(125 days)
LVivo platform is intended for non-invasive processing of ultrasound images to detect, measure, and calculate relevant medical parameters of structures and function of patients with suspected disease and Age >18.
The LVivo Seamless is a standalone application that extends the LVivo Platform and runs offline on a server in a healthcare environment. The system accepts echo examinations in DICOM format that are sent from an Ultrasound device and automatically selects the adequate clips for EF and GLS evaluation. After the clip selection, the LVivo Seamless activates the FDA cleared LVivo EF and LVivo Strain modules which perform automatic evaluation. The results are sent to the PACS and are evaluated by a healthcare professional.
Here's a breakdown of the acceptance criteria and study details for the LVivo Seamless v2.0 device, based on the provided document:
1. Acceptance Criteria and Reported Device Performance
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Correct identification of 4ch, 2ch, and 3ch views in 90% of the examinations. | The system was able to recognize all three 4CH, 2CH, and 3CH clips in 95% of the examinations. (Meets criterion: 95% > 90%) |
| Correlation of 80% between GLS by AFI and GLS by LVivo Seamless. | A correlation of 0.88 was reported between GLS by LVivo Strain (running offline on automatically selected clips) and GLS by AFI. (Meets criterion: 0.88 > 0.80) Additionally, a sensitivity of 0.90 and specificity of 0.83 were reported for a Normal/Abnormal GLS threshold of -18%. |
| Accuracy (Mean ± 1.96STD) for GLS measurement within acceptable ranges (implicitly compared to AFI). | Mean difference for GLS was -1.4% ± 3.93% (LVivo Strain vs. AFI). This metric, while not explicitly given an acceptance threshold, is presented as part of a successful performance evaluation demonstrating conformity to intended use. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 100 patient examinations.
- Data Provenance: The document does not explicitly state the country of origin for the data or whether it was retrospective or prospective. It mentions "measurements done routinely in the Echo lab by AFI," which suggests retrospective use of existing clinical data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
The document does not explicitly state the number of experts used to establish the ground truth or their specific qualifications (e.g., "radiologist with 10 years of experience").
It states that "The measurements by LVivo Strain running offline on the automatically selected clips were compared to the measurements done routinely in the Echo lab by AFI." This implies that the ground truth was established by the "AFI" system (Automated Functional Imaging, GE), which is a commercially available and presumably validated automated measurement tool, as part of routine clinical practice. Since these were routine measurements, they would have been interpreted and validated by qualified medical professionals (e.g., sonographers, cardiologists) in the echo lab. However, the exact process of how the AFI measurements were considered "ground truth" (i.e., whether they were subject to expert review for this study) is not detailed.
4. Adjudication Method for the Test Set
The document does not mention a specific adjudication method (e.g., 2+1, 3+1). The comparison was made between the device's measurements and measurements performed by the AFI system as part of routine lab procedures.
5. If a Multi Reader Multi Case (MRMC) Comparative Effectiveness Study Was Done
No, a Multi Reader Multi Case (MRMC) comparative effectiveness study was not done. The study described compares the algorithm's performance against an existing automated system (AFI) for GLS measurements and view identification. It does not evaluate the improvement of human readers with AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
Yes, a standalone study was done. The performance evaluation compares the LVivo Seamless v2.0 device's automated capabilities (view recognition and GLS measurement) directly against another automated system (AFI) and against predefined acceptance criteria for view identification. There is no mention of human readers interacting with the device for the purpose of this performance evaluation. The device "runs offline on a server" and "automatically selects the adequate clips for EF and GLS evaluation."
7. The Type of Ground Truth Used
The ground truth for the GLS measurements was established by comparing the LVivo Seamless results to "measurements done routinely in the Echo lab by AFI" (Automated Functional Imaging, GE). For the view identification, the ground truth is implicitly based on the actual presence of 4CH, 2CH, and 3CH views in the patient examinations, likely determined by human assessment during the initial acquisition and processing of the images in the echo lab.
8. The Sample Size for the Training Set
The document does not provide the sample size used for the training set. It focuses solely on the performance evaluation using the test 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, as the details of the training process are not included in this summary.
§ 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).