(56 days)
miPlatform is an internet-based image management system intended to be used by trained professionals, including but not limited to physicians, nurses and medical technicians.
The system is a software package that is used with general purpose computing hardware to acquire, store, distribute, process and display images and associated data. The software performs digital image processing, analysis, reviewing, communication and storage.
miPlatform supports receiving, sending, printing, storing and displaying studies received from the following modality types via DICOM: CT, MR, NM, US, XA, PET, DX, DR, RF, RT, MG, SC, VL, as well as hospital/radiology information systems and any other information systems that support DICOM 3.0 standard.
miPlatform also supports multidimensional image visualization, measurement and analysis tools, and reporting algorithms. The user interface is designed to follow typical clinical workflow patterns to process, review, validate/edit and analyze digital images. The software supports the following image analysis options:
Vessel Analysis is an option intended for viewing or displaying vascular obstructive disease by providing a non-invasive survey of a patient's coronary or peripheral arteries. Physicians can select any artery to view the following anatomical references: the highlighted vessel in 3D, two rotate-able curved MPR vessel views displayed at angles orthogonal to each other, and cross sections of the vessel. Physicians can manually measure the lumen width to obtain percentage stenosis calculations. In addition, clinicians can manually measure vessel length along the centerline in standard curved MPR views and examine Houndsfield unit or signal intensity statistics.
Coronary Calcium Scoring is an option intended for cardiac scoring from CT image derived measurements, including non-invasive detection and quantification of atherosclerotic plaque. Physicians can use semi-automatic tools in Coronary Calcium Scoring to mark calcified lesions of coronary arteries, and automated computation of Agatston scoring will be performed and presented in a report.
miPlatform supports a real-time image-based conference option with integrated audio/video capability. Multiple users may log into the system and participate in the conference from different locations via internet connection.
Lossy compressed mammographic images and digitized film screen images must not be reviewed for primary image interpretations. Mammographic images may only be interpreted using an FDA cleared monitor that meets technical specifications reviewed and accepted by FDA.
miPlatform is an internet-based image management system intended to be used by trained professionals, including but not limited to physicians, nurses and medical technicians.
The system is a software package that is used with general purpose computing hardware to acquire, store, distribute, process and display images and associated data. The software performs digital image processing, analysis, reviewing, communication and storage.
miPlatform supports receiving, sending, printing, storing and displaying studies received from the following modality types via DICOM: CT, MR, NM, US, XA, PET, DX, DR, RF, RT, MG, SC, VL, as well as hospital/radiology information systems and any other information systems that support DICOM 3.0 standard.
miPlatform also supports multidimensional image visualization, measurement and analysis tools, and reporting algorithms. The user interface is designed to follow typical clinical workflow patterns to process, review, validate/edit and analyze digital images. The software supports the following image analysis options: Vessel Analysis and Coronary Calcium Scoring.
miPlatform supports a real-time image-based conference option with integrated audio/video capability.
The provided 510(k) summary for the "miPlatform medical imaging suite" (K131424) primarily focuses on demonstrating substantial equivalence to predicate devices through software validation and performance comparison rather than presenting specific acceptance criteria and a detailed study explicitly proving those criteria were met for standalone performance.
Here's an analysis based on the provided text:
1. Acceptance Criteria and Reported Device Performance:
The document does not explicitly state quantitative acceptance criteria for features like "Vessel Analysis" or "Coronary Calcium Scoring." Instead, it relies on general statements about successful passing of tests and compliance with software requirements.
| Acceptance Criteria (Explicitly Stated) | Reported Device Performance |
|---|---|
| All features of the miPlatform device were compliant with the software requirements. | "Support of the substantial equivalence of the miPlatform device was provided as a result of software validation, which confirms all features of the miPlatform device were compliant with the software requirements." (Page 3) |
| Pass/Fail criteria were based on the requirements and intended use of the product. | "Test results showed that all tests successfully passed." (Page 3) |
| Predetermined acceptance criteria were met. | "Designated individuals performed all verification and validation activities and results demonstrated that the predetermined acceptance criteria were met. The system passed all testing criteria." (Page 4) |
| All tests related to technological characteristics passed successfully. | "Extensive performance tests had been conducted regarding the technological characteristics aspects. All tests had been passed successfully." (Page 4) |
2. Sample Size Used for the Test Set and Data Provenance:
The document states: "In addition, we conducted the performance comparison testing on retrospective images to help demonstrate that the proposed device is substantially equivalent to the predicate devices." (Page 3)
- Sample Size for Test Set: Not specified.
- Data Provenance: Retrospective images. The country of origin is not specified.
3. Number of Experts Used to Establish Ground Truth and Qualifications:
Not specified. The document only mentions "physicians" and "clinicians" in the context of using the device's measurement tools. There is no information about experts used to establish a ground truth for testing.
4. Adjudication Method for the Test Set:
Not specified.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
No MRMC study is mentioned. The document primarily focuses on the device's standalone performance and its equivalence to predicate devices, without discussing AI assistance for human readers.
6. Standalone Performance Study:
Yes, a standalone (algorithm only without human-in-the-loop performance) study was indicated, though details are scarce. The document states:
- "Support of the substantial equivalence of the miPlatform device was provided as a result of software validation, which confirms all features of the miPlatform device were compliant with the software requirements." (Page 3)
- "Testing involved system level functionality test, segmentation accuracy test, measurement accuracy test, interfacing test, usability test, serviceability test, labeling test, as well as the test for risk mitigation method analyzed and implemented in the risk management process." (Page 3)
- "Performance Data from nonclinical Testing: Designated individuals performed all verification and validation activities and results demonstrated that the predetermined acceptance criteria were met. The system passed all testing criteria." (Page 4)
These statements suggest that tests were conducted on the software itself to ensure its functions (segmentation, measurement, etc.) met requirements.
7. Type of Ground Truth Used:
The type of ground truth used for specific features like "Vessel Analysis" (lumen width, percentage stenosis calculation, vessel length, Hounsfield unit/signal intensity statistics) and "Coronary Calcium Scoring" (Agatston scoring) is not explicitly detailed. Given the mention of "segmentation accuracy test" and "measurement accuracy test," it's implied that there were reference measurements or segmentations against which the device's outputs were compared. However, it's not specified if this ground truth came from expert consensus, pathology, or another source.
8. Sample Size for the Training Set:
Not applicable. The document does not mention any machine learning or AI models requiring a training set in the context of the device's primary functions described. The focus is on a Picture Archiving and Communications System (PACS) with analytical tools rather than a predictive AI algorithm.
9. How the Ground Truth for the Training Set Was Established:
Not applicable, as no training set is mentioned.
§ 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).