Search Results

AI-Rad Companion Organs RT is a post-processing software intended to automatically contour DICOM CT and MR predefined structures using deep-leaming-based algorithms.

Contours that are generated by AI-Rad Companion Organs RT may be used as input for clinical workflows including external beam radiation therapy treatment planning. AI-Rad Companion Organs RT must be used in conjunction with appropriate software such as Treatment Planning Systems and Interactive Contouring applications, to review, edit, and accept contours generated by AI-Rad Companion Organs RT.

The output of AI-Rad Companion Organs RT are intended to be used by trained medical professionals.

The software is not intended to automatically detect or contour lesions.

AI-Rad Companion Organs RT provides automatic segmentation of pre-defined structures such as Organs-at-risk (OAR) from CT or MR medical series, prior to dosimetry planning in radiation therapy. AI-Rad Companion Organs RT is not intended to be used as a standalone diagnostic device and is not a clinical decision-making software.

CT or MR series of images serve as input for AI-Rad Companion Organs RT and are acquired as part of a typical scanner acquisition. Once processed by the AI algorithms, generated contours in DICOM-RTSTRUCT format are reviewed in a confirmation window, allowing clinical user to confirm or reject the contours before sending to the target system. Optionally, the user may select to directly transfer the contours to a configurable DICOM node (e.g., the TPS, which is the standard location for the planning of radiation therapy).

The output of AI-Rad Companion Organs RT must be reviewed and, where necessary, edited with appropriate software before accepting generated contours as input to treatment planning steps. The output of AI-Rad Companion Organs RT is intended to be used by qualified medical professionals. The qualified medical professional can perform a complementary manual editing of the contours or add any new contours in the TPS (or any other interactive contouring application supporting DICOM-RT objects) as part of the routine clinical workflow.

Here's a summary of the acceptance criteria and the study that proves the device meets them, based on the provided FDA 510(k) summary for AI-Rad Companion Organs RT:

1. Table of Acceptance Criteria and Reported Device Performance

The acceptance criteria and reported performance are detailed for both MR and CT contouring algorithms.

MR Contouring Algorithm Performance

CT Contouring Algorithm Performance

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

• MR Contouring Algorithm Test Set:
  • Sample Size: N = 66
  • Data Provenance: Retrospective study, data from multiple clinical sites across North America & Europe. The document further breaks this down for different sequences:
    • T1 Dixon W: 30 datasets (USA: 15, EU: 15)
    • T2 W TSE: 36 datasets (USA: 25, EU: 11)
    • Manufacturer: All Siemens Healthineers scanners.
• CT Contouring Algorithm Test Set:
  • Sample Size: N = 414
  • Data Provenance: Retrospective study, data from multiple clinical sites across North American, South American, Asia, Australia, and Europe. This dataset is distributed across three cohorts:
    • Cohort A: 73 datasets (Germany: 14, Brazil: 59) - Siemens scanners only
    • Cohort B: 40 datasets (Canada: 40) - GE: 18, Philips: 22 scanners
    • Cohort C: 301 datasets (NA: 165, EU: 44, Asia: 33, SA: 19, Australia: 28, Unknown: 12) - Siemens: 53, GE: 59, Philips: 119, Varian: 44, Others: 26 scanners

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

• The ground truth annotations were "drawn manually by a team of experienced annotators mentored by radiologists or radiation oncologists."
• "Additionally, a quality assessment including review and correction of each annotation was done by a board-certified radiation oncologist using validated medical image annotation tools."
• The exact number of individual annotators or experts is not specified beyond "a team" and "a board-certified radiation oncologist." Their specific experience level (e.g., "10 years of experience") is not given beyond "experienced" and "board-certified."

4. Adjudication Method for the Test Set

• The document implies a consensus/adjudication process: "a quality assessment including review and correction of each annotation was done by a board-certified radiation oncologist." This suggests that initial annotations by the "experienced annotators" were reviewed and potentially corrected by a higher-level expert. The specific number of reviewers for each case (e.g., 2+1, 3+1) is not explicitly stated, but it was at least a "team" providing initial annotations followed by a "board-certified radiation oncologist" for quality assessment/correction.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done

• No, the document does not describe a Multi-Reader Multi-Case (MRMC) comparative effectiveness study evaluating how much human readers improve with AI vs. without AI assistance. The validation studies focused on the standalone performance of the algorithm against expert-defined ground truth.

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

• Yes, the performance validation described in section 10 ("Performance Software Validation") is a standalone (algorithm only) performance study. The metrics (Dice, ASSD, Fail Rate) compare the algorithm's output directly to the established ground truth. The device produces contours that must be reviewed and edited by trained medical professionals, but the validation tests the AI's direct output.

7. The Type of Ground Truth Used

• The ground truth used was expert consensus/manual annotation. It was established by "manual annotation" by "experienced annotators mentored by radiologists or radiation oncologists" and subsequently reviewed and corrected by a "board-certified radiation oncologist." Annotation protocols followed NRG/RTOG guidelines.

8. The Sample Size for the Training Set

• MR Contouring Algorithm Training Set:
  • T1 VIBE/Dixon W: 219 datasets
  • T2 W TSE: 225 datasets
  • Prostate (T2W): 960 datasets
• CT Contouring Algorithm Training Set: The training dataset sizes vary per organ group:
  • Cochlea: 215
  • Thyroid: 293
  • Constrictor Muscles: 335
  • Chest Wall: 48
  • LN Supraclavicular, Axilla Levels, Internal Mammaries: 228
  • Duodenum, Bowels, Sigmoid: 332
  • Stomach: 371
  • Pancreas: 369
  • Pulmonary Artery, Vena Cava, Trachea, Spinal Canal, Proximal Bronchus: 113
  • Ventricles & Atriums: 706
  • Descending Coronary Artery: 252
  • Penile Bulb: 854
  • Uterus: 381

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

• For both training and validation data, the ground truth annotations were established using the "Standard Annotation Process." This involved:
  • Annotation protocols defined following NRG/RTOG guidelines.
  • Manual annotations drawn by a team of experienced annotators mentored by radiologists or radiation oncologists using an internal annotation tool.
  • A quality assessment including review and correction of each annotation by a board-certified radiation oncologist using validated medical image annotation tools.
• The document explicitly states that the "training data used for the training of the algorithm is independent of the data used to test the algorithm."

Ask a specific question about this device

AI-Rad Companion Brain MR is a post-processing image analysis software that assists clinicians in viewing, analyzing, and evaluating MR brain images.

AI-Rad Companion Brain MR VA50 is an enhancement to the predicate, AI-Rad Companion Brain MR VA40 (K213706). Just as in the predicate, the brain morphometry feature of AI-Rad Companion Brain MR addresses the automatic quantification and visual assessment of the volumetric properties of various brain structures based on T1 MPRAGE datasets. From a predefined list of brain structures (e.g. Hippocampus, Caudate, Left Frontal Gray Matter, etc.) volumetric properties are calculated as absolute and normalized volumes with respect to the total intracranial volume. The normalized values are compared against age-matched mean and standard deviations obtained from a population of healthy reference subjects. The deviation from this reference population can be visualized as 3D overlay map or out-of-range flag next to the quantitative values.

Additionally, identical to the predicate, the white matter hyperintensities feature addresses the automatic quantification and visual assessment of white matter hyperintensities on the basis of T1 MPRAGE and T2 weighted FLAIR datasets. The detected WMH can be visualized as a 3D overlay map and the quantification in count and volume as per 4 brain regions in the report.

Here's a breakdown of the acceptance criteria and study details for the AI-Rad Companion Brain MR device, based on the provided FDA 510(k) summary:

Acceptance Criteria and Device Performance

Study Details

1. Sample Size and Data Provenance:

   • Test Set Sample Size: 75 subjects / 150 studies (2 scans per subject).
   • Data Provenance: The data originate from a mix of retrospective and potentially prospective sources, from both the US and Europe:
     • UPenn (US): 15 subjects
     • ADNI (US): 15 subjects
     • Lausanne (EU): 22 subjects
     • Prague (EU): 23 subjects
     • Medical Indication: 60 Multiple Sclerosis (MS) patients, 15 Alzheimer's (AD) patients.
     • Age Range: 25-88 years.
     • Gender Distribution: 56 females, 19 males.
     • Scanner Info: Siemens 3.0T MR scanners, T1w MPRAGE and T2w FLAIR scan protocols.

2. Number of Experts and Qualifications for Ground Truth:

   • The document states that for each dataset, three sets of ground truth were manually annotated. Each set was annotated by a "disjoint group of annotator, reviewer, and clinical expert."
   • For the initial annotation and review, "in-house annotators" and "in-house reviewers" were used.
   • For final review and correction, a "clinical expert" was used, randomly assigned per case to minimize bias.
   • Specific qualifications (e.g., years of experience, board certification) for these experts are not explicitly stated in the provided text, beyond being "clinical experts."

3. Adjudication Method for Test Set:

   • The ground truth process involved a multi-step adjudication. For each test dataset:
     1. Three initial annotations by three different in-house annotators.
     2. Each initial annotation was reviewed by an in-house reviewer.
     3. Each initial annotation (after in-house review) was reviewed by a reference clinical expert.
     4. If corrections by the clinical expert were "significant and time-consuming," they were communicated back to the annotator for correction and then re-reviewed.
   • This resembles a form of iterative consensus building and expert adjudication, where multiple initial annotations are refined through reviewer and expert input, rather than a strict N+1 or N+M voting system for final ground truth, though the final decision appears to rest with the clinical expert.

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

   • No MRMC study was done. The document explicitly states: "The predicate (K213706) was not validated using clinical tests and therefore no clinical tests were conducted to test the performance and functionality of the modifications introduced within AI-Rad Companion Brain MR."
   • The validation focused on standalone algorithmic performance compared to expert-established ground truth and comparison against a "reference device" (icobrain) using equivalent validation methodology for the WMH follow-up feature.
   • Therefore, there's no reported effect size of human readers improving with AI vs. without AI assistance.

5. Standalone (Algorithm Only) Performance Study:

   • Yes, a standalone performance study was conducted for the WMH follow-up feature. The acceptance criteria and reported performance metrics (PCC, Dice, F1-score) are for the algorithm's performance against the established ground truth.

6. Type of Ground Truth Used:

   • The ground truth for the White Matter Hyperintensities (WMH) Follow-Up Feature was established through expert consensus and manual annotation. It involved a "disjoint group of annotator, reviewer, and clinical expert" for each ground truth dataset. The clinical expert performed the final review and correction.

7. Training Set Sample Size:

   • The document states: "The training data used for the fine tuning the hyper parameters of WMH follow-up algorithm is independent of the data used to test the white matter hyperintensity algorithm follow up algorithm."
   • However, the specific sample size for the training set is not provided in the given text. It mentions independent training data but does not quantify it.

8. How Ground Truth for Training Set was Established:

   • The document mentions that training data was used for "fine tuning the hyper parameters." While it implies that the training data would also require ground truth, the method for establishing ground truth for the training set is not explicitly described in the provided text. It only states that the training data was "independent" of the test data. Given the "WMH follow-up algorithm does not include any machine learning component," the type of "training" might refer to calibration or rule optimization rather than machine learning model training in the conventional sense, and subsequently, how ground truth for that calibration was established is not detailed.

Ask a specific question about this device

AI-Rad Companion (Cardiovascular) is image processing software that provides quantitative and qualitative analysis from previously acquired Computed Tomography DICOM images to support radiologists and physicians from emergency medicine, specialty care, urgent care, and general practice in the evaluation and assessment of cardiovascular diseases.

It provides the following functionality:

• Segmentation and volume measurement of the heart
• Quantification of the total calcium volume in the coronary arteries
• Segmentation of the aorta
• Measurement of maximum diameters of the aorta at typical landmarks
• Threshold-based highlighting of enlarged diameters

The software has been validated for non-cardiac chest CT data with filtered backprojection reconstruction from Siemens Healthineers, GE Healthcare, Philips, and Toshiba/Canon. Additionally, the calcium detection feature has been validated on non-cardiac chest CT data with iterative reconstruction from Siemens Healthineers.

Only DICOM images of adult patients are considered to be valid input.

AI-Rad Companion (Cardiovascular) SW version VA20 is an enhancement to the previously cleared device AI-Rad Companion (Cardiovascular) K183268 that utilizes machine and deep learning algorithms to provide quantitative and qualitative analysis to computed tomography DICOM images to support qualified clinicians in the evaluation and assessment of cardiovascular diseases.

As an update to the previously cleared device, the following modifications have been made:

Segmentation of Aorta – Performance Improvement
Although the structure of the underlying neural network has not changed in the subject device of this submission, the performance was enhanced over the previously cleared device by adding training data (re-use of existing annotations + 267 additional annotations).

Aorta diameter measurements - Maximum Diameter Ascending, Descending Aorta
In the previously cleared device diameter measurements of the aorta were performed at nine predefined locations according to the AHA guidelines.

As an enhancement to the previously cleared device and subject of this submission are aorta diameter measurements at the locations of the maximum diameter of the ascending and the descending aorta.

Visualization of aorta's VRT and as cross-sectional MPRs - Maximum Diameter Ascending, Descending Aorta
In the previously cleared device visualization VRT and cross-sectional MPRs were provided at nine predefined locations according to the AHA guidelines.

As an enhancement to the previously cleared device, such visualization of the maximum diameter of the ascending and descending aorta were added to the subject of this submission.

Categorization of diameter measurements - Maximum Diameter Ascending, Descending Aorta
In the previously cleared device categorization of diameter measurements was performed at locations according to the AHA guidelines.

With the subject of this submission, the categorization of diameter measurements was extended to locations of the maximum diameter of the ascending and descending aorta.

Individual Confirmation of Aorta Findings
For the measurements of the aorta, only all the measurements could be accepted or declined in the predicate device.

Within the scope of this submission the concept of individual accept, decline-possibility was introduced to all aorta measurements.

Structured DICOM Report (DICOM TID 1500)
In the predicate device, the system would produce results in form of quantitative, structured and textual reports and would generate DICOM Secondary Capture images which would be forwarded to PACS reading and reporting systems.

Within the scope of this submission, the system supports an alternative, digital output format for the same results. For this purpose, a DICOM Structured Report is generated which is both human and machine readable and, therefore, will support, e.g., a transfer of the results into the clinical report more efficiently. The DICOM Structured Report is compliant to the TID1500 format for applicable content.

Cloud and Edge Deployment
Another enhancement provided within this submission is the existing cloud deployment in an on-premise deployment known as an edge deployment. The system remains hosted in the teamplay digital health platform and remains driven by the AI-Rad Companion Engine; however, with the edge deployment the processing of clinical data and the generation of results is performed within the customer environment. This system remains fully connected to the cloud for monitoring and maintenance of the system from a remote setup. At the time of this submission this feature has been cleared in submission K213706 (AI-Rad Companion Brain MR VA40) and is unchanged within this subject device.

Here's a breakdown of the acceptance criteria and study details for the AI-Rad Companion (Cardiovascular) from the provided text:

1. Table of Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance for Test Set

• Aorta Segmentation:
  • Sample Size: N=315
  • Data Provenance: Retrospective clinical cohort. Details regarding country of origin are not specified.
• Aorta Diameter Measurements:
  • Sample Size: N=193
  • Data Provenance: Representative retrospective clinical cohort. This included:
    • Consecutive patients undergoing Chest CT exams for varying indications.
    • A cohort at increased risk for incidental findings, particularly in the cardiovascular domain, due to the screening nature of the examination.
  • Specific percentages: 50% of cases with dilated aorta, 9% of cases with aortic aneurysm.
  • Details regarding country of origin are not specified.

3. Number and Qualifications of Experts for Test Set Ground Truth

The document does not explicitly state the number or qualifications of experts used to establish the ground truth for the test set. It mentions "inter-reader variability was assessed" for the diameter measurements, implying human expert involvement in establishing reference values, but provides no further details on their credentials or number.

4. Adjudication Method for the Test Set

The adjudication method is not explicitly stated in the provided text.

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

No Multi-Reader Multi-Case (MRMC) comparative effectiveness study (AI vs. human readers with AI assistance vs. without AI assistance) is mentioned. The study focuses on comparing the subject device's performance to the predicate device's performance, and algorithm accuracy against ground truth.

6. Standalone (Algorithm Only) Performance Study

Yes, standalone performance studies were done. The reported performance metrics (DICE coefficient, bias, MAE) are directly attributed to the device's algorithms in comparison to established (likely expert-defined) ground truth, without human interaction during the measurement process. The text explicitly states, "the performance of the aorta segmentation module has been validated... For the subject device, average DICE (± std. dev) coefficient was 0.924 (± 0.046)." Similarly for the diameter measurements, "91.9% of the measurements provided by the subject device were found to lie within the LoA," indicating standalone algorithmic measurement.

7. Type of Ground Truth Used for Test Set

The type of ground truth used is implied to be expert consensus or expert measurements, especially for the aorta diameter measurements where "inter-reader variability was assessed" and the device's measurements were compared against these established ranges. For segmentation, the DICE coefficient comparison against the predicate suggests a reference standard, likely also based on expert annotations or consensus.

8. Sample Size for the Training Set

The document notes that the performance of the aorta segmentation was "enhanced over the previously cleared device by adding training data (re-use of existing annotations + 267 additional annotations)." This indicates that the training set for the aorta segmentation was augmented with at least 267 new cases, in addition to previously used annotations from the predicate device's training. The total size of the training set is not explicitly given, only the additional annotations for the updated model.

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

The text states "re-use of existing annotations + 267 additional annotations" for the training data. While it doesn't explicitly detail how these annotations were created, "annotations" typically refer to expert-labeled segmentation masks or measurements. This implies that medical professionals (e.g., radiologists) meticulously outlined structures or took measurements on the training images to serve as the ground truth for training the deep learning model.

Ask a specific question about this device