(30 days)
PhantomMSK Hip is an image-processing software indicated to assist in the positioning of Total Hip Replacement and Hip Preservation components. It is intended to assist in precisely positioning Total Hip Replacement and Hip Preservation components intraoperatively by measuring their positions relative to the bone structures of interest provided that the points of interest can be identified from radiology images. Clinical judgement and experience are required to properly use the device. The device is not for primary image interpretation. The software is not for use on mobile phones.
The PhantomMSK Hip is a non-invasive software system that provides image analysis tools for Total Hip Replacement and Hip Preservation procedures that use fluoroscopic imaging to assist with implant and anatomic alignment. PhantomMSK Hip provides templating, measurement, and distortion adaptation (correction) tools for intraoperative fluoroscopic image assessment. PhantomMSK Hip does not include any custom computer hardware and is a software-based device that can be run on a "commercial off-the-shelf" system (i.e. PC, keyboard, mouse, touchscreen monitor etc.) that meet minimum performance requirements. Furthermore, PhantomMSK Hip operates on image principles that are not vendor specific. To operate PhantomMSK Hip, a fluoroscopic image is acquired from a C-arm and displayed outside the sterile field, where the image analysis tools can be used at the surgeon's discretion.
Fluoroscopic distortion is attributed to external electromagnetic interference and the mapping of the planar image on a curved input phosphor. The PhantomMSK Hip uses software features in conjunction with its radiopaque calibration array, which attaches to the C-arm image intensifier, to calculate and adapt for fluoroscopic distortion.
The provided text does not contain detailed information about specific acceptance criteria and a study proving the device meets those criteria with quantitative results, sample sizes, expert qualifications, or ground truth establishment methods typical for AI performance testing.
Instead, the document is an FDA 510(k) clearance letter and a 510(k) summary for the OrthoGrid Systems, Inc. PhantomMSK Hip. It focuses on demonstrating substantial equivalence to a predicate device (PhantomMSK K182332) rather than providing a performance study report against specific acceptance metrics for AI functionality.
The key points regarding testing are:
- Verification and validation testing: Performed at code and system level according to written test protocols.
- Purpose of testing: To ensure that all templating overlay, measurement, and distortion correction tools performed as expected.
- Specific equipment used: Philips Zenition 50 Digital Video Signal.
- Calibration array compatibility: Designed for C-arms with specific image intensifier outer diameters (34.5 to 38.5 cm and 28.6 to 33 cm).
- Review of results: Reviewed by "designated technical professionals" to ensure "acceptability criteria were satisfied."
- Conclusion of testing: "Verification strategies and test procedures used are appropriate," "System test procedures trace to requirements," "All requirements are tested or otherwise verified," and "Test results meet the required pass/fail criteria."
Below is a table showing the lack of specific acceptance criteria and performance data in the provided document, along with explanations.
Table of Acceptance Criteria and Reported Device Performance
| Acceptance Criteria (Metric) | Target Performance | Reported Device Performance | Comments/Evidence from Text |
|---|---|---|---|
| Accuracy of Templating Overlay | Not specified quantitatively | "performed as expected" | The document states "all templating overlay... tools performed as expected" and "Test results meet the required pass/fail criteria." No specific numerical accuracy or error margin is provided. |
| Accuracy of Measurement Tools | Not specified quantitatively | "performed as expected" | Same as above. No specific numerical accuracy or error margin is provided for angle, relative, or calibrated measurements. |
| Effectiveness of Distortion Correction | Not specified quantitatively | "performed as expected" | The document notes the device "calculate and adapt for fluoroscopic distortion" and "distortion correction tools performed as expected." No specific quantification of distortion reduction or resulting image quality improvement is given. |
| System Functionality | Meets all requirements | All requirements tested and verified | "All requirements are tested or otherwise verified" and "System test procedures trace to requirements." This is a high-level statement without specific functional or non-functional criteria detailed. |
Study Details (Based on provided text)
The document does not provide a detailed study report with the specific information requested. Here's what can be inferred or explicitly stated:
-
Sample size used for the test set and the data provenance:
- Sample Size: Not specified. The document only mentions "testing was conducted" and "test results were reviewed." It does not provide the number of images, cases, or patients used in the validation.
- Data Provenance: Not specified. There is no mention of the country of origin of the data, nor whether it was retrospective or prospective.
-
Number of experts used to establish the ground truth for the test set and the qualifications of those experts:
- Number of Experts: Not specified. The document states "The test results were reviewed by designated technical professionals." It does not specify the number of professionals or whether they were medical experts (e.g., radiologists, surgeons) or engineering professionals.
- Qualifications of Experts: Only "designated technical professionals" are mentioned. Their specific qualifications (e.g., medical degrees, years of experience, board certification) are not detailed.
-
Adjudication method (e.g., 2+1, 3+1, none) for the test set:
- Adjudication Method: Not specified. The document only states results were "reviewed by designated technical professionals." There's no mention of consensus methods or conflict resolution for ground truth establishment.
-
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. This type of study is not mentioned or described. The device is indicated to "assist in the positioning" and "is intended to assist in precisely positioning," implying an assistive role, but no human-in-the-loop performance study is reported. The document explicitly states, "The device is not for primary image interpretation."
-
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:
- Standalone Performance: While the software has automated functions (e.g., distortion correction, templating, measurement), the document does not detail specific standalone performance metrics (e.g., sensitivity, specificity, F1-score for automated detections/measurements) against a ground truth. The testing described is more about functional verification ("performed as expected").
-
The type of ground truth used (expert consensus, pathology, outcomes data, etc.):
- Type of Ground Truth: Not explicitly stated. Given the nature of the device (image processing for surgical assistance and measurements), the "ground truth" for the tests would likely involve known geometric properties, simulated distortions, or measurements from calibrated phantoms or expert-annotated images. However, the document does not specify how the ground truth was established for the "test results" that "meet the required pass/fail criteria."
-
The sample size for the training set:
- Training Set Sample Size: Not applicable/Not specified. The document does not describe the PhantomMSK Hip as an AI/ML device that requires a distinct "training set" in the context of deep learning or similar algorithms. It is described as "image-processing software" with "software features" to perform templating, measurement, and distortion adaptation. While some algorithms might be used, the typical AI/ML paradigm with training and test sets is not detailed. The focus is on substantial equivalence and functional testing.
-
How the ground truth for the training set was established:
- Training Set Ground Truth Establishment: Not applicable/Not specified, for the same reasons as #7.
§ 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).