(132 days)
ResolutionMD™ Mobile is a software-based Picture Archiving and Communication System (PACS) used with general purpose computing servers and specific mobile devices. It provides for communication, storage, reformatting, rendering on the server component and communication and display of DICOM 3.0-compliant medical images as well as reports on the mobile device.
ResolutionMD Mobile provides wireless and portable access to medical images. The device is intended for use as a diagnostic, review, and analysis tool by trained professionals such as radiologists, physicians and technologists. This device is not intended to replace full workstations and should be used only when there is no access to a workstation.
ResolutionMD Mobile is not to be used for mammography.
The ResolutionMD™ Mobile software is a software-based Picture Archiving and Communication System (PACS) used with general purpose computing servers and highresolution Apple Inc. iOS and Google Inc. Android OS-based wireless mobile devices for the display and advanced visualization of medical image data. It provides for communication, storage, processing, rendering on the server and the display of DICOM 3.0 compliant image data on the mobile device.
Here's an analysis of the acceptance criteria and the study proving the device meets them, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
The acceptance criteria are not explicitly stated in a quantifiable manner (e.g., "accuracy must be >90%"). Instead, the primary acceptance criterion for the clinical testing appears to be agreement among radiologists that the mobile devices running ResolutionMD Mobile provide image quality and diagnostic confidence equivalent or comparable to a predicate PACS workstation for clinical use across various modalities, leading to the same diagnosis.
| Criteria Category | Acceptance Criteria (Implied) | Reported Device Performance |
|---|---|---|
| Clinical Performance | Image quality and diagnostic confidence on mobile devices with ResolutionMD Mobile must be equivalent or comparable to a predicate PACS workstation for diagnostic radiology across X-ray, ultrasound, PET, and SPECT modalities. | |
| Radiologists must be comfortable with diagnoses made on the mobile devices. | ||
| The overall clinical image display quality on mobile devices must be equivalent to the PACS workstation for identification of clinically-relevant pathology. | ||
| Radiologists must indicate acceptable quality for regular use and comfort reviewing images on the devices. | ||
| The same diagnosis should be made on mobile devices with ResolutionMD as on the predicate PACS workstation in both office and low light conditions. | All nine radiologists agreed that the iOS and Android mobile devices (smartphones and tablets) were either "equivalent" or "comparable" to the predicate PACS workstation across all four modalities (X-ray, ultrasound, PET, SPECT) and of adequate quality for clinical use. | |
| They were comfortable with the diagnoses made on the mobile devices using the ResolutionMD Mobile software. | ||
| All agreed that the overall clinical image display quality on the iOS and Android devices was equivalent to the PACS workstation for the identification of clinically-relevant pathology. | ||
| All nine radiologists indicated that the software and devices provide acceptable quality for regular use and they were comfortable reviewing images on the devices. | ||
| For all individual cases, there was agreement by all reviewers that the same diagnosis would be made on the mobile devices with ResolutionMD as on the predicate PACS workstation in office lighting conditions and in low light conditions. None noted perception differences between lighting conditions. | ||
| Technical Performance | Mobile device performance (iOS/Android, smartphones/tablets) in combination with ResolutionMD Mobile must provide acceptable image quality for diagnostic radiology, particularly concerning luminance response as per AAPM guidelines. | Specific results regarding measured luminance from mobile devices with respect to target luminance response using JND plots were provided to the FDA as requested. (The specific numerical values or pass/fail thresholds are not detailed in the summary, but the implication is they met an acceptable standard.) |
| Software Verification/Validation | The software must undergo functional, smoke, and regression tests, and beta tests with minimal critical defects. Clinical workflows must be validated for usability and consistency across client platforms (Web, iOS, Android). | Verification testing included over 160 separate tests, executed multiple times by different testers (functional, smoke, regression). Beta tests were performed. Most tests passed. Defects were either fixed or logged as unresolved anomalies with impact on safety/effectiveness annotated. |
| Validation testing was performed by trained radiology personnel based on typical clinical workflows, including usability assessment and consistency across Web, iOS, and Android platforms. |
2. Sample size used for the test set and the data provenance
- Sample Size for Test Set: The document mentions "a series of typical yet challenging X-ray, ultrasound, PET and SPECT cases." The exact number of cases is not specified, only that there were "individual cases" for which agreement was reached.
- Data Provenance: The document does not explicitly state the country of origin or whether the data was retrospective or prospective. It just refers to "typical yet challenging X-ray, ultrasound, PET and SPECT cases."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts
- Number of Experts: Nine (9) board-certified radiologists.
- Qualifications of Experts: Board-certified radiologists in the United States. No further detail on experience (e.g., "10 years of experience") is provided, but board-certification implies a certain level of expertise.
4. Adjudication method for the test set
The adjudication method appears to be a form of consensus or agreement. The study states, "All nine radiologists agreed that the iOS and Android mobile devices... were either 'equivalent' or 'comparable'..." and "For all the individual cases, there was agreement by all reviewers that the same diagnosis would be made..." This suggests a process where all radiologists had to concur, but the specific mechanics (e.g., independent review followed by discussion, or a sequential review) are not detailed. It is not explicitly a 2+1 or 3+1 method where disagreements are resolved by an additional reader.
5. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, and the effect size of how much human readers improve with AI vs without AI assistance
- MRMC Comparative Effectiveness Study: Yes, a comparative assessment was done. The study specifically compared diagnostic confidence on mobile devices with ResolutionMD Mobile to a predicate PACS workstation. This constitutes a comparison of human readers using different display/interpretation systems.
- Effect Size of Human Readers Improvement with AI vs. without AI Assistance: This device is a PACS (Picture Archiving and Communication System) viewer for mobile devices, not an AI-powered diagnostic assist tool. Therefore, the study does not evaluate improvement with AI assistance. It evaluates the equivalence of a mobile viewing platform to a full workstation. The "effect size" is expressed qualitatively as being "equivalent" or "comparable" to the predicate PACS workstation.
6. If a standalone (i.e. algorithm only without human-in-the loop performance) was done
No, a standalone (algorithm only) performance study was not done for diagnostic interpretation. ResolutionMD Mobile is a display and communication system, intended for use by trained professionals, not to autonomously interpret images. The clinical testing specifically involved human radiologists making diagnoses using the device.
7. The type of ground truth used
The ground truth was established by expert consensus among the panel of nine board-certified radiologists. They made comparative assessments and agreed on the diagnostic equivalence between the mobile device and the predicate PACS workstation for the tested cases. There is no mention of pathology or outcomes data being used as the definitive ground truth reference.
8. The sample size for the training set
The document does not provide information on a "training set" for the ResolutionMD Mobile software in the context of diagnostic interpretation. As a PACS viewer, it's not a machine learning model that is "trained" on images in the same way an AI algorithm for disease detection would be. The software is developed and verified through standard software engineering practices.
9. How the ground truth for the training set was established
Not applicable, as there is no mention of a training set for the diagnostic function of the device in the context of machine learning. The "ground truth" for the software's functionality would be adherence to DICOM standards, performance metrics (like luminance), and usability, as confirmed by verification and validation testing, rather than medical ground truth established from labeled medical images for training purposes.
§ 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).