(10 days)
Orthoview™ is indicated for use when a suitably licensed and qualified healthcare professional requires access to medical images with the intention of using such images, in conjunction with templates for prosthetic devices, for the purposes of choosing the nature and characteristics of the prosthetic device to be used when planning a potential surgical procedure.
Orthoview™ is a software device that permits the orthopedic surgeon to pre-plan surgical procedures by permitting image viewing and manipulation and prosthetic template overlay within a PACS workstation or standalone environment.
The Orthoview™ device, a software for pre-operative surgical planning using digital prosthetic template overlay, was evaluated for its performance.
1. Acceptance Criteria and Reported Device Performance
The acceptance criteria for Orthoview™ were established implicitly through a comparison to traditional hand-scoring templating methods. The device was deemed acceptable if it demonstrated "similar accuracy" to these traditional methods.
| Acceptance Criteria | Reported Device Performance |
|---|---|
| Similar accuracy to traditional templating methods. | The comparison concluded that "Orthoview™ provides an accurate alternative to traditional templating methods" and offers "similar accuracy" to these methods for determining prosthetic size. |
| Provide an alternative to traditional templating. | The study confirms that Orthoview™ "provides an accurate alternative to traditional templating methods." |
2. Sample Size and Data Provenance for the Test Set
- Sample Size: Not explicitly stated. The document mentions "a retrospective technique of comparing the performance of 'templating' using a hand-scoring method versus the scoring achieved by Orthoview™," implying a test set of some size was used but the specific number of cases or images is not provided.
- Data Provenance: Retrospective. The study utilized a "retrospective technique." The country of origin for the data is not specified.
3. Number of Experts and Qualifications for Ground Truth of Test Set
- Number of Experts: Not explicitly stated, but the assessment was "carried out by experienced healthcare professionals."
- Qualifications of Experts: Described as "experienced healthcare professionals." More specific qualifications (e.g., number of years of experience, specific specialty like orthopedic surgeon) are not provided.
4. Adjudication Method for the Test Set
- Adjudication Method: Not explicitly stated. The document describes a comparison between "hand-scoring method versus the scoring achieved by Orthoview™," implying a direct comparison without detailing a specific adjudication process for discrepancies.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- A MRMC comparative effectiveness study was not explicitly reported. The document focuses on the performance of the device itself compared to traditional methods, rather than
human readers using AI vs. without AI assistance.
6. Standalone (Algorithm Only) Performance
- A standalone performance study was implicitly done. The study compared the "scoring achieved by Orthoview™" against a hand-scoring method, suggesting an evaluation of the algorithm's output independently, even if human interaction is required for its use. The device is a "software device" that permits "image viewing and manipulation and prosthetic template overlay," implying the algorithm generates the templating suggestion.
7. Type of Ground Truth Used
- Type of Ground Truth: The ground truth was established by "the actual assessment and determination of prosthetic size using traditional templating methods using X-Ray film and template overlay" (referred to as "hand-scoring"). This can be categorized as expert consensus based on traditional methods.
8. Sample Size for the Training Set
- Sample Size: Not applicable/not provided. As a templating and overlay software, and given the release date (2003), it's highly probable that Orthoview™ relied on predefined algorithms and templates rather than a machine learning model requiring a distinct training set. The descriptions focus on its functionality and comparison to traditional methods. If an internal development set was used, it is not mentioned.
9. How Ground Truth for the Training Set Was Established
- How Ground Truth Was Established: Not applicable/not provided, as no training set is mentioned or implied for an AI/ML model for this device. The software likely implements rules and calculations for scaling and overlay, with templating designs provided by prosthetic manufacturers.
§ 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).