Search Results

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

uCT ATLAS is a computed tomography x-ray system, which is intended to produce cross-sectional images of the whole body by computer reconstruction of x-ray transmission data taken at different angles and planes. uCT ATLAS is applicable to head, whole body, cardiac, and vascular x-ray Computed Tomography.

uCT ATLAS has the capability to image a whole organ in a single rotation. Organs include, but not limited to head, heart, liver, kidney, pancreas, joints, etc.

uCT ATLAS is intended to be used for low dose CT lung cancer screening for the early detection of lung nodules that may represent cancer. The screening must be performed within the established inclusion criteria of protocols that have been approved and published by either a governmental body or professional medical society. * Please refer to clinical literature, including the results of the National Lung Screening Trial (N Engl J Med 2011; 365:395-409) and subsequent literature, for further information.

u WS-CT-Dual Energy Analysis software uses UIH CT images acquired using different tube voltages and/or tube currents of the same anatomical location. The various materials of an anatomical region of interest have different attenuation coefficients, which depend on the used energy. These differences provide information on the chemical composition of the scanned body materials and enable images to be generated at multiple energies within the available spectrum. uWS-CT-Dual Energy Analysis software combines images acquired with low and high energy spectra to visualize this information.

The proposed device uCT ATLAS with uWS-CT-Dual Energy Analysis includes image acquisition hardware, image acquisition, reconstruction and dual energy analysis software, and associated accessories.

The uCT ATLAS is a multi-slice computed tomography scanner that features the following specification and technologies.

• 160 mm z-coverage in a single axial exposure with a 320-row 0.5 mm-slice Z-• Detector
• . 0.25 s rotation speed for high temporal resolution, and maximum 440 mm/s fast volumetric scanning capability
• . 82 cm bore size, 318 kg (700 lbs) maximum table load capacity allows flexible positioning and access for all patients
• . The new generation reconstruction method. Deep IR (also named AIIR), which combines the model-based iterative reconstruction and deep learning technology together, in order to reduce image noise and artifacts, while at the same time improving low contrast detectability and spatial resolution
• . The uAI Vision patient positioning assistance
  Built upon these technologies, the uCT ATLAS is designed to use less radiation dose than the previous generation product while maintaining the same diagnostic level of image quality. Further, the whole organ coverage and fast scanning capability benefits the clinical applications, especially for cardiac imaging, dynamic whole organ imaging and fast body and vascular imaging.

The uWS-CT-Dual Energy Analysis is a software package that uses UIH CT images acquired using different tube voltages and/or tube currents of the same anatomical location. The various materials of an anatomical region of interest have different attenuation coefficients, which depend on the used energy. These differences provide information on the chemical composition of the scanned body materials. CT dual energy analysis application combines images acquired with low and high energy spectra to visualize this information.

The provided text does not contain information about specific acceptance criteria or a detailed study proving that a device meets those criteria. The document is a 510(k) premarket notification summary for the uCT ATLAS with uWS-CT-Dual Energy Analysis system. It focuses on demonstrating substantial equivalence to a predicate device rather than presenting a performance study against predefined acceptance criteria.

While the document mentions "Performance Verification" and "Clinical Image Evaluation of applications," and states that "The testing results show that all the software specifications have met the acceptance criteria," it does not provide:

• A table of acceptance criteria and reported device performance.
• Details on sample sizes, data provenance, number or qualifications of experts, or adjudication methods for test sets.
• Information on multi-reader multi-case (MRMC) comparative effectiveness studies or standalone algorithm performance.
• Specifics about the type of ground truth used or how ground truth for training sets was established.

The document states that "No Clinical Study is included in this submission," which further indicates that the detailed information you're requesting regarding clinical performance studies isn't present in this specific FDA submission summary.

The closest information available is:

• Non-Clinical Testing: Includes dosimetry and image performance tests, and conformance to various electrical safety, EMC, and product particular standards (e.g., NEMA XR 25-2019, IEC 61223-3-5). The acceptance criteria for these would be compliance with the specified standards, but the specific performance values are not detailed.
• Software Verification and Validation: Mentions that "all the software specifications have met the acceptance criteria," but does not list those criteria or performance results.

In summary, the provided document focuses on regulatory clearance through substantial equivalence, indicating that the device has similar performance and safety as legally marketed predicate devices. It does not contain the detailed performance study information you are seeking.

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 ans the capability to image whole organs in a single rotation. Whole organs include but are not limited to brain, heart, liver, kidney, pancreas, etc. 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 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 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 of body materials. This approach enables images to be generated at energies selected from the visualize and analyze information about anatomical and pathological structures.

GSI provides information of the chemical composition of renal calculation and graphical display of the spectrum of effective atomic number. GSI Kidney stone characterization orovides addin the characterization of uric acid versus nonuric acid stones. It is intended to be used as an adjunct to current standard methods for evaluating stone etiology and composition.

The Revolution CT is a multi-slice (256 detector row) CT scanner consisting of a gantry, patient table, scanner desktop (operator console), system cabinet, power distribution unit (PDU), and interconnecting cables. The system includes image acquisition hardware, image acquisition and reconstruction software, and associated accessories.

GE has modified the cleared Revolution CT (K133705) within our design controls to include the Gemstone™ Spectral Imaging (GSI) Option. GSI is the state-of-the-art single source, projection-based, spectral CT application. It is GE's unique dual energy design and implementation which offers clear advantage over traditional dual source Dual Energy implementation. This feature has been previously cleared on Discovery CT750 HD (K081105, K120833) and it is fundamentally the same technology on Revolution CT. Revolution CT however offers a few technology improvements to enable Volume GSI with up to 80mm GSI zcollimation, 245mm/s GSI volumetric scan speed, dose neutrality and more improved workflow to support GSI in routine scanning.

The provided text is a 510(k) summary for the GE Revolution CT with GSI option. The document describes the device, its intended use, and indicates that it is substantially equivalent to predicate devices. However, it does not explicitly detail acceptance criteria in a quantitative table or a specific study proving the device meets acceptance criteria in the way often associated with performance claims for AI/ML devices.

Instead, the document focuses on demonstrating substantial equivalence by outlining:

• Technological similarities and differences with predicate devices.
• Compliance with various industry standards (IEC, 21CFR Subchapter J, NEMA XR-25, XR-26, XR-28, XR-29).
• Adherence to quality system regulations (21CFR 820 and ISO 13485).
• Results from non-clinical (phantom) testing and clinical testing.

The clinical testing aimed to evaluate "image quality related to diagnostic use, reduction of metal artifacts using the MAR algorithm, and suppression of iodine in contrast enhanced acquisitions using VUE algorithm." The evaluation was based on a 5-point Likert scale by radiologists, indicating a subjective assessment of image quality and clinical acceptance rather than predefined quantitative performance metrics or acceptance criteria for a specific diagnostic task.

Therefore, many of the requested items cannot be fully extracted as they are not explicitly or quantitatively provided in the document.

Here's an attempt to answer based on the available information:

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

The document does not provide a quantitative table of acceptance criteria for diagnostic performance metrics (e.g., sensitivity, specificity, AUC) and therefore no numerical performance results against such criteria. The clinical assessment focused on "acceptable diagnostic imaging performance" and "image quality," which are qualitative statements derived from expert review.

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

• Sample Size (Test Set): 51 subjects.
• Data Provenance: The clinical data was collected from two sites: one in the US and one in Canada. The study was prospective in the sense that it involved recruitment of patients and collection of clinical images for the specific evaluation.

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)

• Number of experts: 6 board-certified and qualified radiologists.
• Qualifications: "board certified and qualified radiologists at different institutions in the United States of America." (Specific years of experience are not mentioned).
• Ground Truth establishment for Test Set: This refers to the radiologists evaluating the images for "clinical acceptance and image quality using a 5 point Likert scale." This implies a subjective expert assessment of image quality for diagnostic use, reduction of metal artifacts, and suppression of iodine, rather than a definitive "ground truth" for a specific disease outcome or pathology.

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

• "Each data set was read by three different radiologists depending on their area of expertise." This implies a consensus or individual review approach, but the specific adjudication method (e.g., how disagreements between the three radiologists were resolved or combined into a single outcome) is not specified. It's unclear if a formal adjudication process like 2+1 or 3+1 was used, or if individual reads were separately 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

The document describes an evaluation of the device’s image quality and diagnostic performance by multiple radiologists ("multi-reader"). However, it is not an MRMC comparative effectiveness study comparing human readers with AI assistance vs. without AI assistance. The study evaluated the images produced by the device (which includes the GSI option, a form of advanced image processing, but not explicitly framed as an 'AI assistance' to human interpretation in the common sense of AI CAD/X systems) directly for their diagnostic quality. Therefore, there's no reported effect size of human improvement with vs. without AI assistance.

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

The GSI functionality itself could be considered a form of "algorithm only" processing that produces specific images/data (e.g., material density maps, monochromatic images, virtual unenhanced images, information for kidney stone characterization). The document states GSI "provides information of the chemical composition of renal calculi by calculation and graphical display of the spectrum of effective atomic number" and "provides additional information to aid in the characterization of uric acid versus non-uric acid stones." This output is interpreted by humans. The testing described focuses on the quality of these generated images/information as assessed by radiologists, not on an automated diagnostic output from the algorithm itself without human interpretation. So, while GSI involves algorithms, it's not presented as a standalone diagnostic algorithm in the typical sense of AI/CAD systems providing a diagnosis.

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

• The "ground truth" for the clinical evaluation of the test set was essentially expert assessment/consensus based on image quality and clinical acceptance using a Likert scale. It was not based on definitive pathology, histology, or long-term outcomes data for establishing true disease presence or absence for a diagnostic accuracy study. For kidney stone characterization, it 'provides additional information' and is 'intended to be used as an adjunct to current standard methods for evaluating stone etiology and composition,' implying that the ultimate ground truth for stone composition would come from other established methods.

8. The sample size for the training set

The document does not explicitly mention a "training set" with a specified sample size. This device is an imaging system (CT scanner) with advanced image processing (GSI), not a machine learning model that would typically have a distinct training set for diagnostic classification in the same way. The technologies are based on physics and signal processing, using proprietary algorithms.

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

Since a "training set" for a machine learning model is not explicitly described, neither is the method for establishing its ground truth. The development of the GSI algorithms would have involved engineering and possibly empirical data to refine the material decomposition and image generation, but this is not characterized as a "training set" in the context of supervised learning.

Ask a specific question about this device

The GSI Viewer accepts images from a CT System that 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 GSI Viewer with VUE option employs the same technology as the Technology: that of the GSI Viewer on its predicate device.

The GSI Viewer accepts images from a CT System that 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 on non-contrast studies as an adjunct to current standard methods for evaluating stone etiology and composition.

The unmodified device Discovery CT750 HD (K120833) offers the Gemstone Spectral Imaging (GSI) capability that uses rapid kV switching to acquire the dual energy samples almost simultaneously. This enables generation of material density data that can be used for the separation of materials and derivation of monochromatic spectral images using a projection based reconstruction algorithm.

GSI Viewer is a post processing visualization tool on the Discovery CT750 HD system that allows users to view and process spectral images acquired by the GSI scan modes. It allows for the review of monochromatic energy images at user selectable energy levels, detailed analysis using material decomposed images (such as water-iodine, water calcium, etc.), and complementary information using the Effective-Z images by providing an estimate of the protons' effective atomic number in a voxel.

The modification being introduced is the VUE (Virtual Unenhanced Exam) option that produces a material suppressed image at a given monochromatic energy in the conventional CT Hounsfield Units.

This modification is based on the existing capability of the predicate device that generates material separated images in the Material density (MD) space and is the subject of this pre-market notification.

The provided 510(k) summary for the GE Healthcare GSI Viewer with VUE Option does not include a study that proves the device meets specific acceptance criteria related to its performance.

Instead, the submission states that:

• The device did not require clinical studies to support substantial equivalence.
• GE Healthcare considers the device to be as safe, as effective, and its performance substantially equivalent to the predicate device.

Therefore, many of the requested details cannot be extracted from this document, as a performance study with defined acceptance criteria was not conducted or reported in this summary.

Here's a breakdown of the specific points based on the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

Not applicable. The document explicitly states: "The subject of this premarket submission, GSI Viewer with VUE option, did not require clinical studies to support substantial equivalence." Therefore, no specific acceptance criteria for performance and no reported performance metrics for these criteria are provided.

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

Not applicable. No clinical or performance study involving a test set was reported as part of this 510(k) summary.

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

Not applicable. No ground truth establishment activity was reported, as no clinical or performance study was conducted.

4. Adjudication method for the test set

Not applicable. No test set adjudication method was reported, as no clinical or performance study was conducted.

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

Not applicable. An MRMC comparative effectiveness study was not done. The device description indicates it's a "post processing visualization tool" and a "material suppressed image" option, rather than an AI-assisted diagnostic tool designed to directly improve human reader performance. No human-in-the-loop performance improvement data is provided.

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

Not applicable. No standalone performance study was reported. The device is described as a "GSI Viewer" and an "Option" within an existing viewing system, performing "generation of material density data" and "material suppressed images." No algorithm-only performance metrics were provided.

7. The type of ground truth used

Not applicable. No clinical or performance study requiring ground truth was reported.

8. The sample size for the training set

Not applicable. The document does not describe the development of a machine learning or AI model that would typically require a training set. The modification "is based on the existing capability of the predicate device that generates material separated images in the Material density (MD) space." This suggests an algorithmic modification rather than a data-driven model.

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

Not applicable. As no training set was reported (see point 8), there is no information on how its ground truth might have been established.

Summary of what was done instead of a performance study:

The submission focuses on demonstrating substantial equivalence to a predicate device (K120833 Discovery CT750 HD) based on:

• The GSI Viewer with VUE Option employing the "same technology" as the GSI Viewer on its predicate device.
• Compliance with voluntary standards.
• Application of standard quality assurance measures during development: Risk Analysis, Requirements Reviews, Design Reviews, Performance testing (Verification), Safety testing (Verification), and Final acceptance testing (Validation). (Note: "Performance testing (Verification)" and "Final acceptance testing (Validation)" here refer to engineering/software testing against functional requirements, not clinical performance against acceptance criteria in a comparative study).

Ask a specific question about this device