(15 days)
The SonoCalc software is a Windows-based application program used on a personal computer for the automatic measurement of the intima media thickness of the carotid artery from images obtained from ultrasound systems.
SonoCalc is a software package that runs on a stand-alone computer running a Microsoft Windows™ operating system. There is no dedicated medical equipment required for operation of this software application except for an ultrasound machine that is the source of images of the carotid artery. These images are digitally transferred from the ultrasound machine to the computer containing the software application. SonoCalc then uses proprietary techniques and algorithms to measure the Intima-Media Thickness (IMT) of either or both of the near or far wall(s) of the carotid artery. SonoCalc can generate a report indicating what the patient's IMT value is. This information is used adjunctively with other medical data by a physician to help assess the cardiovascular health of a patient.
SonoCalc also is capable of storing patient measurement values on the hard disk along with the images for future reference.
1. Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Phantom Study: SonoCalc measuring the distance of targets in an ultrasound phantom from images obtained from a commercially available ultrasound system should perform equivalently to the commercial ultrasound system's caliper measurements. | The results of this test showed that the SonoCalc software performed equivalently to the commercial ultrasound system's caliper measurements of the same phantom. |
| Clinical Validation Comparison: SonoCalc software measurements of IMT values should perform equal to or better than manual measurements with respect to accuracy and reproducibility. | The results of this study showed that the SonoCalc software performed equal to or better than the manual measurements with respect to accuracy and reproducibility. |
| Standards Compliance: The SonoCalc software has been designed to comply with the following voluntary standards: ISO Joint Photographic Experts Group (JPEG) Image, Microsoft Windows Bitmap (BMP) Image Encoding. | The SonoCalc software has been designed to comply with the following voluntary standards: ISO Joint Photographic Experts Group (JPEG) Image, Microsoft Windows Bitmap (BMP) Image Encoding. (Compliance of the actual device is implied through the statement rather than explicitly tested as a performance metric.) |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size: 120 ultrasound images obtained from 20 different subjects.
- Data Provenance: The document does not explicitly state the country of origin. The study appears to be prospective in nature, as it involved scanning subjects with a commercially available ultrasound system specifically for this comparison.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: 3 trained sonographers.
- Qualifications: "trained sonographers" is the only qualification mentioned. No details on years of experience or certification are provided.
4. Adjudication Method for the Test Set
- The document describes "Manual caliper measurements of IMT values from the ultrasound system performed by 3 trained sonographers were compared to measurements of the same images performed by SonoCalc." This suggests a direct comparison method rather than a formal adjudication process (like 2+1 or 3+1). The specific method for reconciling differences between the three sonographers' measurements (if any were present) is not described.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The study described is a comparison between SonocCalc and manual measurements performed by 3 sonographers. It does not appear to be an MRMC comparative effectiveness study in the sense of evaluating how much human readers improve with AI assistance versus without. It's a direct comparison of the software's performance against human readers. The document does not provide an effect size for human reader improvement with AI assistance.
6. Standalone Performance
- Yes, a standalone study was done. The "clinical validation comparison" directly compares the SonoCalc software's measurements against manual measurements, indicating its performance as an algorithm-only without human-in-the-loop performance calculation. The phantom study also represents a standalone performance evaluation.
7. Type of Ground Truth Used
- Expert Consensus/Manual Measurement: The ground truth for the clinical validation was established through "Manual caliper measurements of IMT values from the ultrasound system performed by 3 trained sonographers." This indicates a form of expert-derived ground truth.
8. Sample Size for the Training Set
- The document does not specify the sample size for the training set. It only describes the validation study data.
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, as details about the training set itself are absent.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).