(29 days)
MI View&GO is a medical diagnostic application for viewing, manipulation, quantification, analysis and comparison of medical images with one or more time-points. MI View&GO supports functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR).
MI View&GO is intended to be utilized by appropriately trained health care professionals to aid in the management of diseases associated with oncology, cardiology, neurology, and organ function. The images and results produced by MI View&GO can also be used by the physician to aid in radiotherapy treatment planning.
MI View&GO is a software-only medical device which will be delivered with the new generation of Siemens SPECT/CT and PET/CT scanners.
MI View&GO is a medical diagnostic application for viewing, manipulation, quantification, analysis and comparison of medical images with one or more time-points. MI View&GO supports functional data, such as positron emission tomography (PET) or nuclear medicine (NM), as well as anatomical datasets, such as computed tomography (CT) or magnetic resonance (MR)
MI View&GO is intended to be utilized by appropriately trained health care professionals to aid in the management of diseases associated with oncology, cardiology, neurology, and organ function.
Here's an analysis of the provided text regarding the acceptance criteria and study information for the MI View&GO VA10A device:
Important Note: The provided document is a 510(k) summary for the MI View&GO VA10A device. It primarily focuses on demonstrating substantial equivalence to a predicate device rather than presenting a detailed de novo clinical study with specific acceptance criteria for novel performance claims. As such, many of the typical clinical study elements like "effect size," "sample size for test set," "number of experts," etc., are not explicitly described in the same way they would be for a new device with novel performance claims requiring rigorous clinical validation. The testing described is primarily for verification and validation of the software’s functions, performance requirements, and hazard mitigations against predetermined acceptance values, in line with established industry standards for medical device software.
1. Table of Acceptance Criteria and Reported Device Performance
Given the nature of the submission (510(k) for a software update with substantial equivalence), the acceptance criteria are not in the form of clinical performance metrics like sensitivity/specificity for a diagnostic task. Instead, they relate to software engineering and regulatory compliance.
| Acceptance Criterion Type | Reported Device Performance | Comments |
|---|---|---|
| Software Functionality | Functions work as designed | "Verification and Validation activities have been successfully performed on the software package, including assurance that functions work as designed." |
| Performance Requirements | Performance requirements and specifications have been met | "performance requirements and specifications have been met" |
| Hazard Mitigation | All hazard mitigations have been fully implemented | "all hazard mitigations have been fully implemented." |
| Testing Outcomes | All testing has met the predetermined acceptance values | "All testing has met the predetermined acceptance values." |
| Risk Management | Risk analyses in compliance with ISO 14971 | "Risk Management has been ensured via risk analyses in compliance with ISO 14971" |
| Quality System Compliance | Designed and manufactured in accordance with Quality System Regulations (21 CFR 820) | "The device is designed and manufactured in accordance with Quality System Regulations as outlined in 21 CFR 820." |
| Cybersecurity | Specific cybersecurity controls implemented to prevent unauthorized access, modifications, misuse, or denial of use; controls for information storage and transfer | "The software has specific cybersecurity controls to prevent unauthorized access, modifications, misuse or denial of use. Additionally, controls are enabled to prevent the unauthorized use of information that is stored, accessed or transferred between the software and external devices." |
| Traceability | Traceability of requirements ensured during component integration, software validation, and system testing | "Traceability of the requirements specified in the requirement specifications and functional specifications is ensured during component integration, software validation and system testing." |
| Compliance with Standards | Adherence to recognized and established industry standards (EN ISO 13485, IEC 62304, ISO 14971, IEC 62366-1, ISO 15223-1, NEMA PS 3.1 – 3.20) | "Siemens Medical Solutions, USA Inc. adheres to recognized and established industry standards for development including EN ISO 13485 and IEC 62304." (Specific standards listed later) |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not explicitly stated as a separate "test set" in the context of image data for diagnostic performance evaluation. The "test set" here refers to the software testing environment. The document states "Verification and Validation activities have been successfully performed on the software package." This implies internal testing with various inputs.
- Data Provenance (e.g., country of origin of the data, retrospective or prospective): Not specified. Since this is primarily a software update and substantial equivalence claim, the focus is on functional verification rather than a de novo clinical study with specific patient data sets to prove diagnostic accuracy.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Not specified. For this type of submission, "ground truth" refers more to established software requirements and specifications rather than a diagnostic standard established by human experts on a clinical dataset.
- Qualifications of Experts: Not specified.
4. Adjudication Method for the Test Set
- Adjudication Method: Not applicable or described. Adjudication is typically used in clinical studies when multiple human readers evaluate data, and their disagreements need to be resolved to establish a ground truth. Here, "ground truth" pertains to software functionality meeting its design specifications.
5. 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
- MRMC Study: No, an MRMC comparative effectiveness study was not performed or described. The MI View&GO VA10A is described as an image processing software for viewing, manipulation, quantification, analysis, and comparison, not specifically an AI-driven diagnostic aid that would improve human reader performance in terms of diagnostic accuracy. Its features are largely related to workflow, display, and basic image processing.
6. If a Standalone (i.e. algorithm only without human-in-the-loop performance) was done
- Standalone Performance: Not applicable in the sense of a diagnostic algorithm's standalone performance (e.g., sensitivity/specificity for a disease). MI View&GO is a "medical diagnostic application" intended to be "utilized by appropriately trained health care professionals to aid in the management of diseases." It's a tool for professionals, not an autonomous diagnostic algorithm. Its performance is linked to the functionality described (viewing, manipulation, etc.), which were verified to meet specifications, not generate diagnostic outputs independently.
7. The Type of Ground Truth Used
- Type of Ground Truth: The "ground truth" for this submission are the predetermined acceptance values and functional specifications as defined by the software's design and requirements. It also includes compliance with recognized industry standards (ISO 14971, IEC 62304, etc.) and regulatory requirements (21 CFR 820, cybersecurity guidance). This is a software engineering "ground truth" rather than a clinical diagnostic ground truth like pathology or outcome data.
8. The Sample Size for the Training Set
- Sample Size for Training Set: Not applicable. MI View&GO VA10A is not described as an AI/Machine Learning device that undergoes a "training phase" on a dataset. It is image processing software.
9. How the Ground Truth for the Training Set was Established
- Ground Truth for Training Set: Not applicable. As it's not an AI/ML device requiring a training set, the establishment of ground truth for such a set is not relevant.
Summary of the Study:
The "study" or rather, the evidence presented in this 510(k) submission, is a demonstration of Verification and Validation (V&V) activities. This included ensuring that:
- The software's functions worked as designed.
- Performance requirements and specifications were met.
- All hazard mitigations were fully implemented according to risk analyses (ISO 14971).
- All testing met predetermined acceptance values.
- The device adheres to recognized industry standards (e.g., IEC 62304, ISO 13485) and Quality System Regulations (21 CFR 820).
- Cybersecurity controls are in place.
The overall approach is a comparison to predicate devices (syngo.via MI Workflows, syngo.CT View&GO, syngo.CT Extended Functionality) to demonstrate substantial equivalence in terms of intended use, indications for use, and technological characteristics, especially for the new or modified features. The study proves that the device meets its acceptance criteria by stating that "All testing has met the predetermined acceptance values" and that V&V activities confirmed functional and performance requirements were met as per software development and regulatory standards.
§ 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).