(17 days)
Mirada RT is intended to be used by trained medical professionals including, but not limited to, radiologists, nuclear medicine physicians, and physicists.
Mirada RT is a software application intended to display and visualize 2D & 3D multi-modal medical image data. The user may process, render, review, store, print and distribute DICOM 3.0 compliant datasets within the system and/or across computer networks. Supported modalities include, static and gated CT and PET, and static MR, SPECT and planar NM. The user may also create, display, print, store and distribute reports resulting from interpretation of the datasets.
Mirada RT allows the user to register combinations of anatomical and functional images and display them with fused and non-fused displays to facilitate the comparison of image data by the user. The result of the registration operation can assist the user in assessing changes in image data, either within or between examinations and aims to help the user obtain a better understanding of the combined information that would otherwise have to be visually compared disjointedly.
Mirada RT provides a number of tools such as rulers and region of interests, which are intended to be used for the assessment of regions of an image to support a clinical workflow. Examples of such workflows include, but are not limited to, the evaluation of the presence or absence of lesions, determination of treatment response and follow-up.
Mirada RT allows the user to define, import, transform and store and export regions of interest structures and dose volumes in DICOM RT format for use in radiation therapy planning systems.
Mirada RT is a software application for displaying and visualizing 2D & 3D multi-modal medical image data such as static and gated CT and PET, and static MR, SPECT and planar NM. Mirada RT runs on a workstation with color monitor(s), keyboard, mouse and optional CD-RW. Mirada RT is designed to enable rendering, reviewing, storing, printing and distribution of DICOM 3.0 compliant datasets and reports within the system and/or across computer networks.
Mirada RT enables automatic and manual registration of combinations of anatomical and functional images that can be displayed with fused and non-fused displays to facilitate the comparison of image data by the user.
Mirada RT provides a number of tools such as rulers and region of interests through SUV calculation for the assessment of regions of an image to support a clinical workflow. Mirada RT allows the user to define, import, transform and store and export regions of interest structures and dose volumes in DICOM RT format for use in radiation therapy planning systems.
The provided text describes Mirada RT as a software application for displaying and visualizing 2D & 3D multi-modal medical image data, intended for use by trained medical professionals. The document focuses on showing substantial equivalence to predicate devices rather than providing detailed acceptance criteria or a specific study to prove performance against such criteria.
Here's the information extracted and observations based on your request:
1. Table of Acceptance Criteria and Reported Device Performance
The document does not provide a table of acceptance criteria with specific quantitative targets for performance (e.g., accuracy, sensitivity, specificity) for the Mirada RT device. Instead, it states that:
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Substantial Equivalence to Predicate Devices | "The results of performance, functional and algorithmic testing demonstrate that Mirada RT meets the user needs and requirements of the device, which are demonstrated to be substantially equivalent to those of the listed predicate devices." |
| "In conclusion, performance testing demonstrates that Mirada RT is substantially equivalent to, and performs at least as safely and effectively as the listed predicate devices. Mirada RT meets requirements for safety and effectiveness and does not introduce any new potential safety risks." | |
| Compliance with User Needs and Requirements | "Mirada RT is validated and verified against its user needs and intended use by the successful execution of planned performance, functional and algorithmic testing included in this submission." |
| Compliance with Standards | "Verification and Validation for Mirada RT has been carried out in compliance with the requirements of ISO 13485:2003 and in adherence to the DICOM standard." |
Observation: The document focuses on demonstrating substantial equivalence to predicate devices rather than establishing novel quantitative performance criteria for Mirada RT. The "performance testing" mentioned is to demonstrate this equivalence, not to achieve specific predefined operating characteristics for an AI component in the typical sense of current AI/ML device submissions.
2. Sample Size Used for the Test Set and Data Provenance
The document does not explicitly state the sample size used for any test set or the data provenance (e.g., country of origin, retrospective/prospective). It generally refers to "performance, functional and algorithmic testing."
3. Number of Experts Used to Establish Ground Truth and Qualifications
The document does not specify the number of experts used to establish ground truth or their qualifications.
4. Adjudication Method for the Test Set
The document does not specify any adjudication method (e.g., 2+1, 3+1, none) for a test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
An MRMC comparative effectiveness study was not mentioned or described in the provided text. The document does not discuss human reader performance with or without AI assistance. Mirada RT is described as a software application with tools for image display, processing, and analysis, not specifically as an AI solution designed to augment human reader performance in the sense of a standalone diagnostic aid.
6. Standalone (Algorithm Only) Performance
The document does not provide details on standalone (algorithm only) performance. While it mentions "algorithmic testing," it does not present specific metrics or results for such testing in isolation from a human user. The device's intended use clearly involves trained medical professionals, suggesting a human-in-the-loop context.
7. Type of Ground Truth Used
The document does not explicitly state the type of ground truth used (e.g., expert consensus, pathology, outcomes data).
8. Sample Size for the Training Set
The document does not mention or specify any training set sample size, as it does not describe the development or evaluation of an AI/ML model in the typical sense that would require a dedicated training set. The descriptions of "algorithmic testing" are generic and do not refer to machine learning model training.
9. How Ground Truth for the Training Set Was Established
As no training set is discussed, the method for establishing ground truth for a training set is not mentioned.
Summary Observation: This 510(k) summary from 2010 predates the heightened focus on specific AI/ML performance metrics and study designs that are common in more recent submissions. The submission frames Mirada RT as a medical image processing and visualization tool that is substantially equivalent to existing predicate devices, rather than an AI-driven diagnostic or assistive device that would require extensive validation against specific ground truths using large, expertly annotated datasets for training and testing. The validation described is primarily focused on demonstrating the software functions as intended and safely, aligning with general medical device regulations and established standards like DICOM and ISO 13485.
§ 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).