Search Results

ClearView cCAD is a software application designed to assist skilled physicians in analyzing breast ultrasound images. ClearView cCAD automatically classifies shape and orientation characteristics of user-selected regions of interest (ROIs).

The software allows the user to annotate, and automatically record and/or store selected views. The software also automatically generates reports from user inputs annotated during the image analysis process as well as the automatically generated characteristics. The output of this system will be a DICOM compatible (e.g. grayscale softcopy presentation state (GSPS)) and/or PDF report that can be sent along with the original image to standard film or paper printers or sent electronically to an intranet webserver or other DICOM compatible device.

cCAD includes options to annotate and describe the image based on the ACR BI-RADS® Breast Imaging Atlas. In addition. the report form has been designed to support compliance with the ACR BI-RADS @ Ultrasound Lexicon Classification Form.

When interpreted by a skilled physician, this device provides information that may be useful in screening and diagnosis. Patient management decision should not be made solely on the results of the cCAD analysis. The ultrasound images displayed on cCAD must not be used for primary diagnostic interpretation.

ClearView cCAD is a software application designed to assist skilled physicians in analyzing breast ultrasound images. ClearView cCAD automatically classifies shape and orientation characteristics of user-selected regions of interest (ROIs). The device uses multivariate pattern recognition methods to perform characterization and classification of images.

For breast ultrasound, these pattern recognition and classification methods are used by a radiologist to analyze such features as shape, orientation, and putative BI-RADS® category which can then be used to describe the lesion in the ACR BI-RADS® breast ultrasound lexicon as well as assigning an ACR BI-RADS® categorization which is intended to support compliance with the ACR BI-RADS® ultrasound lexicon classification form. Similarly, this process can be used to assist in training, evaluation, and tracking of physician performance.

The cCAD software can be run on any Windows 7 or higher or Windows Embedded platform that has network, Microsoft IIS, and Microsoft SQL support and is cleared for use in medical imaging. The software does not require any specialized hardware, but the time to process ROIs will vary depending on the hardware specifications. ClearView cCAD is based on core BI-RADS models and lesion characteristic extraction algorithms that can use novel statistical, texture, shape, orientation descriptors, and physician input to help with proper ACR BI-RADS® assessment.

The ClearView cCAD processing software is a platform agnostic web service that queries and accepts DICOM compliant digital medical files from an ultrasound device, another DICOM source, or PACS server. To initiate analysis and processing, images are queried from a compatible location and loaded for display within the application. The user then selects an ROI to analyze by clicking and dragging a bounding box around the region requiring analysis. Once selected, the user then clicks the processing button which initiates the analysis and processing sequence. The results are displayed to the user on the monitor and can then be selected for automated reporting, storage, or modification. The output of this system will be a DICOM compatible overlay (e.g. grayscale softcopy presentation state (GSPS)) and/or PDF report that can be sent along with the original image to standard film or paper printers or sent electronically to an intranet webserver or other DICOM compatible devices distributed by various OEM vendors. All fields may be modified by the user at any time during the analysis and prior to archiving.

Here's a breakdown of the acceptance criteria and study details for the ClearView cCAD device, based on the provided text:

ClearView cCAD Acceptance Criteria and Study Details

1. Acceptance Criteria and Reported Device Performance

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

• Test Set Sample Size:
  • 1204 cases for shape analysis.
  • 1227 lesions for orientation analysis.
• Data Provenance: Not explicitly stated (e.g., country of origin). The study involved skilled physicians evaluating a dataset, implying medical images, but whether these were retrospective or prospective, or from specific geographical regions, is not mentioned.

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

• Number of Experts: Three MQSA certified skilled physicians.
• Qualifications of Experts:
  • Each with over 20 years of experience.
  • Each read at least 3000 images per year.

4. Adjudication Method for the Test Set

• Adjudication Method: "Majority decision" was used to establish ground truth for shape and orientation. This implies that if at least two out of the three experts agreed on a characteristic, that was considered the ground truth.

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

• Was an MRMC study done? No, a true MRMC comparative effectiveness study was not explicitly stated as having been performed to measure human reader improvement with AI assistance. The study compared the device's standalone performance to expert performance, showing statistical equivalence, but not how human readers' performance might change with the device.
• Effect size of human reader improvement with AI vs. without AI assistance: Not measured or reported in this document.

6. Standalone Performance Study

• Was a standalone study done? Yes. The study focused on the ClearView cCAD system's "ability to discern BI-RADS® based shape and orientation parameters" independently and compared these results to the ground truth established by expert radiologists.

7. Type of Ground Truth Used

• Type of Ground Truth: Expert consensus (majority decision by three MQSA certified skilled physicians).

8. Sample Size for the Training Set

• Training Set Sample Size: Not explicitly stated in the provided document. The document describes the "bench testing" for the device's performance but does not specify the size of the dataset used to train the underlying multivariate pattern recognition methods and algorithms.

9. How Ground Truth for the Training Set Was Established

• Ground Truth for Training Set: Not explicitly stated. While the document mentions that the device uses "multivariate pattern recognition methods to perform characterization and classification of images" and is "based on core BI-RADS models and lesion characteristic extraction algorithms," it does not describe how the ground truth for these training datasets was established.

Ask a specific question about this device

The ClearView Image Enhancement System is intended for use by a qualified technician or diagnostician to reduce speckle noise, enhance contrast, and transfer ultrasound images. The software provides a DICOM-compliant ClearViewHD-enhanced image along with the original ultrasound image interpretation by the trained physician.

The ClearViewHD image processing software reduces noise and enhances contrast of medical ultrasound images. The software is a Windows XP or higher, Windows Embedded, and DICOM-compatible platform that may be installed on a standalone PC, laptop, or tablet The software does not require any specialized hardware but the time to process an image will vary depending on the hardware specifications. ClearViewHD is based on a core noise reduction and contrast enhancement algorithm that uses novel statistical techniques to determine whether each pixel location is due to mostly noise or signal (tissue structure) and attenuates the regions due to noise while preserving and accentuating the regions due to tissue structure. The statistical method is based on the a priori knowledge that the ultrasound signal is sparse and compressive sampling theory can be used to reconstruct the signal with fewer samples than the Nyquist Rate specifies.

The Clear ViewHD image processing software is a DICOM node that accepts DICOM3.0 digital medical files from an ultrasound device or another DICOM source. ClearViewHD processes the image and returns the original and/or enhanced image to another DICOM node such as a specific PC/workstation or the PACS system. The ClearViewHD software is designed to be compatible with any of the DICOM-compliant medical devices distributed by various OEM vendors.

Here's a breakdown of the acceptance criteria and the study information for the ClearViewHD device, based on the provided text:

Acceptance Criteria and Device Performance

Note: The document does not explicitly state numerical acceptance criteria thresholds. Instead, it implies that improvement in SNR and CNR, along with positive visual inspection, constitutes meeting the performance goals.

Study Information

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

• Test Set Sample Size: 10,000 simulated A-Scans (for SNR improvement). The number of previously collected clinical images used for CNR and visual inspection is not specified.
• Data Provenance: Bench testing on phantoms and previously collected clinical images. The country of origin is not specified, and it appears to be retrospective as it uses "previously collected clinical images."

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

• No information is provided regarding the number of experts or their qualifications for establishing ground truth for the test set. The evaluation seems to rely on objective metrics (SNR, CNR) and general "visual inspection" by unnamed individuals.

4. Adjudication Method for the Test Set:

• Not specified. The document only mentions "visual inspection" alongside objective metric measurements.

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, an MRMC comparative effectiveness study was not reported. The study focuses on the standalone performance of the algorithm in enhancing images, not on human reader performance with or without AI assistance. The indication for use states the enhanced image assists in interpretation by a trained physician, but this is not scientifically measured in the provided summary.

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

• Yes, a standalone performance evaluation was done. The bench testing on phantoms and previously collected clinical images directly assesses the algorithm's ability to reduce noise and enhance contrast, independent of human interaction.

7. The Type of Ground Truth Used:

• The ground truth for the quantitative metrics (SNR and CNR) appears to be derived from the simulated A-Scans and the original (unenhanced) clinical images, serving as a baseline for measuring improvement. For the visual inspection, the "ground truth" seems to be expert consensus on ideal image quality (less speckle, enhanced contrast).
• It's not pathology or outcomes data.

8. The Sample Size for the Training Set:

• The document does not specify the sample size used for the training set. It only mentions the "core noise reduction and contrast enhancement algorithm" is based on "novel statistical techniques" and "a priori knowledge."

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

• The document does not specify how the ground truth for the training set was established. It describes the algorithm as using "novel statistical techniques" and "a priori knowledge" of ultrasound signal sparsity and compressive sampling theory, suggesting a model-driven approach rather than human-annotated ground truth for training.

Ask a specific question about this device