(81 days)
The HS40 diagnostic ultrasound system and probes are designed to obtain ultrasound images and analyze body fluids.
The clinical applications include: Fetal/Obstetrics, Abdominal, Gynecology, Pediatric, Small Organ, Neonatal Cephalic, Adult Cephalic, Trans-rectal, Muscular-Skeletal (Conventional, Superficial), Urology, Cardiac Adult, Cardiac Pediatric and Peripheral vessel.
It is intended for use by, or by the order of, and under the supervision of, an appropriately trained healthcare professional who is qualified for direct use of medical devices. It can be used in hospitals, private practices, clinics and similar care environment for clinical diagnosis of patients.
Modes of Operation: 2D mode, Color Doppler mode, Power Doppler (PD) mode, M mode, Pulsed Wave (PW) Doppler mode, Continuous Wave (CW) Doppler mode, Tissue Doppler Imaging (TDI) mode, Tissue Doppler Wave (TDW) mode, ElastoScan Mode, Combined modes, Multi-Image mode(Dual, Quad), 3D/4D mode.
The HS40 is a general purpose, mobile, software controlled, diagnostic ultrasound system. Its function is to acquire ultrasound data and to display the data as 2D mode, M mode, Color Doppler imaging, Power Doppler imaging (including Directional Power Doppler mode; S-Flow), PW Spectral Doppler mode, CW Spectral Doppler mode, Harmonic imaging(S-Harmonic), Tissue Doppler imaging, Tissue Doppler Wave, Panoramic Imaging, Freehand 3D, 3D imaging mode (real-time 4D imaging mode), Elastoscan Mode or as a combination of these modes. The HS40 also gives the operator the ability to measure anatomical structures and offers analysis packages that provide information that is used to make a diagnosis by competent health care professionals. The HS40 has real time acoustic output display with two basic indices, a mechanical index and a thermal index, which are both automatically displayed.
The provided text describes two AI-based features of the HS40 Diagnostic Ultrasound System: NerveTrack and UterineAssist. Here's a breakdown of their acceptance criteria and supporting studies:
1. Acceptance Criteria and Device Performance
NerveTrack
| Validation Type | Definition | Acceptance Criteria | Reported Device Performance (Average) | 95% CI |
|---|---|---|---|---|
| Accuracy (%) | Number of correctly detected frames / Total number of frames with nerve x 100 | ≥ 80% | 91.7% | 89.5% to 93.9% |
| Speed (FPS) | 1000 / Average latency time of each frame (msec) | ≥ 2 FPS | 7.93 FPS | 7.04 to 8.82 |
UterineAssist
| Validation Type | Acceptance Criteria / Description | Reported Device Performance (Average / Max Error) |
|---|---|---|
| Image Segmentation (Uterus Dice-score) | N/A (implicit high score) | 96% |
| Image Segmentation (Endometrium Dice-score) | N/A (implicit high score) | 92% |
| Feature Points Extraction (Uterus Error) | N/A (implicit low error) | 5.8 mm or less |
| Feature Points Extraction (Endometrium Error) | N/A (implicit low error) | 4.3 mm or less |
| Size Measurement (Measurement Error) | N/A (implicit low error) | 2.0 mm or less |
2. Sample Sizes and Data Provenance
NerveTrack
- Test Set Sample Size:
- Number of Subjects: 18 (13 females, 5 males)
- Number of Images: 2,146 (1,168 from females, 978 from males)
- Data Provenance: All data were collected from Koreans. The study does not specify if the data was retrospective or prospective, but mentions "When collecting scan data, the speed of the probe varies..." which suggests prospective collection or at least data collected under specific scanning conditions.
UterineAssist
- Test Set Sample Size:
- Segmentation Test: 450 sagittal uterus images and 150 transverse uterus images (total 600 images).
- Feature Points Extraction & Size Measurement Tests: 45 sagittal and 41 transverse plane images of uterus (total 86 images).
- Data Provenance: Data collected at three hospitals. The ethnicity/country is All Koreans. It involved a mix of retrospective and prospective data collection in clinical practice.
3. Number and Qualifications of Experts for Test Set Ground Truth
NerveTrack
- Number of Experts: 10 anesthesiologists and 5 sonographers (total 15 experts).
- Qualifications: All experts had more than 10 years of experience.
UterineAssist
- Number of Experts: 3 OB/GYN experts.
- Qualifications: All experts had more than 10 years' experience.
4. Adjudication Method for the Test Set
NerveTrack
- Adjudication Method: "One anesthesiologist who scanned the ultrasound directly drew the GT of nerve location, and two or more other anesthesiologists and sonographers reviewed and confirmed that it was correct. If there was any mistake during the review, it was revised again." This indicates an initial drawing by one expert with confirmation/review by at least two (or more) others, followed by revision if errors were found. This is a form of expert consensus with review and revision.
UterineAssist
- Adjudication Method: "The set of images (uterus and endometrium) were divided into 3 subsets and the three participating OB/GYN experts each drew the ground truths for one of the subsets. The ground truths drawn by an expert were cross-checked by the other two experts. Any images that do not meet the inclusion/exclusion criteria were excluded from the set of images." This is a cross-checking method where each expert's ground truth was reviewed by the other two, with exclusion of non-conforming images.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The provided text does not mention a Multi-Reader Multi-Case (MRMC) comparative effectiveness study to assess the improvement of human readers with AI assistance versus without. The studies described focus on the standalone performance of the AI algorithms.
6. Standalone Performance (Algorithm Only without Human-in-the-Loop)
- Yes, standalone performance was done for both algorithms.
- NerveTrack: The acceptance criteria and reported performance (Accuracy, Speed) directly measure the algorithm's ability to detect nerves and its processing speed, without human intervention in the detection process.
- UterineAssist: The segmentation accuracy (Dice-score) and error in feature point extraction and size measurement refer to the algorithm's direct output.
7. Type of Ground Truth Used
NerveTrack
- Type of Ground Truth: Expert Consensus. The ground truth for the location of 8 different kinds of nerves was established by a group of anesthesiologists and sonographers through a process of drawing, review, and confirmation.
UterineAssist
- Type of Ground Truth: Expert Consensus (Segmentation by experts). "Segmentation of the ground truth was generated by three participating OB/GYN experts with more than 10 years' experience."
8. Sample Size for the Training Set
NerveTrack
- The document states, "The training data used for the training of the NerveTrack algorithm are independent of the data used to test the NerveTrack algorithm," but it does not specify the sample size for the training set.
UterineAssist
- The document states, "Data used for test/training validation purpose are completely separated from the ones during training process and there is no overlap between the two," but it does not specify the sample size for the training set.
9. How the Ground Truth for the Training Set was Established
NerveTrack
- The document mentions that training data is independent of test data but does not describe how the ground truth for the training set was established.
UterineAssist
- The document implies that the ground truth for the training set would have been established similarly to the test set (i.e., by experts), as it only specifies the independence of the datasets. However, it does not explicitly describe the ground truth establishment method for the training set.
§ 892.1550 Ultrasonic pulsed doppler imaging system.
(a)
Identification. An ultrasonic pulsed doppler imaging system is a device that combines the features of continuous wave doppler-effect technology with pulsed-echo effect technology and is intended to determine stationary body tissue characteristics, such as depth or location of tissue interfaces or dynamic tissue characteristics such as velocity of blood or tissue motion. This generic type of device may include signal analysis and display equipment, patient and equipment supports, component parts, and accessories.(b)
Classification. Class II.