(72 days)
Orthopaedic specialists and/or Halifax Biomedical Inc image processing labs use the Model-based RSA Software as standalone analytical software package for the evaluation of orthopaedic implant fixation , bone segment motion. Model-based RSA software measures the in-vivo 3D position and/or relative motion of metal implants, marker beads, and/or bone segments. When interpreted by trained physicians these measurements may be useful to derive conclusions for patient treatment. NOT FOR MAMMOGRAPHY.
This is a Windows based software only product. It represents an advancement and extension of the same software cleared in K042383. Model-based RSA (Roentgen Stereophotogrammetric Analysis) is a stand-alone analytical software package for RSA digital image post-processing that runs on standard workstations running a Microsoft Windows operating system. This software is used to analyze roentgen images. It accepts digital images in the specific formats from all the major roentgen manufacturers (DICOM - CR and DX modality) as well as scanned roentgen films in bitmap (BMP) format. Generally, a pair of stereo roentgen images is taken of a patient's joint pre-operatively or postoperatively at one or more time points. Model-based RSA software is then used to measure the three dimensional (3D) relative position and/or relative motion of 3D models in the RSA images. Models may generally represent orthopaedic implants, a group of implanted markers (small tantalum beads), or bones. The 3D relative position and/or relative motion measures may provide information regarding of implants, wear of implants, and excessive or reduced motion between bones such as in spine instability and spine fusion
The Halifax Biomedical Inc. Model-based RSA Software, K133966, did not include specific acceptance criteria or quantitative performance metrics in the provided documentation. The submission focuses on demonstrating substantial equivalence to a predicate device (K042383, the RSA-CMS) through qualitative comparisons of features and a general claim of safety and effectiveness based on software validation, clinical evaluation, and risk analysis.
Here's a breakdown of the requested information based on the provided text, with details that could not be found explicitly noted:
1. Table of Acceptance Criteria and Reported Device Performance
| Characteristic / Metric | Acceptance Criteria (Not explicitly stated) | Reported Device Performance |
|---|---|---|
| Accuracy of Migration Calculations | Not explicitly stated in quantitative terms | "migration calculations by the Model-based RSA software are not biased and have high accuracy and precision." |
| Precision of Migration Calculations | Not explicitly stated in quantitative terms | "migration calculations by the Model-based RSA software are not biased and have high accuracy and precision." |
| Bias of Migration Calculations | Not explicitly stated in quantitative terms | "migration calculations by the Model-based RSA software are not biased" |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: The document mentions "Five studies in all showed that migration calculations by the Model-based RSA software are not biased and have high accuracy and precision." However, the specific sample sizes (number of phantom experiments or clinical cases) for these five studies are not provided.
- Data Provenance: The document mentions "phantom experiments" for validation and "clinical experiments" for assessing accuracy and precision. The country of origin for the data is not specified. It's stated that Halifax Biomedical Inc. is located in Nova Scotia, Canada, which might imply Canadian data, but this is not confirmed. The clinical data type is retrospective as it is an analytical software package processing existing scans.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Their Qualifications
- Number of Experts: The document does not specify the number of experts used to establish ground truth for the test set.
- Qualifications of Experts: The document mentions that the measurements "When interpreted by trained physicians these measurements may be useful to derive conclusions for patient treatment." This implies trained physicians would interpret the output, but it does not clarify their role in establishing ground truth for the validation studies, nor their specific qualifications (e.g., years of experience, subspecialty).
4. Adjudication Method for the Test Set
- The document does not specify any adjudication method (e.g., 2+1, 3+1, none) used for establishing ground truth in the test set.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- The document does not mention a multi-reader multi-case (MRMC) comparative effectiveness study. The focus is on the software's standalone measurement capabilities.
- Therefore, no effect size of human readers improving with AI vs. without AI assistance is provided.
6. Standalone (Algorithm Only) Performance Study
- Yes, a standalone performance study was done. The device is described as "standalone analytical software package" and the validation includes "comparing the calculated migrations with accurately applied translations and rotations using a micromanipulator in phantom experiments" and "clinical experiments studied the accuracy and precision of migration calculations using Model-based RSA." This indicates standalone algorithm performance was assessed.
7. Type of Ground Truth Used
- For the non-clinical (bench) testing, the ground truth was established by "accurately applied translations and rotations using a micromanipulator in phantom experiments." This can be considered a phantom-based, precisely controlled measurement.
- For the clinical testing, the document states "clinical experiments studied the accuracy and precision of migration calculations." The exact nature of the ground truth for these clinical experiments is not explicitly detailed but would typically involve highly accurate reference measurements (e.g., from high-resolution imaging, physical markers, or another established gold standard method) against which the RSA software's calculations are compared. It does not mention pathology or outcomes data as direct ground truth.
8. Sample Size for the Training Set
- The document does not provide any information regarding a "training set" or its sample size. This suggests that the software's underlying algorithms may be deterministic or based on established physical models rather than a machine learning model that requires explicit training data in the typical sense.
9. How the Ground Truth for the Training Set Was Established
- Since no training set is described, information on how its ground truth was established is not applicable/not provided.
§ 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).