(20 days)
Colon CAR 1.2 is a PC-based, stand-alone, non-invasive, image analysis software application for the display and visualization of 2D and 3D medical image data of the colon derived from CT scans, for the purpose of assisting radiologists and other clinicians in the evaluation of polyps, cancers and other lesions. The software provides functionality for the user to extract the region of interest (ROI) either manually using a drawing tool, or "semi-automatically" through the user selecting single or double seed points followed by interactive fine-tuning the boundaries of the ROI. It also allows for the simultaneous display of supine and prone images.
Colon CAR 1.2 contains additional imaging tools which allow enhancement of specified features, and which the clinician can view simultaneously with the non-enhanced view.
Colon CAR™ (Computer Assisted Reader) 1.2 is a software tool designed to assist radiologists and other clinicians in the evaluation of polyps and other lesions in the colon. The software allows the user to select regions of interest either manually or by selecting a single or double seed point, followed by semi-automatic detection of the ROI boundary. It provides 2D and 3D visualisation of polyps and measurement of polyp characteristics such as size and volume. The further feature of Colon CAR™ 1.2 as compared to the cleared device is a Polyp Enhanced Viewing Filter (PEV), the results of which are presented in a Joint Reader filter view (enhanced and non-enhanced data viewed simultaneously). The PEV filter identifies intra-colonic filling defects protruding into the colonic lumen, thereby highlighting potential polyp candidates for further interrogation by the reporting radiologist. This filter is fully adjustable and, in deciding the desired characteristics of the objects to be highlighted, the radiologist may specify the degree of object sphericity (or roundness), the height of the protruding object in relation to its base (object 'flatness') as well as select an approximate object diameter range.
The provided text does not contain specific acceptance criteria or an explicit study describing the device's performance against such criteria. The document is a 510(k) summary for the Medicsight Colon CAR 1.2, focusing on its substantial equivalence to a predicate device rather than presenting detailed performance statistics or an independent study to prove acceptance criteria.
However, based on the information provided, we can infer some aspects and highlight what is missing:
1. Table of Acceptance Criteria and Reported Device Performance:
| Acceptance Criteria (Inferred) | Reported Device Performance |
|---|---|
| Substantial Equivalence to Predicate Device (MedicColon 1.0, K033102) | "The functional features and the intended use of Colon CAR 1.2 are substantially equivalent to the predicate device. The modifications to the original device did not introduce any new potential safety risks." |
| Safety: No new potential safety risks | "A comprehensive hazard analysis was carried out on Colon CAR 1.2, which concluded that any residual risks were as low as reasonably practicable and judged as acceptable when weighed against the intended benefits of use of the system." |
| Effectiveness: Equivalent to legally marketed device | "Colon CAR 1.2 is equivalent in performance to the existing legally marketed device." |
2. Sample Size for Test Set and Data Provenance:
- Sample Size: Not explicitly stated. The document mentions "Test data are provided to validate the performance of the system," but does not specify the size of this test set.
- Data Provenance: Not explicitly stated. The document mentions "Medicsight PLC." is located in "London W1J 5AT UK," but there is no information about the origin of the test data (e.g., country of origin, retrospective or prospective).
3. Number of Experts and Qualifications for Ground Truth:
- Not explicitly stated. The document refers to "radiologists and other clinicians" as intended users, but there is no information about experts used to establish ground truth for any test sets.
4. Adjudication Method for Test Set:
- Not explicitly stated. No details are provided regarding how ground truth was established or if any adjudication process was used.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study:
- Not explicitly stated. The document does not describe an MRMC study comparing human readers with and without AI assistance, nor does it provide an effect size. The device is described as "a software tool designed to assist radiologists," implying human-in-the-loop, but no comparative effectiveness study is presented.
6. Standalone Performance Study:
- Not explicitly stated. While the device is "PC-based, stand-alone, non-invasive, image analysis software," the document does not present a standalone performance study of the algorithm without human-in-the-loop. The "Polyp Enhanced Viewing Filter (PEV)" is described as highlighting "potential polyp candidates for further interrogation by the reporting radiologist," indicating an assisted workflow rather than a standalone diagnostic output.
7. Type of Ground Truth Used:
- Not explicitly stated. Given the context of colon polyp detection, common ground truths include expert consensus (e.g., colonoscopy findings, pathology reports), but the document does not specify.
8. Sample Size for Training Set:
- Not explicitly stated. There is no information provided about a training set or its size.
9. How Ground Truth for Training Set was Established:
- Not explicitly stated. Since no training set is mentioned, there is no information on how its ground truth might have been established.
Summary of Missing Information:
The provided 510(k) summary primarily focuses on demonstrating substantial equivalence to a predicate device, which often relies on functional comparisons and hazard analysis rather than detailed performance studies with explicit acceptance criteria and corresponding results. The document lacks the specific details requested regarding test set size, data provenance, expert qualifications, ground truth establishment methods, and detailed performance metrics that would be found in a comprehensive clinical or technical study report.
§ 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).