(153 days)
The KINEGRAPH VMA™ software is a quantitative imaging software application intended to be used to process digital image files. It is designed for physicians and clinical professionals who are interested in the analysis of motion in medical images, particularly in musculoskeletal images of the spine. KINEGRAPH VMA™ software permits users to review static and dynamic digital lumbar spine images acquired with the assistance of the MOTION NORMALIZER™ patient handling and data collection device, which is designed for use by imaging technicians and intended to assist with patient lumbar bending and data collection during imaging. KINEGRAPH VMA™ software also facilitates quantitative assessment of vertebral motion in digital medical images. Information about the motion of selected objects, such as bone structures, can be generated and presented in the form of a 'motion analysis' report containing graphics, charts, and text.
The subject device consists of the KINEGRAPH VMA™ software that analyzes images from the MOTION NORMALIZER™ on an Off-the-Shelf ("OTS") imaging workstation. The MOTION NORMALIZER patient handling and data collection device is an accessory device to the KINEGRAPH VMA™ software that is used to assist with subject lumbar bending and data collection while images are captured with standard fluoroscopes. The MOTION NORMALIZER is comprised of two powered, electromechanical patient handling devices connected to and controlled by a consolemounted OTS computer running custom software connected to various OTS hardware accessories. The subject system is able to capture and record fluoroscopic image data, as well as data from the patient handling devices, and to output this data into DICOM compatible digital image files for analysis using the KINEGRAPH VMA™ software.
The provided document, K112109, does not contain the specific detailed acceptance criteria or a study that rigorously proves the device meets such criteria with quantitative performance metrics for a medical imaging AI device as typically understood today. The information available is very high-level and predates the common expectations for AI/ML device submissions.
However, based on the available text, here's an attempt to structure the information as requested, highlighting what is present and what is conspicuously absent:
Acceptance Criteria and Study for KINEGRAPH VMA™ Software and MOTION NORMALIZER™
1. Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria Category | Specific Criteria (Implicit/General) | Reported Device Performance (Implicit/General) |
|---|---|---|
| Functionality | Device functions as intended. | "functioned as intended" (General Statement) |
| Validation & Verification | Compliance with FDA regulations and recognized standards for validation and verification. | Designed and developed in accordance with FDA regulations, including validation and verification testing per FDA recognized standards. |
| Repeatability | Device produces consistent results under repeated conditions. | Repeatability testing was performed. (No specific thresholds or quantitative results are provided). |
| Accuracy | Device produces results that are close to the true value (though "true value" is not defined here). | Accuracy testing was performed. (No specific thresholds or quantitative results are provided). |
| Substantial Equivalence | Same intended use, indications for use, technological characteristics, and principles of operation as predicate devices, with no new issues of safety or effectiveness. | The device has the same intended use, indications for use, technological characteristics, and principles of operation as identified predicate devices. Validation and verification data demonstrate the subject device functions as intended and performs functions substantially equivalent to the predicate devices. |
Missing Information: Crucially, the document does not provide quantitative acceptance criteria (e.g., minimum sensitivity, specificity, accuracy thresholds, or specific error margins for motion analysis), nor does it present quantitative performance results against such criteria. The statements are largely qualitative assertions.
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: Not specified. The document states "repeatability and accuracy testing was performed" but does not give any details on the number of cases or subjects used for this testing.
- Data Provenance: Not specified. There is no information provided regarding the country of origin of the data, nor whether it was retrospective or prospective.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: Not specified.
- Qualifications of Experts: Not specified.
- Role of Experts: The document does not indicate if experts were used to establish ground truth in the context of performance testing. The KINEGRAPH VMA™ software is an analytical tool for "physicians and clinical professionals," implying their use of the output rather than their role in ground truth establishment for validation.
4. Adjudication Method for the Test Set
- Adjudication Method: Not specified, and likely not applicable in the context described, as ground truth establishment by experts for specific performance metrics is not detailed.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- MRMC Study Done: No, there is no mention of a Multi-Reader Multi-Case (MRMC) comparative effectiveness study being performed. The document describes the device as a software for quantitative analysis and data collection, not a tool for human reader interpretation improvement, which would be the typical context for an MRMC study.
- Effect Size: Not applicable, as no MRMC study was performed or reported.
6. Standalone (Algorithm Only Without Human-in-the-Loop) Performance Study
- Standalone Study Done: Yes, in a general sense. The "repeatability and accuracy testing" refers to the performance of the KINEGRAPH VMA™ software and its accessory. The software's function is to "facilitate quantitative assessment of vertebral motion" and generate reports. While a human uses the output, the testing described would be of the algorithm's ability to process images and generate these quantitative assessments. However, the exact methods and quantitative results of this standalone performance are not provided.
7. Type of Ground Truth Used
- Type of Ground Truth: Not explicitly stated. For "accuracy testing," it would imply comparison against a known "true" value. Given the system's function (analysis of motion in musculoskeletal images of the spine), potential ground truth could involve:
- Phantom studies: Using precisely controlled physical models with known motion characteristics.
- Manual measurements: Highly precise manual measurements by experts on the same images, though the document doesn't specify this.
- Clinical correlation/Pathology: Unlikely to be the direct ground truth for motion analysis in this context, but perhaps for clinical utility validation.
The document only broadly states "accuracy testing was performed," but does not detail how accuracy was determined against a ground truth.
8. Sample Size for the Training Set
- Sample Size for Training Set: Not applicable / Not specified. The KINEGRAPH VMA™ software, from the description, appears to be a rule-based or algorithmic system for quantitative measurement and image processing, rather than an AI/ML system that would require a dedicated training set in the modern sense. There is no mention of machine learning or deep learning, which would necessitate a training set. The term "software" is used, implying traditional programming.
9. How the Ground Truth for the Training Set Was Established
- Ground Truth for Training Set: Not applicable, as there is no indication of a training set for an AI/ML model.
§ 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).