Search Results

See-Mode AVA (Augmented Vascular Analysis) is a stand-alone, image processing software for analysis, measurement, and reporting of DICOM-compliant vascular ultrasound images obtained from carotid and lower limb arteries. The analysis includes segmentation of vessels walls and measurement of the intima-media thickness (IMT) of the carotid artery in B-Mode images, finding velocities in Doppler images, and reading annotations on the images. The software generates a vascular ultrasound report based on the image analysis results to be reviewed and approved by a qualified clinician after performing quality control. The client software is designed to run on a standard desktop or laptop computer. See-Mode AVA is intended to be used by trained medical professionals, including but not limited to physicians and medical technicians. The software is not intended to be used as an independent source of medical advice, or to determine or recommend a course of action or treatment for patients.

See-Mode AVA (Augmented Vascular Analysis) is a standalone software for analysis and reporting of vascular ultrasound images. There is no dedicated medical equipment required for operation of this software except for an ultrasound machine that is the source of image acquisition. The software runs on a standard off-the-shelf computer and is accessible within a web browser.

See-Mode AVA takes as input DICOM-compliant vascular ultrasound images. The software uses proprietary algorithms for image analysis. including segmentation of vessel walls and measurement of the intima-media thickness (IMT) of the carotid artery in B-Mode images and finding peak systolic and end diastolic velocities (PSV and EDV) from Doppler images. The software generates a vascular ultrasound report based on the image analysis results to be reviewed and approved by a qualified clinician after performing quality control. Any information within this report must be fully reviewed and approved by a qualified clinician before the vascular ultrasound report is finalized.

See-Mode AVA is not intended to be used as an independent source of analysis and reporting vascular ultrasound images. Any information provided by the software has to be reviewed by a qualified clinician (including sonographers, radiologists, and cardiologists) and can be modified to correct any possible mistakes. The software provides multiple methods for performing quality control and modification of image analysis results. When the vascular ultrasound report is finalized by a qualified clinician, See-Mode AVA exports the report. This report can be used adjunctly with other medical data by a physician to help in the assessment of the cardiovascular health of the patient.

Here's an analysis of the acceptance criteria and study details for the See-Mode AVA device, based on the provided FDA 510(k) summary:

1. Table of Acceptance Criteria and Reported Device Performance

The document doesn't explicitly list "acceptance criteria" for all tasks in a table format. However, it does present performance metrics that imply the criteria met for each function. I've extracted these and presented them in a table, along with the device's reported performance.

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

• Segmentation of B-mode Carotid Ultrasound Images & IMT Measurement:
  • Sample Size: 205 longitudinal B-mode carotid images.
  • Data Provenance: Retrospective dataset from multiple centers. The document does not specify the country of origin.
• Text Recognition (Reading Annotations):
  • Sample Size: Varied from 783 to 1432 images, depending on the type of annotation being read.
  • Data Provenance: Retrospective vascular ultrasound dataset. The document does not specify the country of origin.
• Signal Processing (Reading PSV & EDV from Doppler Waveforms):
  • Sample Size: 1117 images.
  • Data Provenance: Images where clinicians annotated PSV and EDV values at the time of image acquisition. The document does not specify the country of origin or whether it's retrospective or prospective, though the nature of "annotations at the time of image acquisition" suggests a retrospective analysis of existing data.
• Waveform Type Classifier (Lower Limb Doppler Images):
  • Sample Size: 150 images.
  • Data Provenance: A collection of images representing typical use cases in the clinical field. The document does not specify the country of origin or whether it's retrospective or prospective.

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

• Segmentation of B-mode Carotid Ultrasound Images & IMT Measurement:
  • Number of Experts: 2 expert readers.
  • Qualifications: Not explicitly stated beyond "expert readers."
• Text Recognition (Reading Annotations):
  • Number of Experts: Not explicitly stated, implied to be based on existing annotations, likely from clinicians.
  • Qualifications: Not explicitly stated.
• Signal Processing (Reading PSV & EDV from Doppler Waveforms):
  • Number of Experts: Clinicians.
  • Qualifications: "Clinicians at the time of image acquisition." No further details on their specific roles or experience are provided.
• Waveform Type Classifier (Lower Limb Doppler Images):
  • Number of Experts: Expert readers.
  • Qualifications: Not explicitly stated beyond "expert readers."

4. Adjudication Method for the Test Set

The document does not explicitly describe an adjudication method (such as 2+1, 3+1, or none) for any of the test sets.

• For IMT measurement, it compares the algorithm to the "average of two experts," implying that their individual measurements were used, but not necessarily a consensus process or adjudication beyond averaging.
• For other tasks, it refers to "expert annotations" or "clinician annotations" without detailing how disagreements, if any, were resolved.

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

No, an MRMC comparative effectiveness study that measures the improvement of human readers with AI assistance versus without AI assistance was not explicitly described.

The studies primarily evaluated the standalone performance of the AVA device against ground truth established by experts/clinicians or against the performance of a predicate device. While it claims the device "outperforms the reported results of the predicate device" for IMT, this is a comparison of standalone algorithm performance, not human-in-the-loop effectiveness.

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

Yes, standalone (algorithm only) performance evaluations were done for all the described device functions:

• Segmentation of B-mode carotid ultrasound images and IMT measurement.
• Text recognition algorithm for reading annotations.
• Signal processing algorithm for analyzing doppler waveforms (PSV and EDV).
• Waveform type classifier on lower limb doppler images.

The results presented (correlation coefficients, accuracy) are indicative of the algorithm's direct performance.

7. The Type of Ground Truth Used

The following types of ground truth were used:

• Expert Consensus/Annotations:
  • For Segmentation of B-mode Carotid Ultrasound Images & IMT Measurement, ground truth was established by "2 expert readers' measurements" (implied average).
  • For Waveform Type Classifier (Lower Limb Doppler Images), ground truth was "annotations (i.e., waveform type) by expert readers."
• Clinician Annotations:
  • For Signal Processing (Reading PSV & EDV from Doppler Waveforms), ground truth was "annotations (i.e. PSV and EDV values) on the images annotated by clinicians at the time of image acquisition."
• Existing Image Annotations:
  • For Text Recognition (Reading Annotations), the algorithm's performance was evaluated against "reading different types of annotations," implying these annotations were present as ground truth on the images.

No pathology or outcomes data was mentioned as ground truth.

8. The Sample Size for the Training Set

The document does not provide any specific information or sample size for the training set used for the AI/ML algorithms in See-Mode AVA. It only mentions that the device "incorporates a logical update to use artificial intelligence for image analysis" and benefits from "established machine learning methods."

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

Since no information about the training set's sample size or data is provided, the document does not describe how the ground truth for the training set was established.

Ask a specific question about this device

Arterys Oncology DL is a medical diagnostic application for viewing, manipulation and comparison of medical images from multiple imaging modalities and/or multiple time-points. The application supports anatomical datasets, such as CT or MR. The images can be viewed in a number of output formats including MIP and volume rendering.

Arterys Oncology DL enables visualization of information that would otherwise have to be visually compared disjointedly. Arterys Oncology DL provides analytical tools to help the user assess and document changes in morphological activity at diagnostic and therapy follow-up examinations.

Arterys Oncology DL is designed to support the oncological workflow by helping the user confirm the absence or presence of lesions, including evaluation, quantification, follow-up and documentation of any such lesions.

Note: The clinician retains the ultimate responsibility for making the pertinent diagnosis based on their standard practices and visual comparison of the separate unregistered images. Arterys Oncology DL is a complement to these standard procedures.

This traditional 510(k) is being submitted for Arterys Oncology DL which is intended for viewing, manipulation, 3D-visualization and comparison of medical images from multiple imaging modalities and/or multiple time-points. The application supports anatomical datasets, such as CT or MR. The images can be viewed in a number of output formats including MIP and volume rendering. The software supports the oncological workflow by helping the user to confirm the absence or presence of lesions, including evaluation, follow-up and documentation of any such lesions.

Key features of the software are:

• 2D and 3D visualization and comparative review
• Manual volumetric segmentation
• Semi-automatic volumetric segmentation of lung nodules and liver lesions
• Co-registration
• Longitudinal tracking
• Nodule/lesion size quantifications
• Data reporting based on Lung-RADS and LI-RADS guidelines

The provided text describes the Arterys Oncology DL device and its 510(k) submission for FDA clearance. While it outlines general performance data and verification activities, it lacks the specific details required to fully address all aspects of the acceptance criteria and the study that proves the device meets them.

Here's an analysis based on the available information:

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

The document mentions "software specifications" and "design requirements" but does not explicitly state quantitative acceptance criteria for the device's performance (e.g., specific accuracy, sensitivity, or specificity thresholds). Instead, it broadly states that "the device meets its design requirements and intended use, that it is as safe and as effective as the predicate devices, and that no new issues of safety and effectiveness were raised."

Therefore, a precise table of acceptance criteria and reported device performance cannot be generated from the given text.

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

The document mentions "Testing for Liver MR Deep Learning Model, Lung MR Deep Learning Model, Lung Longitudinal Tracking and usability." However, it does not specify the sample sizes used for these test sets.

It also does not provide information on the data provenance (e.g., country of origin, retrospective or prospective nature) for the test sets.

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

The document does not provide any information regarding the number of experts used to establish the ground truth for the test set or their qualifications.

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

The document does not provide any information about the adjudication method used for the test set.

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

The document does not explicitly state that a multi-reader multi-case (MRMC) comparative effectiveness study was done, nor does it provide any effect size for human reader improvement with AI assistance. It mentions that "the clinician retains the ultimate responsibility" and that the device "is a complement to these standard procedures," suggesting an AI-assisted workflow, but no specific study details are provided.

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

The document states, "Arterys non-clinical V&V testing included Testing for Liver MR Deep Learning Model, Lung MR Deep Learning Model, Lung Longitudinal Tracking and usability." This suggests that performance of the deep learning models themselves was evaluated, which would align with standalone algorithm performance, particularly for the "segmentation of lung nodules and liver lesions" feature. However, the document does not explicitly present or detail standalone (algorithm only) performance metrics or studies.

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

The document does not specify the type of ground truth used for any of the testing mentioned (Liver MR Deep Learning Model Testing, Lung MR Deep Learning Model Testing, Lung Longitudinal Tracking).

8. The sample size for the training set

The document does not provide the sample size for the training set.

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

The document does not provide information on how the ground truth for the training set was established.

Summary of Missing Information:

The provided text focuses on the regulatory submission process, the device's intended use, and its general adherence to safety and performance standards. It lacks the detailed technical and scientific study information typically found in a clinical study report or technical performance evaluation, specifically:

• Quantitative acceptance criteria.
• Specific sample sizes for test and training sets.
• Data provenance for test and training sets.
• Details on expert involvement (number, qualifications, adjudication) for ground truth establishment.
• Specific performance metrics for the deep learning models (standalone or assisted).
• Details of any comparative effectiveness studies with human readers.
• Methods for establishing ground truth for both training and testing.

Ask a specific question about this device