Search Results

True Enhance DL is a deep learning-based image processing method trained to estimate monochromatic, 50 keV GSI images. The algorithm is intended to improve the contrast of 120 kVp, single energy images of the body.

This device is intended to provide non-quantitative, adjunct information and should not be interpreted without the original 120 kVp image.

True Enhance DL may be used for patients of all ages.

True Enhance DL is a deep learning-based image processing method for contrast enhanced images of the body obtained using the Revolution Ascend Family (K213938), which consists of multiple commercial configurations: Revolution Ascend Elite, Revolution Ascend Plus, and Revolution Ascend Select. True Enhance DL is intended to post-process single energy, 120 kVp images to output nonquantitative, adjunctive information with better contrast than single energy input data.

True Enhance DL brings four deep leaning models that the user can choose depending on different contrast enhancement phases. These four models are CT Angiography, Arterial, Portal/Venous, and Delayed True Enhance DL.

True Enhance DL is not intended to replace hardware based Monochromatic Imaging by Gemstone Spectral Imaging (GSI) technology or replicate GSI dual energy acquisitions. The device was trained to estimate monochromatic, 50 keV GSI images, and only enhances images from 120 kVp acquisitions on non-GSI Revolution Ascend systems.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance:

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

• Sample Size: Not explicitly stated as a number of cases. The text mentions "sample clinical data" and "Additional representative clinical cases and anthropomorphic phantom cases."
• Data Provenance: Retrospective. The study used "retrospectively collected representative clinical cases." The country of origin is not specified.

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

• Number of Experts: Four.
• Qualifications of Experts: "Four board certified radiologists." Specific years of experience are not mentioned.

4. Adjudication Method for the Test Set:

• The text does not explicitly state a formal adjudication method (e.g., 2+1, 3+1). It indicates that the four radiologists each provided a comparative assessment of image quality related to diagnostic use. This suggests individual reader assessment rather than a consensus-building adjudication process for ground truth. However, they were asked to "rate the contrast enhancement in the True Enhance DL series vs the native image series," which implies a comparative evaluation.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and Effect Size:

• A MRMC-like study was done, as "four board certified radiologists" read the images.
• Effect Size: The text states, "the readers were asked to rate the contrast enhancement in the True Enhance DL series vs the native image series" and "validated that True Enhance DL software provides additional benefit by improving contrast." However, a quantitative effect size of human readers' improvement with AI vs. without AI assistance is not provided in this summary. The focus was on the software's ability to improve contrast rather than a comparative effectiveness of human performance with and without the tool.

6. If a Standalone (Algorithm Only Without Human-in-the-Loop Performance) Was Done:

• Yes, a standalone evaluation was conducted to assess image characteristics. The text mentions "Additional representative clinical cases and anthropomorphic phantom cases from a GSI system generating both single energy 120 kVp and 50 keV monochromatic images were evaluated for CT number in various anatomical regions to study image characteristics for different materials of the device output compared to 50 keV and 120 kVp reference images." This assesses the algorithm's output properties directly against a reference, which constitutes a standalone performance aspect.

7. The Type of Ground Truth Used:

• Expert Consensus / Reader Assessment: For the image quality and contrast improvement aspects, the subjective assessment of "four board certified radiologists" served as the ground truth.
• Reference Images / Clinical Data: For the standalone evaluation, "50 keV and 120 kVp reference images" (likely derived from GSI systems with known energy characteristics) were used to study the algorithm's output. Clinical cases with "disease/pathology" were used, implying the presence of known conditions, although how these conditions served as "ground truth" for the AI's performance beyond simply being present in the data is not fully detailed.

8. The Sample Size for the Training Set:

• The sample size for the training set is not provided in this document. The text only states, "The device was trained to estimate monochromatic, 50 keV GSI images."

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

• The document implies that the training was based on "to estimate monochromatic, 50 keV GSI images." This suggests that 50 keV monochromatic GSI images (likely acquired from dual-energy CT scans, which serve as a form of ground truth for spectral decomposition) were used as the target output for the deep learning model during training. The process of generating these reference 50 keV GSI images themselves would involve the CT system's physics and reconstruction algorithms.

Ask a specific question about this device

The Deep Learning Image Reconstruction software 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, (Volumetric), and Cardiac acquisitions, for all ages.

Deep Learning Image Reconstruction software 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.

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' preference for the specific clinical need.

The DLR algorithm was modified on the Revolution CT/Apex platform for improved reconstruction speed and image quality and cleared in February 2022 with K213999. The same modified DLIR is now being ported to Revolution EVO (K131576) /Revolution Maxima (K192686), Revolution Ascend (K203169, K213938) and Discovery CT750 HD family CT systems including Discovery CT750 HD, Revolution Frontier and Revolution Discovery CT (K120833).

The provided text describes that the Deep Learning Image Reconstruction software was tested for substantial equivalence to a predicate device (K213999). The study performed was largely an engineering bench testing, comparing various image quality metrics between images reconstructed with Deep Learning Image Reconstruction (DLIR) and ASiR-V from the same raw datasets.

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

1. Table of Acceptance Criteria and Reported Device Performance

The text indicates that the device aims to maintain the performance of ASiR-V in specific areas while offering an image appearance similar to traditional FBP images. The "acceptance criteria" can be inferred from the list of image quality metrics evaluated, with the performance goal being comparable or improved relative to ASiR-V.

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

• Test Set Sample Size: The text states "the identical raw datasets obtained on GEHC's Revolution Ascend, Revolution Frontier and Discovery CT750 HD systems". However, the number of cases or specific sample size for these datasets is not explicitly stated.
• Data Provenance: The raw datasets were "obtained on GEHC's Revolution Ascend, Revolution Frontier and Discovery CT750 HD systems". The country of origin is not specified, and it is stated that the study used retrospective raw datasets (i.e., existing data, not newly acquired data for the study).

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

The provided text focuses on engineering bench testing and image quality metrics. It does not mention the use of experts to establish ground truth for the test set or their qualifications. The evaluation primarily relies on quantitative image quality metrics.

4. Adjudication Method for the Test Set

Since experts were not explicitly used to establish ground truth, there is no mention of an adjudication method for the test set in the provided text.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its effect size

An MRMC comparative effectiveness study was not performed according to the provided text. The study focused on technical image quality comparisons at the algorithm level, not human reader performance with or without AI assistance.

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

Yes, a standalone performance evaluation was done. The study described is primarily a standalone evaluation of the algorithm's image quality output (e.g., noise, resolution, artifacts, detectability) when compared to images reconstructed with ASiR-V from the same raw data.

7. The Type of Ground Truth Used

The "ground truth" for the test set was essentially:

• Quantitative Image Quality Metrics: Performance relative to ASiR-V for metrics like image noise, LCD, spatial resolution, streak artifact suppression, CT uniformity, CT number accuracy, CNR, spatial resolution (longitudinal), NPS, and artifact analysis.
• Reference Image Appearance: The stated goal was an image appearance similar to traditional FBP images shown on axial NPS plots.

There is no mention of pathology, expert consensus on clinical findings, or outcomes data being used as ground truth for this particular substantial equivalence study.

8. The Sample Size for the Training Set

The text states that the Deep Neural Network (DNN) is "trained on the CT scanner" and models the scanned object using "information obtained from extensive phantom and clinical data." However, the specific sample size for the training set is not provided.

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

The ground truth for the training set is implicitly established through the "extensive phantom and clinical data" mentioned as being used to train the DNN. The text indicates the DNN is trained to model noise propagation and identify noise characteristics to remove it, and to generate images with an appearance similar to traditional FBP while maintaining ASiR-V performance. This suggests the training involves learning from "ground truth" as defined by:

• Reference Image Quality: Likely images reconstructed with proven methods (e.g., FBP, ASiR-V) or images from phantoms with known properties.
• Noise Characteristics: The DNN is trained to understand and model noise.

However, the specific methodology for establishing this ground truth for the training data (e.g., expert annotation, simulated data, pathology confirmed disease) is not detailed in the provided text.

Ask a specific question about this device

The Deep Learning Image Reconstruction software 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 software 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: dose, 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 software support a normal throughput for routine CT.

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' preference for the specific clinical need.

The provided text is a 510(k) summary for the GE Healthcare Japan Corporation's "Deep Learning Image Reconstruction" device. It outlines the device's technical characteristics, intended use, and comparison to predicate devices for substantial equivalence determination. However, it does not include detailed information regarding specific acceptance criteria, a comprehensive study proving the device meets these criteria, or specific performance metrics in a tabular format. The document focuses on establishing substantial equivalence based on the fundamental technology being unchanged from the predicate and successful completion of design control testing and quality assurance measures.

Therefore, I cannot extract all the requested information. Here's what can be inferred and what is missing:

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

This information is not provided in the document. The document states: "Design verification and validation, including IQ bench testing, demonstrate that the Deep Learning Image Reconstruction (DLIR) software met all of its design requirement and performance criteria." However, it does not specify what those "design requirement and performance criteria" are or the reported performance data against them.

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

This information is not provided in the document. The document mentions "IQ bench testing" and "System Testing" including "Image Performance Testing (Verification)" and "Simulating Use Testing (Validation)," but does not detail the sample sizes or data provenance used for these tests.

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)

This information is not provided in the document.

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

This information is not provided in the document.

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

This information is not provided in the document. The document describes the device as a "deep learning based reconstruction method" that produces images with "similar to traditional FBP images while maintaining the performance of ASiR-V in the following areas: dose, image noise (pixel standard deviation), low contrast detectability, high-contrast spatial resolution, and streak artifact suppression." This implies a comparison to other reconstruction methods, but not a MRMC study involving human readers with and without AI assistance.

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

Yes, based on the description, the primary testing described is "standalone" algorithm performance. The device is a "deep learning based reconstruction method" and the testing described, such as "IQ bench testing" and "Image Performance Testing," focuses on the intrinsic image quality outputs of the algorithm. There is no mention of human-in-the-loop performance in the context of effectiveness studies.

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

This information is not explicitly stated in the document. Given the context of "IQ bench testing" and performance metrics like "image noise," "low contrast detectability," and "spatial resolution," it's highly likely that objective phantom studies and potentially established image quality metrics (which could be considered a form of "ground truth" for image quality, validated against known physical properties) were used. However, expert consensus on clinical diagnostic accuracy or pathology is not mentioned as a ground truth.

8. The sample size for the training set

This information is not provided in the document. It mentions that the device "uses a dedicated Deep Neural Network (DNN) that has been designed and trained specifically to generate CT Images," but the details of the training set are not disclosed.

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

This information is not provided in the document. While it states 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," the method for establishing the ground truth for this training is not detailed.

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 data taken at different angles and planes, including Axial, Cine, Helical (Volumetric), Cardiac, and Gated acquisitions. 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 in patients of all ages.

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

The Revolution Ascend is a head and whole-body CT system composed of a gantry, patient table, operator console with a host computer, power distribution unit, and interconnecting cables. The system also includes image acquisition and reconstruction hardware/software, general system software, accompanying documents, and associated accessories/interconnections. The system has a 75 cm gantry bore and 64-row detector.

Revolution Ascend generates cross-sectional images of the body by computer reconstruction of x-ray transmission data taken at different angles and planes, including Axial, Cine, Helical (Volumetric), Cardiac, and Gated acquisitions modes.

A design change has been made to the Revolution Ascend with an alternative detector scintillator material prompting this premarket notification. While this change is being made, the design and manufacturing is such that the system performance remains identical to its unmodified predicate. The proposed device carries over all the features, options and specifications of the predicate device, including the Deep Learning Iterative Recon (DLIR) cleared via K212067 without change.

This document is a 510(k) Premarket Notification Summary for the Revolution Ascend CT system. The purpose of this submission is to demonstrate that the proposed device, with a change in detector scintillator material, is substantially equivalent to a legally marketed predicate device. Therefore, the acceptance criteria and study design are focused on proving this equivalence rather than establishing the de novo performance of an AI algorithm or a new medical device.

Based on the provided document, here's a description of the acceptance criteria and the study that proves the device meets them:

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

The document doesn't provide a direct table of specific numerical acceptance criteria for image quality metrics. Instead, the acceptance criteria are implicitly stated as demonstrating equivalence to the predicate device, Revolution Ascend (K203169), across various performance aspects.

2. Sample size used for the test set and the data provenance

The document explicitly states that the testing was non-clinical bench testing using "standard IQ, QA phantoms." It does not involve human patient data or a specific "test set" in the context of clinical studies. Therefore, sample size in terms of patient cases is not applicable here.

• Data Provenance: Not applicable as it's non-clinical bench testing with phantoms.

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

Not applicable. As the testing was non-clinical bench testing using phantoms and established metrics (e.g., IEC standards, NEMA standards), the "ground truth" is based on the known physical properties and performance characteristics of the phantoms and the objective measurements derived from them, rather than expert interpretation of patient images.

4. Adjudication method for the test set

Not applicable. Since the testing is non-clinical bench testing with phantoms and objective measurements, there is no need for expert adjudication of image findings.

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. This submission is for a hardware change (detector scintillator material) in a CT system, not for a new AI-powered diagnostic device or a modification to an existing AI feature (DLIR is carried over without change). Therefore, an MRMC comparative effectiveness study regarding human reader performance with/without AI assistance is outside the scope of this particular 510(k) submission. The document explicitly states the DLIR was "cleared via K212067 without change," implying its performance was evaluated in that separate submission.

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

No. This submission is for a CT scanner system that includes hardware and software. It's not for a standalone algorithm. The "Deep Learning Image Reconstruction (DLIR)" component referenced is a reconstruction algorithm within the CT system, and its standalone performance likely would have been assessed in its original 510(k) clearance (K212067). This submission focuses on demonstrating that the change in detector material does not degrade the performance of the overall system, including features like DLIR.

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

For the non-clinical testing, the "ground truth" is based on objective phantom measurements and established engineering metrics as defined by standards like IEC 61223-3-5 Ed. 2. This is not clinical ground truth (e.g., pathology, expert consensus on disease diagnosis). The goal is to demonstrate physical and image quality equivalence.

8. The sample size for the training set

Not applicable. This submission is about a hardware change in an already cleared CT system and is not for training a new AI algorithm. The DLIR component, which involves deep learning, would have had a training set in its original development and clearance (K212067), but details for that are not provided in this document as it's "carried over without change."

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

Not applicable. As above, this pertains to the development of the DLIR algorithm (likely cleared in K212067), not the current submission for a detector material change.

Ask a specific question about this device

The Deep Learning Image Reconstruction software 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 software 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: dose, 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 software support a normal throughput for routine CT.

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.

Here's a breakdown of the acceptance criteria and the study that proves the device meets them, based on the provided text:

Acceptance Criteria and Device Performance

The core of the acceptance criteria revolves around demonstrating that the Deep Learning Image Reconstruction (DLIR) on the Revolution Ascend system is substantially equivalent to its predicate device (DLIR on Revolution EVO) and performs at least as well as, or better than, ASiR-V reconstruction in key image quality metrics.

Study Details

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

   • Sample Size: A total of 60 retrospectively collected clinical cases were used.
   • Data Provenance: The data was retrospectively collected. The country of origin is not explicitly stated in the provided text.

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

   • Number of Experts: 9 board-certified radiologists.
   • Qualifications: These radiologists had "expertise in the specialty areas that align with the anatomical region of each case."

3. Adjudication method for the test set:

   • Each image was read by 3 different radiologists.
   • The readers completed their evaluations independently and were blinded to the results of the other readers' assessments.
   • The text doesn't explicitly state an adjudication method like 2+1 or 3+1 for discrepancies. It implies a consensus or agreement was sought, or that individual assessments contributed to the overall conclusion of substantial equivalence. Given they provided an assessment on a Likert scale and then compared images, it seems individual reader assessments were aggregated, rather than a discrepancy resolution process.

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:

   • Yes, an MRMC study was implicitly done, as 9 radiologists evaluated 60 cases, with each case being read by 3 different radiologists. The study involved a comparison between ASiR-V reconstructions and Deep Learning Image Reconstruction (DLIR) images.
   • Effect Size: The document does not provide a specific effect size (e.g., percentage improvement in accuracy or AUC) of how much human readers improved with DLIR assistance compared to ASiR-V. It states that the study results "support substantial equivalence and performance claims" and that readers assessed image quality and compared noise texture and sharpness, implying favorable or equivalent performance.

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

   • Yes, extensive standalone (algorithm only) non-clinical engineering bench testing was performed. This included evaluations of:
     • Low contrast detectability (LCD)
     • Image Noise (pixel standard deviation)
     • High contrast spatial resolution (MTF)
     • Streak Artifact Suppression
     • Spatial Resolution
     • Noise Power Spectrum (NPS) and Standard Deviation of noise
     • CT Number Accuracy and Uniformity
     • Contrast to Noise (CNR) ratio
     • Artifact analysis - metal objects, unintended motion, truncation
     • Pediatric Image Quality Performance
     • Low Dose Lung Cancer Screening

6. The type of ground truth used:

   • For the clinical reader study, the ground truth was based on expert assessment/consensus (implying the "gold standard" for diagnostic image quality, noise texture, and sharpness was the radiologists' expert opinion). The cases were "retrospectively collected clinical cases," suggesting the presence of a known clinical diagnosis or outcome, but the specific ground truth for disease presence/absence is not explicitly stated as the primary output of the DLIR evaluation. The evaluation focused more on image quality attributes and comparison between reconstruction methods rather than diagnostic accuracy against a separate definitive truth.

7. The sample size for the training set:

   • The document states the Deep Neural Network (DNN) was "trained on the Revolution family CT Scanners" but does not provide the specific sample size (number of images or cases) used for training.

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

   • The text does not explicitly detail how the ground truth for the training set was established. It mentions the DNN was "designed and trained specifically to generate CT Images to give an image appearance... similar to traditional FBP images while maintaining the performance of ASiR-V in the following areas: dose, image noise (pixel standard deviation), low contrast detectability, high-contrast spatial resolution, and streak artifact suppression." This suggests the training likely involved pairing raw CT data with expertly reconstructed ASiR-V or FBP images as a reference for image quality characteristics. The ground truth in this context would be the desired output image characteristics (e.g., low noise, high resolution) that the DLIR algorithm was optimized to reproduce.

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 data taken at different angles and planes, including Axial, Cine, Helical (Volumetric), Cardiac, and Gated acquisitions. 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 X-ray Computed Tomography applications in patients of all ages.

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

The Revolution Ascend CT system is head and whole body CT system incorporating the same basic fundamental operating principles as the predicate device. It is composed of a gantry, patient table, operator console, host computer, and power distribution unit (PDU), and interconnecting cables. The system also includes image acquisition and reconstruction hardware/software, general system software, accompanying documents, and associated accessories, interconnections. Its materials and construction are identical to our existing marketed products.

Identical to the predicate, Revolution Ascend generates cross-sectional images of the body by computer reconstruction of x-ray transmission data taken at different angles and planes, including Axial, Cine, Helical (Volumetric), Cardiac, and Gated acquisitions modes. Revolution Ascend's Intended Use and Indications for Use remain identical to those of the predicate device.

Revolution Ascend includes virtually all the available features of the predicate device Revolution Maxima. Compared to the predicate, the changes incorporated into Revolution Ascend are primarily to introduce a widended bore gantry for easy handling of large patient, trauma examinations, interventional procedures and radiotherapy planning, and addition of other existing features already available from GE's other CT systems. These ported features include Auto Pilot workflow enabled by Deep learning based patient Auto Positioning, Intelligent Protocoling enabled by Machine Learning, Smart Plan and Auto Prescription all integrated into the modern software platform and GUI adopted from Revolution CT, and cardiac feature Auto Gating and as well as Interventional feature 3D Guidance.

The provided text describes a 510(k) premarket notification for a Computed Tomography (CT) system, Revolution Ascend, seeking substantial equivalence to a predicate device, Revolution Maxima. This document primarily focuses on demonstrating the new device's equivalence to an already cleared device rather than proving its performance against a new set of clinical acceptance criteria through a standalone study with human readers or specific AI performance metrics.

Therefore, the information required for a comprehensive answer regarding acceptance criteria and a study proving a device meets these criteria (especially for a medical AI/CADe device) is largely not present in this document. The submission is for a new iteration of a CT scanner, not a novel AI-powered diagnostic tool requiring specific clinical performance validation for its AI components against a defined ground truth.

However, I can extract the information that is implicitly or explicitly stated, and highlight where the requested information is absent or not applicable to this type of submission.

Acceptance Criteria and Device Performance (Implicit):

Since this is a 510(k) for substantial equivalence to a predicate CT system, the "acceptance criteria" are primarily that the new device, Revolution Ascend, performs as safely and effectively as the predicate device, Revolution Maxima, and other previously cleared GE CT systems for specific features. The performance is assessed through non-clinical bench testing, image quality (IQ) and dose evaluation using phantoms, and verification/validation testing.

Regarding the Study Proving the Device Meets Acceptance Criteria:

The document describes non-clinical testing for substantial equivalence, not a clinical study designed to prove new performance claims or the efficacy of novel AI features in a clinical setting with human readers.

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

   • Test Set Sample Size: No specific number of "cases" or "patients" for a clinical test set is mentioned. The testing involves "standard IQ, QA and ACR phantoms for standard conditions as well as challenging conditions such as with phantoms simulating large patients" and "3D guidance test with phantoms simulating interventional conditions." This indicates laboratory/bench testing using physical phantoms, not a dataset of patient images.
   • Data Provenance: Not applicable as clinical data are not the primary basis for performance evaluation in this submission. The tests are "non-clinical bench test results."

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

   • Not applicable. The "ground truth" for non-clinical phantom testing involves established physical properties, measurements, and engineering specifications, not expert clinical interpretation.

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

   • Not applicable as no human interpretation or adjudication of a test set is described.

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:

   • No MRMC study was done, nor is it described. This submission is for a CT system, not an AI/CADe device requiring direct clinical performance evaluation in synergy with human readers. While the device includes "Intelligent Protocoling enabled by Machine Learning" and "Auto Positioning by Deep Learning," these appear to be workflow/control features, not diagnostic AI features needing MRMC studies for reader performance improvement for a 510(k) submission.

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

   • No standalone performance study of a diagnostic algorithm is detailed. The performance assessment is focused on the CT system's image quality and dose output, verified through phantom studies and engineering testing, ensuring it's equivalent to the predicate.

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

   • For the non-clinical testing, the "ground truth" is based on the known physical properties of the phantoms, established metrics for image quality and dose (e.g., in accordance with IEC 61223-3-5), and design specifications. There's no clinical ground truth (e.g., pathology, expert consensus) involved.

7. The sample size for the training set:

   • The document mentions "Intelligent Protocoling enabled by Machine Learning" and "Auto Positioning by Deep Learning." However, it does not provide any details about the training data size, composition, or provenance for these AI features. As these are described as "workflow features" and integral to the CT system's operation (rather than standalone diagnostic AI tools with independent performance claims), such detail is typically not required for a 510(k) of a CT scanner. They are presented as existing, ported features or minor enhancements that don't alter the fundamental operating principles or intended use.

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

   • Not described/provided in the document. (See point 7).

Ask a specific question about this device

The Deep Learning Image Reconstruction software 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 software 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 software support a normal throughput for routine CT.

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.

Deep Learning Image Reconstruction software was initially introduced on the Revolution CT systems (K133705, K163213). The DLR algorithm is now ported to Revolution EVO (K131576), which offers 64 detector row and up to 40mm collimation, and ASIR-V reconstruction option.

Here's a breakdown of the acceptance criteria and study details based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly state quantitative "acceptance criteria" in a pass/fail format with numerical thresholds. Instead, it describes performance goals relative to the predicate device (ASiR-V) or traditional FBP images. The reported device performance generally indicates "as good as or better than" the reference.

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

• Sample Size: 60 retrospectively collected clinical cases.
• Data Provenance: Retrospective. The origin country is not explicitly stated, but the submitter is GE Healthcare Japan Corporation, so it's possible some or all cases originated from Japan or a region where GE Healthcare Japan Corporation operates.

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

• Number of Experts: 7 board-certified radiologists.
• Qualifications: Board-certified radiologists with expertise in the specialty areas that align with the anatomical region of each case. The document does not specify years of experience.

4. Adjudication Method for the Test Set

• Adjudication Method: Each image was read by 3 different radiologists who provided independent assessments of image quality. The readers were blinded to the results of other readers' assessments. There is no explicit mention of an adjudication process (e.g., 2+1 or 3+1 decision) for discrepant reader opinions; it appears the individual assessments were analyzed.

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 Study: Yes, a clinical reader study was performed where 7 radiologists read images reconstructed with both ASiR-V (without DLIR) and DLIR.
• Effect Size of Human Reader Improvement: The document states that readers were asked to "compare directly the ASIR-V and Deep Learning Image Reconstruction (DLIR) images according to three key metrics of image quality preference – image noise texture, image sharpness, and image noise texture homogeneity." It reports that the results support substantial equivalence and performance claims and implies a preference for DLIR images, but does not quantify the effect size of how much human readers "improve" with AI assistance in terms of diagnostic accuracy or efficiency. The study primarily focused on radiologists' preference for image quality characteristics.

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

• Standalone Performance: Yes, extensive non-clinical engineering bench testing was performed where DLIR and ASiR-V reconstructions were compared using identical raw datasets. This included objective metrics such as Low Contrast Detectability (LCD), Image Noise (pixel standard deviation), High-Contrast Spatial Resolution (MTF), Streak Artifact Suppression, Noise Power Spectrum (NPS), CT Number Accuracy and Uniformity, and Contrast to Noise (CNR) ratio. This constitutes a standalone (algorithm-only) performance evaluation.

7. The Type of Ground Truth Used

• For the Reader Study (Clinical Performance): The ground truth for evaluating diagnostic use was based on the assessment of image quality related to diagnostic use according to a 5-point Likert Scale by board-certified radiologists. This is a form of expert consensus on image quality suitable for diagnosis, rather than a definitive "truth" established by pathology or patient outcomes.
• For the Bench Testing (Technical Performance): The "ground truth" was the objective measurement of various image quality metrics (e.g., pixel standard deviation for noise, MTF for spatial resolution) in phantoms, which have known properties.

8. The Sample Size for the Training Set

• The document states that the Deep Neural Network (DNN) used in Deep Learning Image Reconstruction was "trained specifically" but does not disclose the sample size of the training set.

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

• The document implies that the DNN was trained to generate CT Images to give an image appearance similar to traditional FBP images while maintaining ASiR-V performance in certain areas. This suggests that existing "traditional FBP images" or images reconstructed with "ASiR-V" served as a reference or a form of "ground truth" for the training process. However, the exact methodology for establishing ground truth during the training phase (e.g., using paired low-dose/high-dose images, or simulated noise reduction) is not detailed in the provided text.

Ask a specific question about this device

The SIGNA Pioneer 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 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 the SIGNA Pioneer 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.

The SIGNA Pioneer features a 3.0T superconducting magnet with a 70cm bore size. The RF receiver is equipped with 97 RF channels. The data acquisition system accommodates 32 channels for image reconstruction simultaneously. The system uses a combination of time-varying magnetic fields (gradients) and RF transmissions to obtain information regarding the density and position of nuclei exhibiting magnetic resonance. The system can image in the sagittal, coronal, axial, oblique, and double oblique planes, using various pulse sequences and reconstruction algorithms. The SIGNA Pioneer uses multi-drive RF transmit for imaging of the head and body regions. The SIGNA Pioneer is designed to conform to NEMA DICOM standards.

The provided document is a 510(k) summary for the GE Healthcare SIGNA Pioneer Magnetic Resonance Diagnostic Device. It states that the device has been found substantially equivalent to a predicate device (Discovery MR750w 3.0T, K142085). The summary primarily focuses on affirming that the SIGNA Pioneer performs equivalently to the predicate device and meets established safety standards rather than establishing new acceptance criteria for an AI/algorithm-driven device.

Therefore, the information requested in the prompt, which is typically relevant for studies evaluating the performance of AI/algorithm-driven devices against specific acceptance criteria, is largely not present in this document. This document describes a traditional medical device (an MRI scanner) and its substantial equivalence to another MRI scanner, not a standalone AI diagnostic software.

However, I can extract the relevant information that is present and identify what is missing based on your questions.

1. Table of Acceptance Criteria and Reported Device Performance

The document does not present specific "acceptance criteria" in the format of a table with numerical thresholds for performance metrics for an AI/algorithm. Instead, it states that the device was verified to meet safety criteria and demonstrated acceptable diagnostic imaging performance, which is "substantially equivalent" to the predicate device.

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

• Test Set Sample Size: Not specified. The document only mentions "clinical images and clinical results summary" were used, but no numbers are provided for cases or subjects.
• Data Provenance: Not specified (e.g., country of origin, retrospective/prospective).

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

• Number of Experts: Not specified.
• Qualifications: The document states that "images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis." This implies physicians were involved in interpreting clinical data, but their number and specific qualifications (e.g., years of experience, subspecialty) are not detailed.

4. Adjudication Method for the Test Set

• Not specified.

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

• Was it done?: No, a traditional MRMC comparative effectiveness study as typically understood for AI-assisted reading was not performed or described. The comparison is between the SIGNA Pioneer MRI device and a predicate MRI device, focusing on substantial equivalence in overall performance and safety, not on how an AI improves human reader performance.
• Effect size of AI improvement: Not applicable, as this was not an AI assistance study.

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

• Was it done?: No. This document describes an MRI scanning device, which produces images for physician interpretation. It is not an algorithm that performs a diagnosis in a standalone manner. The device's "performance" refers to the quality of the images it produces and its adherence to safety standards.

7. Type of Ground Truth Used

• The document implies that "clinical images and clinical results" were evaluated, likely against the interpretations of "trained physicians" (expert consensus based on clinical findings) for diagnostic imaging performance. However, specific methodologies for establishing ground truth (e.g., pathology, long-term outcomes) are not detailed.

8. Sample Size for the Training Set

• Not applicable/Not specified. This device is a hardware scanner, not a machine learning algorithm that requires a training set in the conventional sense for its primary function. While some integrated software features might have been developed using data, the document does not distinguish or describe a "training set" for the fundamental device performance.

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

• Not applicable/Not specified for the reasons stated above.

Ask a specific question about this device

The Discovery MR750w 3.0T 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 the Discovery MR750w 3.0T 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.

The Discovery MR750w 3.0T features a superconducting magnet operating at 3.0 Tesla. The data acquisition system accommodates up to 32 independent receive channels in various increments, and multiple independent coil elements per channel during a single acquisition series. The system uses a combination of time-varying magnetic fields (gradients) and RF transmissions to obtain information regarding the density and position of elements exhibiting magnetic resonance. The RF technology of the Discovery MR750w system integrates an RF transmit architecture designed to improve the overall image uniformity. This technology, called Multi-drive, optimizes RF transmit by adjusting the amplitude and phase of the RF output depending on the anatomy being scanned. In order to support Multi-Drive, the RF Transmit (Tx) chain is changed from MR750 and both Tx lines are divided into 2 lines with Dual output Exciter, Dual output RF amp, Dual Transmit/Receive Switch (DTRSW), dual UPM and a 70cm-wide patient bore RF body coil. The system can image in the sagittal, coronal, axial, oblique and double oblique planes, using various pulse sequences and reconstruction algorithms. The Discovery MR750w 3.0T is designed to conform to NEMA DICOM standards (Digital Imaging and Communications in Medicine).

Here's a breakdown of the requested information based on the provided 510(k) summary for the Discovery MR750w 3.0T.

1. Table of Acceptance Criteria and Reported Device Performance

The 510(k) summary for the Discovery MR750w 3.0T primarily focuses on demonstrating substantial equivalence to predicate devices and adherence to established standards for safety and performance testing for Magnetic Resonance Imaging (MRI) systems. It does not provide specific numerical acceptance criteria with corresponding reported performance values in a direct table format. Instead, it states that various parameters "have been measured and documented through testing to NEMA, IEC or ISO standards" and that these tests were "executed with acceptable results."

Performance Parameters Tested:

Safety Parameters Tested:

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

The document does not explicitly state a specific sample size for a "test set" in the context of clinical studies where individual cases are evaluated for device performance against a ground truth. Instead, it refers to "clinical images and clinical results summary" used to demonstrate imaging performance.

• Sample Size: Not explicitly stated. The summary refers to "clinical images and clinical results summary" but does not quantify the number of patients or images.
• Data Provenance: The manufacturing entity is GE Healthcare, (GE Healthcare Japan Corporation) and the contact person is in Japan. However, the document does not specify the country of origin of the clinical data (e.g., patient demographics, where the scans were acquired). It does not explicitly state whether the data was retrospective or prospective.

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

The document does not detail the process of establishing ground truth for a clinical test set in the way one might expect for an AI/CAD device. It states, "These images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis." This implies that the interpretation by trained physicians (plural) constitutes the clinical reference standard or ground truth.

• Number of Experts: The document does not specify the number of experts. It generally refers to interpretation by "a trained physician" (singular in the Indications for Use, but "physicians" is implied for general clinical practice).
• Qualifications of Experts: The document only states "trained physician." No specific qualifications (e.g., specialty, years of experience) are provided.

4. Adjudication Method for the Test Set

The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for a test set. This type of detail is typically found in studies for AI-powered diagnostic devices, where disagreements among readers about ground truth or device performance are resolved. For this MRI system, the primary focus is on technical performance and equivalence to predicates, rather than a diagnostic performance study with specific adjudication.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a Multi-Reader Multi-Case (MRMC) comparative effectiveness study was not explicitly described or reported in this 510(k) summary. The document does not discuss human reader performance, with or without AI assistance. The summary's focus is on the device's technical performance and safety, and its substantial equivalence to predicate MRI systems.

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

The Discovery MR750w 3.0T is a Magnetic Resonance Imaging System, not an algorithm or AI-powered diagnostic tool in the typical sense that would have "standalone performance" evaluated for diagnostic accuracy. It's a hardware system that generates images. Therefore, the concept of "standalone performance" as it applies to an algorithm without human-in-the-loop is not relevant here. The device's performance is inherently tied to the quality of the images it produces, which are then interpreted by a human physician.

7. The Type of Ground Truth Used

The ground truth for clinical evaluation is implicitly based on expert consensus/interpretation by trained physicians using the images produced by the device. The document states that "images and/or spectra when interpreted by a trained physician yield information that may assist in diagnosis." This suggests the clinical utility is assessed through conventional medical diagnostic workflows. There is no mention of pathology, long-term outcomes data, or other objective ground truth methods.

8. The Sample Size for the Training Set

The concept of a "training set" is not applicable in the context of this 510(k) submission. The Discovery MR750w 3.0T is an MRI system, a hardware device, not a machine learning or AI algorithm that requires a training set of data. Its design and performance are based on engineering principles, physics, and established medical imaging standards, rather than learned patterns from a dataset.

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

Since the device is an MRI system and not an AI algorithm, there is no "training set" or corresponding ground truth establishment process in the machine learning sense. The device's operational parameters and image quality are validated against physical phantoms, engineering specifications, and established industry standards (NEMA, IEC, ISO).

Ask a specific question about this device