(60 days)
The Mobile MIM software program is used for the viewing, registration, fusion, and/or display for diagnosis of medical images from the following modalities: SPECT, PET, CT, MRI, X-ray and Ultrasound.
Mobile MIM can be used to review images, contours, DVH, and isodose curves from radiation treatment plans. Mobile MIM can be used to approve these plans.
Mobile MIM provides wireless and portable access to medical images. This device is not intended to replace full workstations and should be used only when there is no access to a workstation.
This device is not to be used for mammography.
Mobile MIM (RT) extends the Mobile MIM software application previous cleared under K103785. In addition to SPECT. PET. CT. MRI modalities. Mobile MIM can be used for the viewing and/or display for diagnosis of X-ray and Ultrasound medical images.
It also provides functionality for the review of medical images, contours. DVH, and isodose curves from radiation treatment plans. In addition. Mobile MIM (RT) will allow permitted users the ability to approve reviewed radiation treatment plans.
The provided text describes the 510(k) summary for the Mobile MIM (RT) software, which is an extension of the existing Mobile MIM software. The document details the device's intended use, substantial equivalence to predicate devices, and performance data.
Here's an analysis of the provided information regarding acceptance criteria and the studies conducted:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not explicitly state quantitative (numerical) acceptance criteria. Instead, it describes general qualitative goals for the performance studies. The reported device performance is also qualitative, affirming that the software met these general expectations.
| Acceptance Criteria (Inferred from Study Descriptions) | Reported Device Performance |
|---|---|
| Image quality for diagnostic viewing of X-ray and Ultrasound modalities under different environmental conditions must be acceptable. | "Results of these studies affirm the diagnostic image viewing capabilities of Mobile MIM when used as indicated." |
| Display quality of isodose curves, DVH graphs, and contours for radiation therapy plan review must be acceptable. | "The results indicated the display quality for of isodose curves, DVH graphs, and contours was of acceptable quality for review and approval of radiation therapy plans, and were equivalent to those viewed on a full workstation." |
| Software must pass performance requirements and meet specifications through verification, validation, and functional testing. | "In all cases, the software passed its performance requirements and met specifications." Note: This refers to internal software quality assurance processes rather than clinical performance studies described above. |
2. Sample Size Used for the Test Set and Data Provenance
-
X-ray and Ultrasound Diagnostic Viewing Study:
- Sample Size: Not specified. The document states "multiple studies" were performed by "qualified radiologists" evaluating "the two additional modalities of X-ray and Ultrasound."
- Data Provenance: Not specified. It does not mention the country of origin or if the data was retrospective or prospective.
-
Radiation Therapy Plan Review Study:
- Sample Size: Not specified. It mentions evaluating "multiple areas of treatments" and using "plan data from 3 major vendors."
- Data Provenance: Not specified. It does not mention the country of origin or if the data was retrospective or prospective.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of those Experts
-
X-ray and Ultrasound Diagnostic Viewing Study:
- Number of Experts: Not specified, but referred to as "qualified radiologists."
- Qualifications of Experts: "qualified radiologists." No further details on experience (e.g., "10 years of experience") are provided.
-
Radiation Therapy Plan Review Study:
- Number of Experts: Not specified, but referred to as "trained medical professionals."
- Qualifications of Experts: "dosimetrists and radiation oncologists." No further details on experience are provided.
4. Adjudication Method for the Test Set
The document does not describe any specific adjudication method (e.g., 2+1, 3+1, none) for either study. The studies appear to be based on expert evaluations, but the mechanism for resolving disagreements or establishing a consensus ground truth is not detailed.
5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done, and the Effect Size
No MRMC comparative effectiveness study is explicitly mentioned. The studies described are focused on assessing the standalone performance or equivalence of the Mobile MIM (RT) display capabilities to a full workstation, rather than measuring human reader improvement with AI assistance. Therefore, no effect size for human reader improvement with AI vs. without AI assistance is provided.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done
The performance studies described in the document are primarily focused on the human-in-the-loop performance, where radiologists, dosimetrists, and radiation oncologists are using the Mobile MIM (RT) software to evaluate images and plans. The studies assess the software's ability to display information adequately for human interpretation and decision-making. No "algorithm only" standalone performance is discussed, as the device is a viewing and review software, not an AI diagnostic algorithm in the modern sense.
7. The Type of Ground Truth Used
- X-ray and Ultrasound Diagnostic Viewing Study: The ground truth for evaluating "diagnostic image viewing capabilities" would likely be the consensus opinion of the qualified radiologists regarding the diagnostic quality of the images displayed on the Mobile MIM (RT), presumably compared to "gold standard" interpretations or full workstation views. This is an inferred-expert consensus.
- Radiation Therapy Plan Review Study: The ground truth for evaluating "display quality for of isodose curves, DVH graphs, and contours" and "review and approval of radiation therapy plans" would be the consensus opinion of the trained medical professionals (dosimetrists and radiation oncologists), compared to views on a "full workstation." This is an inferred-expert consensus and comparison to a recognized standard (full workstation).
8. The Sample Size for the Training Set
The document does not describe the development or training of an AI algorithm or machine learning model. Mobile MIM (RT) is presented as an image viewing and review software application. Therefore, there is no mention of a "training set" in the context of an AI model. The "performance data" section focuses on testing the usability and display quality of the software for its stated functions.
9. How the Ground Truth for the Training Set Was Established
As there is no mention of a training set for an AI algorithm, this information is not applicable. The device is software for viewing and interacting with medical images and plans, not an AI system that learns from a training set.
§ 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).