(252 days)
RBknee is a radiological fully automated image processing software device of either computed (CR) or directly digital (DX) images intended to aid medical professionals in the measurement of minimum joint space width; the assessment of the presence or absence of sclerosis, joint space narrowing, and osteophytes based on OARSI criteria for these parameters; and, the presence or absence of radiographic knee OA based on Kellgren-Lawrence grading of standing, fixed-flexion radiographs of the knee.
It should not be used in-lieu of full patient evaluation or solely relied upon to make or confirm a diagnosis.
The system is to be used by trained professionals including, but not limited to, radiologists, orthopedics, physicians and medical technicians.
RBknee as a fully-automated image processing stand-alone software is a software device designed to assist clinicians in analyzing and measuring radiographic abnormalities during review of posterior-anterior (PA) and anterior-posterior (AP) radiographs.
In brief, RBknee takes digital radiographs (AP/PA) as input and as output provides:
-
- A visual report with
- a. A copy of regions of interest from the original radiographs with overlays that mark the minimum Joint Space Width (JSW)
- A table with the measurement of the minimum JSW in millimeters (mm), information on the presence or absence of joint space narrowing, osteophytes, and sclerosis based on OARSI gradings, and information on the presence or absence of radiographic knee osteoarthritis (OA) based on the Kellgren-Lawrence (KL) score.
-
- A text report with
- a. A textual summary of the presence or absence of joint space narrowing, osteophytes, and sclerosis based on OARSI gradings (called findings), and a textual summary of the presence or absence of radiographic knee osteoarthritis (OA) based on the Kellgren-Lawrence score (called impression).
RBknee is not interpreting any results but makes an objective measurement and providing an output based on a well established scale (OARSI/KL).
RBknee can be integrated to a PACS and the outputs of RBknee can be reviewed in a DICOM viewer.
RBknee operates in a Linux environment and can be compatible with any operating system supporting the third-party software Docker. The integration environment has to support RBknee data input and output requirements. The device does not interact with the patient directly, nor does it control any life-sustaining devices.
Here's a breakdown of the acceptance criteria and study details for the RBknee device, based on the provided FDA 510(k) summary:
1. Table of Acceptance Criteria and Reported Device Performance
The provided document outlines the software's performance metrics (Sensitivity, Specificity, Slope, and Intercept) which serve as the acceptance criteria for the device's clinical validation.
| Metric | Acceptance Criteria (Reported Performance) |
|---|---|
| Kellgren-Lawrence status | Sensitivity: 0.88 (95% CI: 0.85-0.91) |
| (KL-grade ≥ 2) | Specificity: 0.87 (95% CI: 0.84-0.89) |
| Joint Space Narrowing Status | Sensitivity: 0.82 (95% CI: 0.79-0.86) |
| (OARSI-grade > 0) | Specificity: 0.87 (95% CI: 0.84-0.90) |
| Osteophytosis status | Sensitivity: 0.89 (95% CI: 0.87-0.91) |
| (OARSI-grade > 0) | Specificity: 0.78 (95% CI: 0.72-0.84) |
| Subchondral Sclerosis status | Sensitivity: 0.84 (95% CI: 0.80-0.87) |
| (OARSI-grade > 0) | Specificity: 0.87 (95% CI: 0.84-0.90) |
| Medial JSW Measurement | Slope: 1.00 (95% CI: 0.98-1.02) |
| Intercept: -0.07 (95% CI: -0.17-0.03) | |
| Lateral JSW Measurement | Slope: 1.00 (95% CI: 0.97-1.03) |
| Intercept: -0.10 (95% CI: -0.27-0.06) |
2. Sample Size Used for the Test Set and Data Provenance
-
Sample Size (Test Set):
- For KL-grade and Joint Space Narrowing: 4279 images / 421 unique subjects
- For Osteophytosis: 2427 images / 289 unique subjects
- For Subchondral Sclerosis: 2329 images / 272 unique subjects
- For JSW Measurements: The specific sample size for comparison with OAI measurements is not explicitly stated as a separate count, but it's implied to be from the same OAI dataset.
-
Data Provenance: The data was obtained from the Osteoarthritis Initiative (OAI), a large U.S. prospective multicenter observational study. The data is described as "open-access."
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Number of Experts: Two physicians.
- Qualifications of Experts: The document states "two physicians," but no further specific qualifications (e.g., years of experience, subspecialty) are provided.
4. Adjudication Method for the Test Set
- Adjudication Method: "Following adjudication procedures with a third reviewer for discrepancies." This indicates a 2+1 adjudication model.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- No, a multi-reader multi-case (MRMC) comparative effectiveness study focusing on human reader improvement with AI assistance was not reported in this document. The study described is a standalone validation of the RBknee algorithm against ground truth.
6. Standalone (Algorithm Only) Performance Study
- Yes, a standalone clinical performance validation of RBknee was performed. The reported sensitivities, specificities, slopes, and intercepts are for the algorithm's performance without human intervention.
7. Type of Ground Truth Used
- The ground truth was established by expert consensus (two physicians with adjudication by a third for discrepancies) based on:
- Kellgren Lawrence grades
- Osteophyte grades (OARSI guidelines)
- Sclerosis grades (OARSI guidelines)
- Joint space narrowing grades (OARSI guidelines)
- Measurements of the minimum joint space width
8. Sample Size for the Training Set
- The document does not explicitly state the sample size used for the training set. It mentions "machine learning algorithms trained on medical images" but does not provide details on the training data.
9. How the Ground Truth for the Training Set Was Established
- The document does not explicitly state how the ground truth for the training set was established. It only describes the establishment of ground truth for the validation (test) set.
§ 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).