(46 days)
The Diagnostic Ultrasound Systems Aplio i900 Model TUS-Al900, Aplio i800 Model TUS-AI800, Aplio i700 Model TUS-AI700 and Aplio i600 Model TUS-AI600 are indicated for the visualization of structures, and dynamic processes with the human body using ultrasound and to provide image information for diagnosis in the following clinical applications: fetal, abdominal, intra-operative (abdominal), pediatric, small organs, trans-vaginal, trans-rectal, neonatal cephalic, adult cephalic, cardiac (both adult and pediatric), peripheral vascular, transesophageal, musculo-skeletal (both conventional and superficial) and laparoscopic.
The Aplio i900 Model TUS-AI900, Aplio i800 Model TUS-AI800, Aplio i700 Model TUS-AI700 and Aplio i600 Model TUS-AI600, V4.0 are mobile, compact diagnostic ultrasound systems which implement the latest technologies. These systems are Track 3 devices that employ a wide array of probes including flat linear array, convex linear array, and sector array with frequency ranges between approximately 2 MHz to 30 MHz.
The provided text describes a 510(k) premarket notification for the Aplio i900/i800/i700/i600 Diagnostic Ultrasound System, V4.0. The submission claims substantial equivalence to previously cleared devices and includes information on new and improved features, along with testing details.
Here's a breakdown of the requested information based on the provided document:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly provide a table of "acceptance criteria" with specific quantitative thresholds. Instead, it describes what each study confirmed. The general acceptance criterion implied throughout the document for new features is "substantially equivalent to the predicate function" and for improvements, "met specifications and performed as intended." For workflow improvements, the implied criterion is "faster and easier workflow" or "workflow is improved."
Here's a summary of the reported device performance for each feature, interpreted as meeting the implied acceptance criteria:
| Feature / Improvement | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Aortic Valve Analysis (AV Analysis) | Measurement values are substantially equivalent to predicate function. Provides faster and easier workflow compared to predicate. | Confirmed that AV Analysis provides measurement values of the aortic valve complex that are substantially equivalent to those by the predicate function. Confirmed that this function provides a faster and easier workflow in comparison to the predicate function. |
| BI-RADS Checklist | Provides standardized checklist options according to ACR BI-RADS. Establishes a worksheet displaying check items in specified layout. | Confirmed that this function provides a check list with options standardized according to ACR BI-RADS and that this function establishes a worksheet displaying check items in the specified layout. |
| TI-RADS Checklist | Provides standardized checklist options according to ACR TI-RADS and provides clinical assessments (risk classification). Establishes a worksheet displaying check items in specified layout. | Confirmed that this subject function provides a check list with options standardized according to ACR TI-RADS and automatically provides clinical assessments (risk classification in terms of Thyroid cancer) standardized according to ACR TI-RADS and that this function establishes a worksheet displaying check items in the specified layout. |
| 2D Wall Motion Tracking for Fetal Heart one cycle detection | Measurement values are substantially equivalent to predicate function. Operation time is reduced. Automatically provides clinically appropriate candidate one heart cycle period. Workflow is improved. | Confirmed that the measurement values by the subject function are substantially equivalent to the predicate function and that the operation time is reduced as compared to the predicate function. Confirmed that the subject function automatically provides a clinically appropriate candidate one heart cycle period and that workflow is improved by comparison of the subject function to the predicate. |
| Color Doppler imaging | Improved visibility of blood flow. | Results demonstrated that the improvements met specifications and performed as intended. |
| Volume rendering view (Mecha4D) | Previously available only in MPR view; now improved. | Results demonstrated that the improvements met specifications and performed as intended. (Comment indicates "Previously only available in MPR view -Improvement") |
| Mitral Valve Analysis (MVA) (A2/P2 length) | Addition of parameters leads to improvement. | Results demonstrated that the improvements met specifications and performed as intended. (Comment indicates "Addition of parameters -Improvement") |
| Auto E/A | Automation of previously manual measurements leads to improvement. | Results demonstrated that the improvements met specifications and performed as intended. (Comment indicates "Automation of previously manual measurements -Improvement") |
2. Sample Averages for Test Set and Data Provenance
The document does not provide specific sample sizes (number of cases or images) for the test set used in performance testing, nor does it specify the country of origin of the data. The studies are described as "bench assessment" and "clinical evaluation," implying that both synthetic/controlled data and real clinical data were used. It does not state whether the data was retrospective or prospective.
3. Number of Experts and Qualifications for Ground Truth
The document does not specify the number of experts used to establish ground truth or their specific qualifications (e.g., "radiologist with 10 years of experience"). It implicitly refers to "clinical evaluation" and "clinically appropriate candidate" for some features, suggesting medical professionals were involved in assessing the results, but details are not provided.
4. Adjudication Method for the Test Set
The document does not describe any specific adjudication method (e.g., 2+1, 3+1) used for the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
The document does not mention an MRMC comparative effectiveness study where human readers' performance with and without AI assistance was evaluated, nor does it quantify any effect size of improvement. The studies described focus on the device's performance against predicate functions or specifications, and workflow efficiency.
6. Standalone Performance (Algorithm Only without Human-in-the-Loop Performance)
The document primarily discusses the device's functions and improvements, and its performance relative to predicate functions. For several features (AV Analysis, 2D WMT, Auto E/A), it compares the device's measurements/automation to that of a "predicate function," which implies a standalone performance assessment of the new/improved algorithmic features, though not explicitly an "algorithm-only" study in isolation from the ultrasound system itself. For example, "AV Analysis provides measurement values... substantially equivalent to those by the predicate function" suggests a direct comparison of the algorithmic output.
7. Type of Ground Truth Used
The ground truth appears to be established by comparison to "predicate functions" and implicitly, "clinically appropriate" assessments by unspecified medical professionals in "clinical evaluations." For the BI-RADS and TI-RADS checklists, the ground truth is standardization according to ACR BI-RADS and ACR TI-RADS guidelines, respectively. This implies a standard of care/expert consensus as a form of ground truth.
8. Sample Size for the Training Set
The document does not specify the sample size used for the training set for any AI/machine learning components.
9. How Ground Truth for the Training Set was Established
The document does not describe how ground truth was established for the training set. Given that this is a 510(k) for an ultrasound system with improved features and some new features, it's possible that many improvements are algorithmic enhancements or automation rather than deep learning requiring extensive labeled training data in the AI sense. However, for features like "Auto E/A" and "2D Wall Motion Tracking for Fetal Heart one cycle detection," some form of training data and associated ground truth would likely be involved, but this information is not detailed in the provided text.
§ 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.