how much human readers improve with AI assistance (Sonic DL) versus without it. Instead, the studies aim to demonstrate non-inferiority or comparable diagnostic quality despite acceleration. There's no performance gain stated explicitly for the human reader in terms of diagnostic accuracy or confidence when using Sonic DL images compared to conventional images; rather, the benefit is in maintaining diagnostic quality with faster acquisition.

6. Standalone (Algorithm Only) Performance Study

• Was a standalone study done? Yes, extensive non-clinical testing was performed as a standalone assessment of the algorithmic performance. This included evaluations using:
  • Digital reference objects (DROs) and MR scans of physical ACR phantoms to measure PSNR, RMSE, SSIM, resolution, and low contrast detectability.
  • A task-based study using a convolutional neural network ideal observer (CNN-IO) to quantify low contrast detectability.
  • Reconstruction of in vivo datasets with unseen data inserted to assess model stability and hallucination risk.
    These studies directly evaluated the algorithm's output metrics and behavior independently of human interpretation in a clinical workflow, making them standalone performance assessments.

7. Type of Ground Truth Used

• Non-Clinical Testing:
  • Quantitative Metrics (PSNR, RMSE, SSIM, Resolution, Contrast Detectability): Fully sampled data was used as the reference "ground truth" against which the under-sampled and reconstructed Sonic DL 3D images were compared.
  • Model Stability (Hallucination): The "ground truth" was the original in vivo datasets before inserting previously unseen data, allowing for evaluation of whether the algorithm introduced artifacts or hallucinations.
• Quantitative Post Processing (Clinical Testing):
  • Fully sampled data sets were used as the reference for comparison of volumetric measurements with Sonic DL 3D and ARC + HyperSense images.
• Clinical Evaluation Studies (Likert-score based):
  • The implied "ground truth" was the diagnostic quality and presence/absence of pathology as assessed by the conventional ARC + HyperSense images, which were considered the clinical standard for comparison. The radiologists were essentially comparing Sonic DL images against the standard of care images without a separate, absolute ground truth like pathology for every lesion.

8. Sample Size for the Training Set

The document does not specify the sample size used for training the Sonic DL 3D deep learning model. It only mentions that Sonic DL is a "Deep Learning based reconstruction technique" and includes a "deep learning convolutional neural network."

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. It is standard practice for supervised deep learning models like Sonic DL to be trained on pairs of under-sampled and corresponding fully-sampled or high-quality (e.g., conventionally reconstructed) images, where the high-quality image serves as the 'ground truth' for the network to learn to reconstruct from the under-sampled data. However, the specifics of this process (e.g., data types, annotation, expert involvement) are not mentioned in this document.

Ask a specific question about this device

The SIGNA Prime Elite is a whole body magnetic resonance scanner designed to support high signal-to-noise ratio, and short scan times. It is indicated for use as a diagnostic imaging device to produce axial, sagittal, coronal, and oblique images, spectroscopic images, parametric maps, and/or spectra, dynamic images of the structures and/or functions of the entire body, including, but not limited to, head, neck, heart, abdomen, pelvis, joints, prostate, blood vessels, and musculoskeletal regions of the body.

Depending on the region of interest being imaged, contrast agents may be used. The images produced by SIGNA Prime Elite reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance.

These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis.

SIGNA Prime Elite is a whole body magnetic resonance scanner designed to support high resolution, high signal-to-noise ratio, and short scan time. The system uses a combination of time-varying magnet fields (Gradients) and RF transmissions to obtain information regarding the density and position of elements exhibiting magnetic resonance. The system can image in the sagittal, coronal, axial, oblique, and double oblique planes, using various pulse sequences, imaging techniques and reconstruction algorithms. The system features a 1.5T superconducting magnet with 60 cm bore size. The system is designed to conform to NEMA DICOM standards (Digital Imaging and Communications in Medicine).

The document does not provide a table of acceptance criteria and reported device performance. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting specific quantitative performance metrics against pre-defined acceptance criteria.

Here's an analysis of the provided information concerning acceptance criteria and study details:

1. A table of acceptance criteria and the reported device performance

The document does not contain a specific table outlining quantitative acceptance criteria and corresponding reported device performance metrics. It indicates that the SIGNA Prime Elite's image quality performance was compared to the predicate device through bench and clinical testing and found to be "substantially equivalent."

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

The document states: "The subject of this premarket submission, the SIGNA Prime Elite, did not require clinical studies to support substantial equivalence. Sample clinical images have been included in this submission."

Therefore, there is no formal test set sample size mentioned for a specific clinical performance study. The "sample clinical images" are used to demonstrate acceptable diagnostic image performance, but details about their sample size, provenance (country of origin), or whether they are retrospective or prospective are not provided.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

Since no formal clinical study with a defined test set and ground truth establishment is described, this information is not provided. The document mentions that images "when interpreted by a trained physician yield information that may assist in diagnosis," but it doesn't specify expert review for a test set.

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

As there is no formal test set described for a clinical performance study, an adjudication method is not applicable and not mentioned.

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

The document states that the SIGNA Prime Elite is a "whole body magnetic resonance scanner." There is no mention of AI assistance or a multi-reader multi-case (MRMC) comparative effectiveness study comparing human readers with and without AI assistance. The submission is for an imaging device, not an AI-powered diagnostic tool.

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

This question is not applicable as the device is a magnetic resonance scanner, not an algorithm that operates standalone without human interpretation.

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

Given that clinical studies were not required and only "sample clinical images" were included to demonstrate acceptable diagnostic image performance, there is no mention of a formally established ground truth type (e.g., expert consensus, pathology, outcomes data) for a test set. The images are expected to be interpreted by a "trained physician."

8. The sample size for the training set

The document describes the SIGNA Prime Elite as a new 1.5T MR system. It is a hardware device with associated software, not a machine learning model. Therefore, the concept of a "training set" in the context of machine learning is not applicable and not mentioned.

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

As the device is an MR scanner and not an AI/ML model requiring a training set, this information is not applicable and not provided.

Ask a specific question about this device

SIGNA MAGNUS system is a head-only magnetic resonance scanner designed to support high resolution, high signal-tonoise ratio, diffusion-weighted imaging, and short scan times. SIGNA MAGNUS is indicated for use as a diagnostic imaging device to produce axial, sagittal, coronal, and oblique images, parametric maps, and/or spectra, dynamic images of the structures and/or functions of the head, neck, TMJ, and limited cervical spine on patients 6 years of age and older. Depending on the region of interest being imaged, contrast agents may be used.

The images produced by SIGNA MAGNUS reflect the spatial distribution or molecular environment of nuclei exhibiting magnetic resonance. These images and/or spectra, when interpreted by a trained physician, yield information that may assist in diagnosis.

SIGNA MAGNUS is a 3.0T high-performance magnetic resonance imaging system designed to support imaging of the head, neck, TMJ and limited cervical spine. The system supports scanning in axial, coronal, sagittal, oblique, and double oblique planes using a variety of pulse sequences, imaging techniques, acceleration methods, and reconstruction algorithms. The system can be delivered as a new system installation, or as an upgrade to existing compatible whole-body 3.0T MR

Key aspects of the system design:
• An asymmetrically designed, head-only gradient coil that achieves up to 300 mT/m peak gradient amplitude and 750 T/m/s peak slew rate.
• A graduated patient bore size, starting at 74 cm at the entry down to 37 cm at isocenter.
• Uses the same magnet as a conventional whole-body 3.0T system, with integral active shielding and a zero boil-off cryostat.
• Can be installed as a new system or upgraded from an existing compatible whole-body 3.0T MR system.
• A dockable mobile patient table.
• Oscillating Diffusion Encoding (ODEN) - a spectral diffusion technique that uses a sinusoidal diffusion gradient waveform.

The provided text is a 510(k) Summary for the GE Healthcare SIGNA MAGNUS, a magnetic resonance diagnostic device. The summary indicates that this device did not require clinical studies to support substantial equivalence. Therefore, there are no acceptance criteria, performance metrics, sample sizes for test/training sets, expert qualifications, or other details related to clinical performance studies to report for this device, as these were not performed or deemed necessary by the manufacturer for this submission.

The document states:
"The subject of this premarket submission, SIGNA MAGNUS did not require clinical studies to support substantial equivalence. Sample clinical images have been included in this submission. The sample clinical images demonstrate acceptable diagnostic image performance of SIGNA MAGNUS in accordance with the FDA Guidance 'Submission of Premarket Notifications fo October 10, 2023. The image quality of SIGNA MAGNUS is substantially equivalent to that of the predicate device."

This means that the substantial equivalence was primarily based on non-clinical tests and a comparison of technological characteristics and indications for use with a predicate device (SIGNA Premier (K193282)). The non-clinical tests focused on safety and performance in compliance with various voluntary standards (e.g., ANSI AAMI ES60601-1, IEC 60601-1-2, IEC 60601-2-33, IEC 62304, IEC 60601-1-6, IEC 62366-1, IEC62464-1, ISO 10993-1, NEMA MS, NEMA PS3 DICOM).

Due to the absence of a clinical study, the requested information cannot be extracted from the provided text.

Ask a specific question about this device

ECG-less Cardiac streamlines patient preparation by enabling an alternative acquisition of cardiac CT images for general cardiac assessment without the need of a patient-attached ECG monitor. ECG-less Cardiac is for adults only.

ECG-less Cardiac is a software device that is an additional, optional cardiac scan mode that can be used on the Revolution Apex Elite, Revolution Apex, and Revolution CT with Apex edition systems. There is no change to the predicate device hardware to support the subject device. Currently, the available cardiac scan modes on the Revolution CT Family are Cardiac Axial and Cardiac Helical, which makes use of an ECG signal to physiologically trigger the cardiac acquisitions and/or to retrospectively gate the reconstruction.

ECG-less Cardiac is a third cardiac scan mode that introduces the ability to acquire cardiac images without the need of a patient-attached ECG monitor. Hence, an ECG signal from the patient is not utilized for this scan mode. The ECG-less Cardiac workflow leverages the full-heart coverage capability of 160 mm configurations, fast gantry speeds (0.28 and 0.23 s/rot), and existing cardiac software options of SmartPhase and SnapShot Freeze 2 (K183161) to acquire images that are suitable for coronary and cardiac functional assessment.

The ECG-less cardiac feature allows the user to acquire a cardiac CT scan without the need to complete the steps associated with utilizing an ECG monitor, such as attaching ECG electrodes to the patient, checking electrode impedance, and confirming an ECG trace is displayed on the operator console, thus optimizing the workflow.

ECG-less Cardiac may be best utilized in examinations where excluding the ECG connection would streamline the patient examination, including and unloading of the patient. This may result in an improved workflow for certain clinical presentations. ECG-less Cardiac may also increase access to cardiac assessment for patients that are difficult to receive an ECG signal from. Circumstances where the subject device is expected to increase cardiac access includes scenarios where trauma patient has a diagnostic ECG attached and/or other instrumentation, such that there is added difficulty of attaching ECG leads for a gated scan, and situations where it is challenging to get an ECG signal from a patient such as a patient's t-wave triggering the scan or R-peak being difficult to detect.

Here's a summary of the acceptance criteria and the study proving the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria are implicitly derived from the study's conclusions, focusing on diagnostic utility and image quality. No specific quantitative thresholds for acceptance are explicitly stated in the document beyond "interpretable without a significant motion artifact penalty" and "of diagnostic utility."

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

• Sample Size for Test Set: The document does not explicitly state the exact number of cases or images included in the reader study (test set). It refers to "a reader study of sample clinical data" and "prospectively collected clinical data."
• Data Provenance: The data was prospectively collected clinical data from patients undergoing a routine cardiac exam. The country of origin is not specified.

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

• Number of Experts: Three experts were used.
• Qualifications of Experts: They were board-certified radiologists who specialize in cardiac imaging. The document does not specify their years of experience.

4. Adjudication Method for the Test Set

The adjudication method is not explicitly stated. The document mentions that each image was "read by three board certified radiologists who specialize in cardiac imaging who provided an assessment of image quality." This suggests independent readings, but it does not detail a consensus or adjudication process (e.g., 2+1, 3+1).

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

• No, an MRMC comparative effectiveness study involving human readers improving with AI vs. without AI assistance was not conducted or reported.
• The study was a reader study where experts assessed images generated by the ECG-less Cardiac system. The primary goal was to validate the diagnostic utility and image quality of the ECG-less Cardiac acquisitions themselves, not to assess human reader performance with or without an AI assist feature.

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

Yes, a form of standalone performance was assessed in the engineering bench testing. This testing "assessed how simulated ECG-less Cardiac scan conditions performed against an ECG-gated 'ground truth' nominal phase location." This component evaluated the algorithm's ability to generate images comparable to traditional ECG-gated acquisitions without human interpretation being the primary focus.

7. The Type of Ground Truth Used

• For the engineering bench testing, the ground truth was an ECG-gated "ground truth" nominal phase location. This implies a comparison to a known, established reference standard for cardiac imaging synchronization.
• For the clinical reader study, the ground truth was effectively the expert consensus/assessment of the three board-certified radiologists regarding the interpretability, motion artifact, and diagnostic utility of the ECG-less images. There is no mention of pathology or outcomes data being used as ground truth for this part of the study.

8. The Sample Size for the Training Set

The document does not provide any information regarding the sample size used for the training set of the ECG-less Cardiac software.

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

The document does not provide any information on how the ground truth for the training set was established. It only discusses the testing (validation) phase.

Ask a specific question about this device

Critical Care Suite with Pneumothorax Detection AI Algorithm is a computer-aided triage, notification, and diagnostic device that analyzes frontal chest X-ray images for the presence of a pneumothorax. Critical Care Suite identifies and highlights images with a pneumothorax to enable case prioritization or triage and assist as a concurrent reading aide during interpretation of radiographs.

Intended users include qualified independently licensed healthcare professionals (HCPs) trained to independently assess the presence of pneumothoraxes in radiographic images and radiologists.

Critical Care Suite should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis. It is not intended to replace the review of the X-ray image by a qualified physician. Critical Care Suite is indicated for adults and Transitional Adolescents (18 to < 22 years old but treated like adults).

Critical Care Suite is a suite of Al algorithms for the automated image analysis of frontal chest X-rays acquired on a digital x-ray system for the presence of critical findings. Critical Care Suite with Pneumothorax Detection Al Algorithm is indicated for adults and transitional adolescents (18 to <22 years old but treated like adults) and is intended to be used by licensed qualified healthcare professionals (HCPs) trained to independently assess the presence of pneumothoraxes in radiographic images and radiologists. Critical Care Suite is a software module that can be deployed on several computing platforms such as PACS, On Premise, On Cloud or X-ray Imaging Systems.

Today's clinical workflow, hospitals are overburdened by large volume of orders and long turnaround times for radiologist reports. Critical Care Suite with the Pneumothorax Detection Al Algorithm enables effective prioritization and assists in the detection / diagnosis of pneumothoraxes for radiologists and HCPs that have been trained to independently assess the presence of pneumothoraxes in radiographic images. It performs this task by flagging images with a suspicious finding and providing a localization overlay of the suspected pneumothorax as well as a graphical representation of the algorithm's confidence in the resultant finding. These outputs can be displayed wherever the reviewing physician normally conducts their reads per their standard of care, including PACS, On Premise, On Cloud and Digital Projection Radiographic Systems.

Here's a summary of the acceptance criteria and study details for the GE Medical Systems, LLC Critical Care Suite with Pneumothorax Detection AI Algorithm, based on the provided document:

1. Table of Acceptance Criteria and Reported Device Performance

The document primarily focuses on reporting the device's performance against its own established criteria rather than explicitly listing pre-defined "acceptance criteria" tables. However, we can infer the acceptance criteria from the reported performance goals.

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

• Sample Size for Test Set: 804 images
• Data Provenance: The test set included images from two North American sites.
• Retrospective/Prospective: The document does not explicitly state if the test set was retrospective or prospective. However, given it's a "final validation ground truth dataset" that was not used in training, it's highly likely to be retrospective.

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

• Number of Experts: Three blinded radiologists.
• Qualifications of Experts: Radiologists (no specific experience level mentioned, but "blinded radiologists" implies qualified professionals).

4. Adjudication Method for the Test Set

• Adjudication Method: The ground truth was established by "three blinded radiologists." This implies a consensus method, likely majority rule or a process where discrepancies were resolved to arrive at a single ground truth label. The specific phrase "consensus" or "adjudication" is not used, but the description points to this approach.

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

• MRMC Study Done: Yes, a multi-reader multi-case study was conducted.
• Effect Size of Human Reader Improvement with AI vs. Without AI Assistance:
  • Mean AUC: Improved by 14.5% (from 76.8% non-aided to 91.3% aided; p=0.002).
  • Sensitivity: Increased by 16.3% (from 67.4% non-aided to 83.7% aided; p<0.001).
  • Specificity: Increased by 12.4% (from 76.6% non-aided to 89.0% aided; p<001).
  • Large Pneumothorax (Mean AUC): Improved by 10.5% (p=0.009).
  • Large Pneumothorax (Sensitivity): Improved by 13.4% (p<0.001).
  • Small Pneumothorax (Mean AUC): Improved by 17.6% (p<0.001).
  • Small Pneumothorax (Sensitivity): Improved by 18.7% (p<0.001).

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

• Standalone Study Done: Yes, the "standalone performance of the Pneumothorax Detection AI Algorithm was tested against this dataset."

7. The Type of Ground Truth Used

• Type of Ground Truth: Expert consensus by three blinded radiologists.

8. The Sample Size for the Training Set

• Sample Size for Training Set: The algorithm was developed using "over 12,000 images." This number includes images used for training, verification, and validation, but the specific breakdown for the training set alone is not provided. It's implied that the majority would be for training.

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

• Ground Truth for Training Set: The document states that the "Pneumothorax Detection AI Algorithm was developed using over 12,000 images from six sources, including the National Institute of Health and sites within the United States, Canada, and India." It then clarifies this data was "segregated into training, verification, and validation datasets." While it doesn't explicitly detail the methodology for establishing ground truth for the training set, it's standard practice that such large datasets for deep learning and medical imaging are meticulously annotated by medical experts (e.g., radiologists) or derived from existing clinical reports and pathology, which would then be reviewed or confirmed by experts. Given the rigor for the validation set, it's reasonable to infer a similar expert-driven process for the training data, although the specifics are not provided in this excerpt.

Ask a specific question about this device

Auto Segmentation generates a Radiotherapy Structure Set (RTSS) DICOM with segmented organs at risk which can be used by dosimetrists, medical physicists, and radiation oncologists as initial contours to accelerate workflow for radiation therapy planning. It is the responsibility of the user to verify the processed output contours and user-defined labels for each organ at risk and correct the contours/labels as needed. Auto Segmentation may be used with images acquired on CT scanners, in adult patients.

Auto Segmentation is a post-processing software designed to automatically generate contours of organ(s) at risk (OARs) from Computed Tomography (CT) images in the form of a DICOM Radiotherapy Structure Set (RTSS) series. The application is intended as a workflow tool for initial segmentation of OARs to streamline the process of organ at risk delineation. The Auto Segmentation is intended to be used by radiotherapy (RT) practitioners after review and editing, if necessary, and confirming the accuracy of the contours for use in radiation therapy planning.

Auto Segmentation uses deep learning algorithms to generate organ at risk contours for the head and neck, thorax, abdomen and pelvis regions from CT images across 40 organ subregion(s). The automatically generated organ at risk contours are networked to predefined DICOM destination(s), such as review workstations supporting RTSS format, for review and editing, as needed.

The organ at risk contours generated with the Auto Segmentation are designed to improve the contouring workflow by automatically creating contours for review by the intended users. The application is compatible with CT DICOM images with single energy acquisition modes and may be used with both GE and non-GE CT scanner acquired images (contrast), in adult patients.

Here's an analysis of the acceptance criteria and study detailed in the provided document for the GE Medical Systems Auto Segmentation device:

1. Table of Acceptance Criteria and Reported Device Performance

Note: The reported device performance (Dice Mean and Lower CI95) for almost all organs meets or exceeds the specified acceptance criteria. The only exception where the device's Dice Mean is slightly below the acceptance criteria is for Mandible (92.70% vs 94.0%) and Oral Cavity (87.43% vs 91.0%) and Pituitary (75.62% vs 78.0%), however there is no further discussion or justification provided in the text for these specific instances. The document does state that "The evaluation of the Dice mean for the Auto Segmentation algorithms demonstrates that the algorithm performance is in line with the performance of the predicate, as well as state of the art, recently cleared similar automated contouring devices."

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

• Sample Size for Test Set: 302 retrospective CT radiation therapy planning exams (generating 2552 contours).
• Data Provenance: Multiple clinical sites in North America, Asia, and Europe. The demographic distribution includes adults (18-89 years old) of various genders and ethnicities from 9 global sources (USA, EU, Asia). The data was acquired using a variety of CT scanners and scanner protocols from different manufacturers.
• Retrospective/Prospective: Retrospective.

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

• Number of Experts: Three (3).
• Qualifications of Experts: Independent, qualified radiotherapy practitioners.
• Comment: The document states that the ground truth annotations were established following RTOG and DAHANCA clinical guidelines.

4. Adjudication Method for the Test Set

• The document implies a consensus-based approach guided by clinical guidelines, as "ground truth annotations were established (...) manually by three independent, qualified radiotherapy practitioners," but it does not specify an explicit adjudication method like "2+1" or "3+1" for resolving disagreements between the three experts. The phrase "established following RTOG and DAHANCA clinical guidelines" suggests that these guidelines were used to define the correct contours.

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

• The document describes a qualitative preference study that involved three qualified radiotherapy practitioners reviewing the contours generated by the Auto Segmentation application. They assessed the adequacy of the generated contours for radiotherapy planning using a Likert scale.
• However, this was NOT a comparative effectiveness study of human readers with and without AI assistance. It was a study to determine the adequacy of the AI-generated contours themselves for initial use. Therefore, no effect size of human readers improving with AI vs. without AI assistance can be reported from this document.

6. Standalone Performance Study (Algorithm Only)

• Yes, a standalone performance study was conducted. The "Performance testing to evaluate the device's performance in segmenting organs-at-risk was performed using a database of 302 retrospective CT radiation therapy planning exams." The Dice Similarity Coefficient (DSC) was used as the primary metric to compare the Auto Segmentation generated contours to ground truth contours. The reported Dice Mean values and their 95% confidence intervals are direct metrics of the algorithm's standalone performance.

7. Type of Ground Truth Used

• Expert Consensus/Manual Annotation: Ground truth annotations were "established following RTOG and DAHANCA clinical guidelines manually by three independent, qualified radiotherapy practitioners."

8. Sample Size for the Training Set

• 911 different CT exams.

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

• The document states that "The Auto Segmentation algorithms were developed and trained using a dataset of 911 different CT exams from several clinical sites from multiple countries. The original development and training data was used for radiotherapy planning..."
• It does not explicitly detail the process for establishing ground truth for the training set, but given the context of the test set ground truth and the overall development, it is highly probable it involved manual annotation by experts for radiotherapy planning purposes.

Ask a specific question about this device

Spectral Bone Marrow is an automated image processing software application, utilizing deep learning technology for bone segmentation, to facilitate optimized visualization of bone marrow in spectral body and extremity CT images. Spectral Bone Marrow's output can be used during the review of traumatic and non-traumatic bone pathologies.

Spectral Bone Marrow is a deep-learning based software analysis package designed for the visualization of bone marrow based on GE HealthCare's spectral CT acquisitions data. Spectral Bone Marrow assists clinicians by providing an automatically generated fused material density image of the segmented bone region over a base monochromatic image optimized for the visualization of bone marrow during the review of traumatic or non-traumatic bone pathologies. The software creates a fully automated post processing workflow for creating these images and improving reader efficiency.

The Spectral Bone Marrow application involves generating a bone mask with a deep learning bone segmentation algorithm and uses this segmented region to define bone regions of water minus hydroxyapatite (Water(HAP)) material density images, which are subsequently colored. The application outputs the colored Water(HAP) material density images overlayed on monochromatic CT images or Virtual Unenhanced (VUE) images.

Additionally, the Spectral Bone Marrow application has the optional ability to automatically set the window width and window level of the color overlay images to provide for optimal visualization of bone marrow. The software provides multiplanar export of the fused images. Spectral Bone Marrow is hosted on GE's Edison Health Link (EHL) computational platform.

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

Acceptance Criteria and Device Performance

The provided document does not explicitly present a table of quantitative acceptance criteria for device performance. However, it states that the engineering bench testing showed that the algorithm is capable of accurately segmenting bones and is safe and effective for its intended use. Furthermore, the clinical assessment validated that the Spectral Bone Marrow software provides additional diagnostic value for the evaluation of bone marrow and increased overall reader efficiency.

This implies that the acceptance criteria revolved around demonstrating accurate bone segmentation, diagnostic value, and improved reader efficiency. The specific metrics and thresholds for "accuracy," "additional diagnostic value," and "increased efficiency" are not quantified in this summary.

Inferred Acceptance Criteria:

Study Details

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

• Test Set Sample Size: 146 retrospective Spectral CT series.
• Data Provenance: Retrospective, with the country of origin not explicitly stated, but the mention of "US board certified radiologists" suggests the data could be from the US or at least interpreted by US experts.

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

• Number of Experts: Three.
• Qualifications: US board certified radiologists with expertise in both the evaluation of bone marrow and dual energy imaging review.

3. Adjudication Method for the Test Set

The document does not explicitly state a specific adjudication method like "2+1" or "3+1." It mentions that the ground truth for the 146 retrospective Spectral CT series was generated by three US board certified radiologists. This implies an expert consensus approach, but the specific decision-making process (e.g., majority vote, agreement by all three) is not detailed.

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

• Was an MRMC study done? Yes, a form of clinical assessment involving multiple readers was conducted. The clinical testing involved "three board certified radiologists" assessing a "representative set of clinical sample images" processed by the software. They evaluated "image quality related to diagnostic use according to a Likert scale" and rated "their efficiency when using the algorithm compared to using without." This setup resembles an MRMC study, focusing on reader performance with and without the AI.
• Effect size of human readers improve with AI vs without AI assistance: The document states that the assessment validated that the Spectral Bone Marrow software provides additional diagnostic value for the evaluation of bone marrow and increased overall reader efficiency. However, it does not provide quantitative effect sizes (e.g., specific percentage improvement in diagnostic accuracy or time saved). It merely confirms an improvement was observed and validated.

5. Standalone (Algorithm Only Without Human-in-the-Loop Performance) Study

Yes, a standalone study (referred to as "engineering bench testing") was done to evaluate the bone segmentation algorithm itself. This testing used a database of 146 retrospective Spectral CT series. The "result of the engineering bench testing showed that the algorithm is capable of accurately segment bones and is safe and effective for its intended use."

6. Type of Ground Truth Used

• Expert Consensus: The ground truth for the engineering bench testing (bone segmentation evaluation) was "generated by three US board certified radiologists."
• Clinical Assessment by Experts: For the clinical evaluation of diagnostic value and reader efficiency, the "assessment used retrospectively collected clinical cases" and each image was "read by each board certified radiologist who provided an assessment of image quality related to diagnostic use according to a Likert scale." This also relies on expert interpretation and assessment as the ground truth for these subjective measures.

7. Sample Size for the Training Set

The document does not specify the sample size for the training set used to develop the deep learning bone segmentation algorithm. It only refers to the training of a "deep learning bone segmentation algorithm."

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

The document does not explicitly state how the ground truth for the training set was established. It only mentions that the bone segmentation algorithm uses deep learning technology. Typically, ground truth for training deep learning models involves manual annotation by experts, but this detail is not provided in the summary.

Ask a specific question about this device

The Deep Learning Image Reconstruction option is a deep learning based reconstruction method intended to produce cross-sectional images of the head and whole body by computer reconstruction of X-ray transmission data taken at different angles and planes, including Axial, Helical (Volumetric), and Cardiac acquisitions, for all ages.

Deep Learning Image Reconstruction can be used for head, whole body, cardiac, and vascular CT applications.

Deep Learning Image Reconstruction is an image reconstruction method that uses a dedicated Deep Neural Network (DNN) that has been designed and trained specifically to generate CT Images to give an image appearance, as shown on axial NPS plots, similar to traditional FBP images while maintaining the performance of ASiR-V in the following areas: image noise (pixel standard deviation), low contrast detectability, high-contrast spatial resolution, and streak artifact suppression.

The images produced are branded as "TrueFidelity™ CT Images". Reconstruction times with Deep Learning Image Reconstruction support a normal throughput for routine CT.

Deep Learning Image Reconstruction was trained specifically on the Revolution CT/Apex platform (K163213, K133705, K19177). The deep learning technology is integrated into the scanner's existing raw data-based image reconstruction chain to produce DICOM compatible "TrueFidelity™ CT Images".

The system allows user selection of three strengths of Deep Learning Image Recon: Low, Medium or High. The strength selection will vary with individual users' preferences and experience for the specific clinical need.

The DLR algorithm is now being modified on the Revolution family CT systems (K133705, K163213, K19177) for improved reconstruction speed and image quality, thus triggering this premarket notification.

The provided document describes the Deep Learning Image Reconstruction (DLIR) device, its acceptance criteria, and the study conducted to prove it meets these criteria.

Here's a breakdown of the requested information:

1. Table of Acceptance Criteria and Reported Device Performance

The document does not explicitly state numerical acceptance criteria with pass/fail thresholds for each metric. Instead, it focuses on demonstrating non-inferiority or improvement compared to a predicate device (ASiR-V) and ensuring diagnostic quality. The reported device performance is qualitative, indicating "significantly better subjective image quality" and "diagnostic quality images."

However, based on the non-clinical and clinical testing sections, we can infer the performance metrics evaluated.

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

• Sample Size: 40 retrospectively collected clinical cases.
• Data Provenance: Retrospectively collected clinical cases. The country of origin is not specified in the provided text.

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

• Number of Experts: 6 board-certified radiologists.
• Qualifications of Experts: Board-certified radiologists with "expecialty areas that align with the anatomical region of each case."

4. Adjudication Method for the Test Set

The document describes a reader study where each of the 40 cases (reconstructed with both ASiR-V and DLIR) was read by 3 different radiologists independently. They provided an assessment of image quality using a 5-point Likert scale. There's no explicit mention of an adjudication process (e.g., 2+1, 3+1) if there were disagreements among the three readers, as the focus seems to be on independent assessment and overall subjective preference comparison.

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

Yes, a multi-reader multi-case (MRMC) comparative effectiveness study was done. Human readers compared images reconstructed with DLIR (AI-assisted reconstruction) against images reconstructed with ASiR-V (without DLIR).

• Effect Size: The study confirmed that DLIR (the subject device) produced diagnostic quality images and "have significantly better subjective image quality" than the corresponding images generated with the ASiR-V reconstruction algorithm. The text doesn't provide a specific numerical effect size (e.g., a specific improvement percentage or statistical metric), but it qualitatively states a "significant" improvement based on reader preference for image noise texture, image sharpness, and image noise texture homogeneity.

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

Yes, extensive standalone (algorithm-only) performance testing was conducted. This is detailed in the "Additional Non-Clinical Testing" section, where DLIR and ASiR-V reconstructions of identical raw datasets were compared for various objective image quality metrics without human interpretation during these specific tests.

7. The Type of Ground Truth Used

The ground truth for the clinical reader study was established through expert consensus/assessment of image quality and preference by the participating radiologists. For the non-clinical bench testing, the ground truth was based on objective physical measurements and established phantom data with known properties.

8. The Sample Size for the Training Set

The document mentions that the Deep Neural Network (DNN) for DLIR was "trained specifically on the Revolution CT/Apex platform." However, it does not specify the sample size (number of images or cases) used for the training set.

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

The text states that the DNN was "trained specifically to generate CT Images to give an image appearance, as shown on axial NPS plots, similar to traditional FBP images while maintaining the performance of ASiR-V." It also notes that the DNN "models the scanned object using information obtained from extensive phantom and clinical data."

While the exact method for establishing ground truth for training isn't explicitly detailed, it implies a process where:

• Reference Images: Traditional FBP (Filtered Back Projection) and ASiR-V images likely served as reference or target outputs for the DNN, specifically regarding image appearance, noise characteristics, and spatial resolution.
• "Extensive phantom and clinical data": This data, likely corresponding to various anatomical regions, pathologies, and dose levels, was fed into the training process. The ground truth would involve teaching the network to reconstruct images that, when compared to conventionally reconstructed images (FBP/ASiR-V), exhibit desired image quality attributes (e.g., reduced noise while preserving detail).
• Noise Modeling: The training process characterized "the propagation of noise through the system" to identify and remove it, suggesting a ground truth related to accurate noise modeling and reduction.

Ask a specific question about this device