(266 days)
InterView XP is a Software as Medical Device (SaMD) aimed at reviewing medical images such as planar scans (Static, Whole Body, Dynamic, Multi-Gated) and tomographic scans (SPECT, Gated SPECT) acquired by gamma cameras. Review of other image modalities is also supported. Common Users for clinical purposes are trained medical professionals, including clinicians and technicians in hospitals or imaging centers. Software components provide functions for image display, manipulation, enhancements, analysis and quantification. This device is not indicated for mammography use or dental diagnostics. The software provides diagnostic information, however, diagnostic decision cannot be based solely on the software. InterView XP has no specific target population.
InterView FUSION is a Software as Medical Device (SaMD) aimed at reviewing medical images such as planar scans and tomographic scans from SPECT, PET, CT, and MRI modalities. Review of other image modalities is also supported. The common users for clinical purposes are trained medical professionals, including clinicians in hospitals or imaging centers. Software components provide functions for image display, manipulation, enhancements, analysis, and quantification. This device is not indicated for mammography use or dental diagnostics. The software provides diagnostic information - however, diagnostic decisions cannot be based solely on this software. InterView FUSION has no specific target population.
InterView XP is a DICOM image visualization and post-processing Software as Medical Device (SaMD). It is a standalone medical device. Developed by Medical Imaging Systems, built on state-of-the-art technologies, providing evaluation method according to the international guidelines for planar, whole body and SPECT nuclear medicine applications. The product is designed as a software only product, operating on Windows based OS. The software inputs are images of nuclear medicine studies that are DICOM 3.0 compatible and uploaded into the user's computer and the Software will process the images in multiple ways to achieve the image analysis by the user's demands.
InterView FUSION is a multi-modal visualization and evaluation software. Developed by Mediso built on state-of-the-art technologies, novel image processing algorithms and tools for evaluating different medical imaging modalities. The product is designed as a standalone software, i.e. Software as Medical Device (SaMD) product, operating on Windows OS as a classical user application.
Here's a summary of the acceptance criteria and study information for the InterView XP and InterView FUSION devices, based on the provided FDA 510(k) summary:
Acceptance Criteria and Device Performance
The FDA 510(k) summary provided does not explicitly list specific numerical "acceptance criteria" for performance metrics (e.g., sensitivity, specificity, accuracy) of the InterView XP and InterView FUSION software. Instead, the submission relies on demonstrating substantial equivalence to a predicate device (Xeleris V Processing and Review Systems cleared under K201103) based on functional equivalency, technological characteristics, and conformance to relevant standards.
The "reported device performance" is essentially the demonstrated functional capabilities and features of the InterView XP and InterView FUSION, which are compared to the predicate device's functionalities. The study's conclusion is that both devices meet the acceptance criteria for substantial equivalence to the predicate device.
Given the information, a table of acceptance criteria and reported device performance would look like this:
| Acceptance Criteria (Implied by Substantial Equivalence to Predicate) | Reported Device Performance (as demonstrated by comparison) |
|---|---|
| Functional Equivalence | |
| - Medical image display, manipulation, enhancement, analysis, quantification. | The device provides functions for image display, manipulation, enhancements, analysis, and quantification. |
| - Review of planar scans (Static, Whole Body, Dynamic, Multi-Gated), tomographic scans (SPECT, Gated SPECT). | InterView XP supports these scan types. |
| - Review of planar scans and tomographic scans from SPECT, PET, CT, and MRI modalities (for FUSION). | InterView FUSION supports these scan types. |
| - Support for various clinical procedures in Nuclear Medicine (Cardiology, Endocrinology, Osteology, etc. similar to predicate). | Both InterView XP and FUSION support a comprehensive set of nuclear medicine clinical procedures, largely comparable to the predicate. Minor differences in specific processing methods were noted but not deemed to impact substantial equivalence. |
| - Not for mammography or dental diagnostics. | The device explicitly states it is not for mammography use or dental diagnostics. |
| - Diagnostic decisions not based solely on the software. | The device explicitly states diagnostic decisions cannot be based solely on the software. |
| Technological Characteristics | |
| - Standalone Software as Medical Device (SaMD) with Graphical User Interface (GUI). | The device is a standalone SaMD with a GUI. |
| - Operates on Windows OS (single-user or multi-user environment). | The device operates on Windows 10 (client) or Windows Server 2019 (server). |
| - DICOM 3.0 compatible. | The device inputs are DICOM 3.0 compatible images. |
| - Conformance to applicable software and medical device standards. | Non-clinical testing demonstrated conformance to IEC 62304, IEC 62366-1, ISO 12052, NEMA PS3, and FDA guidance on software validation. |
1. Sample sized used for the test set and the data provenance:
- Test Set Sample Size: Not specified. The submission states that functional design validations and usability validations were performed, and acceptance criteria were fulfilled, implying a test set was used for these validations. However, the exact number of cases or data points in these test sets is not provided in the summary.
- Data Provenance: Not specified. The submission does not mention the country of origin of the data or whether it was retrospective or prospective. It only states that the software inputs are "images of nuclear medicine studies that are DICOM 3.0 compatible."
2. 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. Given that no clinical testing was performed, and the assessment was primarily non-clinical software validation and comparison to a predicate, the "ground truth" as typically understood in clinical efficacy studies with expert review is likely not applicable in the same way. The ground truth for software validation would be adherence to specified requirements and expected outputs.
3. Adjudication method for the test set:
- This information is not provided in the 510(k) summary. Since clinical testing with human readers and adjudication for diagnostic performance was not conducted, a formal adjudication method as found in clinical trials would not be present.
4. 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:
- No MRMC comparative effectiveness study was done. The submission explicitly states: "No clinical testing was performed in association with this submission." Therefore, there is no information on the effect size of human reader improvement with or without AI assistance.
5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Yes, a standalone performance assessment was done implicitly. The devices (InterView XP and InterView FUSION) are described as "Software as Medical Device (SaMD)" and their functionalities (image display, manipulation, enhancement, analysis, quantification) were validated through "Non-Clinical Testing" and comparison to a predicate device. This non-clinical testing focused on verifying that the software performed its intended functions according to its specifications and relevant standards, independently of a human user's diagnostic interpretation.
6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- For the non-clinical software validation, the "ground truth" would be the software's own specifications, user needs, functional requirements, and component requirements, as traced and tested according to standards like IEC 62304. The testing aimed to verify that the software produced expected outputs and behaved as designed. Since no clinical testing was performed, there was no ground truth established based on expert consensus, pathology, or outcomes data related to diagnostic accuracy.
7. The sample size for the training set:
- Not applicable / Not provided. The summary describes the device as post-processing and visualization software. It is not presented as an AI/ML device that requires a separate training set for algorithm development in the traditional sense. The software's functionalities are based on established image processing algorithms and principles rather than a learned model from a training data set specified in the submission.
8. How the ground truth for the training set was established:
- Not applicable / Not provided. As mentioned above, a "training set" in the context of machine learning with a specific "ground truth" establishment method is not described in this 510(k) summary for these devices.
§ 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).