(61 days)
ADAS 3D is indicated for use in clinical settings to support the visualization and analysis of MR and CT images of the heart for use on individual patients with cardiovascular disease.
ADAS 3D is indicated for patients with myocardial scar produced by ischemic heart disease. ADAS 3D processes MR and CT images. The quality and the resolution of the medical images determines the accuracy of the data produced by ADAS 3D.
ADAS 3D is indicated to be used only by qualified medical professionals (cardiologists, radiologists, radiologists, radiologists or trained technicians) for the calculation and visualization of cardiac images and intended to be used for pre-planning and during electrophysiology procedures. The data produced by ADAS 3D must not be used as an irrefutable basis or a source of medical advice for clinical diagnosis or patient treatment. The data produced by ADAS 3D is intended to be used to support qualified medical professionals for clinical decision making.
The clinical significance of using ADAS 3D to identify arrhythmia substrates for the treatment of cardiac arthythmias (e.g., ventricular tachycardia) or risk stratification has not been established.
ADAS 3D is a software tool intended to be used for post-processing cardiovascular enhanced Magnetic Resonance (MR) images and Computed Tomography (CTA) images that are formatted in the Digital Imaging and Communication in Medicine (DICOM) standard. ADAS 3D is intended for the non-invasive calculation, quantification of cardiac imaging data to support a comprehensive diagnostic decision-making process for understanding cardiovascular disease.
ADAS 3D exports information to multiple industry standard file formats suitable for documentation and information sharing purposes. The 3D data is exported into industry standard file formats supported by catheter navigation systems.
ADAS 3D analyses the enhancement of myocardial fibrosis from DICOM MR images to support:
- Visualization of the distribution of the enhancement in a three-dimensional (3D) chamber of the heart.
- Quantification of the total volume of the enhancement within the Left Ventricle (LV) and the visualization of the enhancement area in multiple layers through the cardiac structure.
- Calculation, quantification and visualization of corridors of intermediate, signal intensity enhancement in the LV.
- Quantification and visualization of the total area and distribution of the enhancement within the left Atrium (LA).
Additionally, ADAS 3D imports DICOM CTA images to support:
- Quantification of LV wall thickness.
- Identification and Visualization of other 3D anatomical structures.
- Quantification and visualization of LA wall thickness.
- Quantification and visualization of distances from the LA epicardium to other 3D anatomical structures.
Additionally, ADAS 3D imports DICOM Magnetic Resonance Angiography (MRA) images to support:
- Identification and Visualization of other 3D anatomical structures.
It is designed to be used by qualified medical professionals (cardiologists, radiologists or trained technicians) experienced in examining and evaluating cardiovascular MR and CTA images as part of the comprehensive diagnostic decision-making process.
The provided text is a 510(k) summary for the ADAS 3D device. It outlines changes from a previous version (K212421) but does not contain detailed information about the acceptance criteria or a specific study proving the device meets those criteria, especially in the context of clinical performance or accuracy metrics of the AI algorithms. The summary focuses on comparing the modified device to its predicate and describing the changes.
Therefore, much of the requested information cannot be extracted from this document regarding a study proving the device meets acceptance criteria. However, I can provide what is mentioned about the modifications and the general statement about testing.
Here's an attempt to answer based on the limited information available in the provided text:
Acceptance Criteria and Study for ADAS 3D (K230803)
The provided 510(k) summary details modifications to an existing device (ADAS 3D, K212421) and states that "The modified ADAS 3D device has been subject to design controls including design review, risk analyses, design verification / validation testing in order to ensure its safety and effectiveness. The modifications were assessed using well-established methods to validate that the software fully satisfies system requirements."
However, this document does not provide a specific table of detailed acceptance criteria with numerical performance targets or the results of a specific study demonstrating that the device explicitly meets these criteria for its AI-powered functionalities beyond a general statement of design verification and validation.
Without a dedicated section detailing specific performance metrics and a corresponding study, the table below represents what can be inferred or is missing from the provided text.
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Inferred/Missing from document) | Reported Device Performance (Inferred/Missing from document) |
|---|---|
| Accuracy of initial identification of coronaries (Change 1) | Not specified. Stated "improved with an option to provide an initial identification." |
| Accuracy of initial identification of Left Ventricle (Change 1) | Not specified. Stated "improved with an option to provide an initial identification." |
| Accuracy of initial identification of left chambers and aorta (Change 1) | Not specified. Stated "improved with an option to provide an initial identification." |
| Preservation of tissue type transition in DIF-5.0 export (Change 2) | Not specified. Stated "optimized to preserve the transition." |
| Compatibility/functionality with Navigant and Rhythmia HDx systems (Change 2) | Not specified beyond "improved to add support." |
| Accuracy of generic distance measurements (Change 3) | Not specified. Stated "A generic Measurement Module has been added to allow computing distances between points." |
| Accuracy/detail of LV wall thickness segmentation for CTA (Change 4) | Not specified. Stated "improved to obtain a more detailed segmentation... and a better visualization." |
| Robustness of 3D corridor detection for special cases (Change 5) | Not specified. Stated "improved to handle special cases." |
| Successful import of MRA DICOM images (Change 6) | Not specified. Stated "improved to add support for the MRA image modality." |
| Functionality of Exclude Image Region Tool (Change 7) | Not specified. Stated "improved by adding an Exclude Image Region Tool." |
| Overall safety and effectiveness of modified device | "The implemented design control activities demonstrate the safety and effectiveness of the modified device." (General statement, no specific metrics) |
2. Sample size used for the test set and the data provenance
The document states that the modifications were "assessed using well-established methods to validate that the software fully satisfies system requirements." However, it does not specify the sample size used for any test sets, nor does it provide information on the data provenance (e.g., country of origin, retrospective or prospective) for any specific performance evaluations.
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
This information is not provided in the 510(k) summary. The document mentions that the device is intended for use by "qualified medical professionals (cardiologists, electrophysiologists, radiologists or trained technicians)." However, it does not detail how ground truth was established for any specific test set related to the modifications.
4. Adjudication method (e.g., 2+1, 3+1, none) for the test set
This information is not provided in the 510(k) summary.
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
The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study or any effect size for human reader improvement with AI assistance. The Indications for Use explicitly state: "The data produced by ADAS 3D must not be used as an irrefutable basis or a source of medical advice for clinical diagnosis or patient treatment. The data produced by ADAS 3D is intended to be used to support qualified medical professionals for clinical decision making." This indicates the device is for decision support rather than a standalone diagnostic tool, but no human-in-the-loop performance study is detailed here.
6. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done
While the document implies some level of algorithm performance validation through "design verification / validation testing," it does not explicitly describe a standalone performance study with specific metrics for any of the modified functionalities (e.g., accuracy of coronary identification, LV segmentation, or corridor detection).
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc.)
The document does not specify the type of ground truth used for any validation testing of the modified functionalities.
8. The sample size for the training set
The document does not provide any information regarding the sample size used for training the algorithms, nor does it explicitly state that the modifications involved retraining existing AI models or developing new ones from scratch (though "improvements" to existing tools could imply model updates).
9. How the ground truth for the training set was established
As no training set information is provided, how its ground truth was established is also not mentioned in this document.
§ 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).