(108 days)
Rendoscopy's Gentle Colon, revision 2.0, is a system for the display and visualization of 3D and 2D medical image data of the colon derived from DICOM compliant CT scans for the purpose of complete colonic mucosa assessment. The user is capable to assure the colonic mucosa image quality through the following provisions built into the software:
- 3D visualization (3D detection, 2D assessment) .
- No blind areas behind colonic folds due to splitting colon techniques .
- Multi-path tracking system allows path finding over collapsed or liquid- filled . parts of the colon
- The software provides full presentation of cross sectional imaging, such as axial, . sagittal, frontal, oblique, intra-luminal, split colon, topogram view, external and unrolled view of the colon and double contrast visualization
It also includes an automatic report creation facility and is intended for use by Radiologists, Clinicians and referring Physicians to process, render, review, archive, print and distribute colon image study reports utilizing PC hardware.
The target population of the Gentle Colon 3D application is the adult patient. It is intended to be used as adjunctive to standard radiology practices for diagnosis, such as the double contrast/barium enema, of the colon.
The Gentle Colon contains all of the required software components to provide interactive 3D views from diagnostic CT scan 2D slice cut images of the colon utilizing PC hardware. The views include cross sectional imaging such as axial, sagittal, frontal, oblique, intraluminal, split colon, topogram view, external view of the colon and double contrast visualization. After the CT scan , axial cuts scanned colon image data are transferred to the Rendoscopy work station. The software loads the data from the CT without the need of manual interaction with the application, enabling the track through the colon including over collapsed parts or over liquid closed lumen.
Surface calculation of the colonic mucosa and splitting of the colon along the track follow automatically. The clip plane is oriented by the maximum curvature of the track, which ensures a free view of the colonic loops or folds.
Rendoscopy's 3D imaging algorithms create surfaces with almost no partial volume effect. Therefore, the 3D images have the highest possible technical contrast resolution, higher than 2D axial cuts.
By splitting the colon the user can get a free view behind the colonic folds, with no distortion. If the gas filled colon tube is interrupted by fluid, or by a collapsed colon part, the user will not run into trouble examining the adjacent colonic part. The Multipath Tracking System will find each path in the 3D dataset without any manual interaction.
This software device provides complete information on cross sectional imaging of any colon location and the information is updated at each step along the track. It is a user friendly, interactive automated Virtual Colonscopy (VC) that uses DICOM data from today's advanced multislice scanners from reputed manufacture. It has been tested and found to work smoothly with different PACS system produced by various manufacturers.
Here's a breakdown of the acceptance criteria and the study that demonstrates the device meets these criteria, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Feature/Criterion | Reported Device Performance (Rendoscopy Gentle Colon, Rev 2.0) |
|---|---|
| Equivalence to Predicate Device (GE Navigator) | Substantially equivalent in rendering 3D images for medical diagnostics. |
| Ability to view normal anatomy & pathologic findings. | Radiologist found images equivalent in all 30 cases (compared to predicate). |
| Support for 2D and 3D reconstructions. | Provides 3D visualization and 2D assessment methods. |
| Visualization of well-distended colons. | Demonstrated ability to visualize in well-distended colons. |
| Visualization of partially collapsed colons. | Demonstrated ability to visualize in partially collapsed colons. |
| Software development consistency with accepted standards. | Developed consistent with accepted standards; reliable, easy to use. |
| Meeting design specifications and performance requirements. | Passed all final acceptance tests/verification. |
| Performance as intended. | Verified by a radiologist during clinical validation. |
| Technical contrast resolution of 3D images. | Higher than 2D axial cuts due to almost no partial volume effect. |
| No blind areas behind colonic folds. | Achieved through splitting colon techniques. |
| Path finding over collapsed/liquid-filled parts. | Multipath Tracking System allows this without manual interaction. |
| Comprehensive cross-sectional imaging presentation. | Provides axial, sagittal, frontal, oblique, intra-luminal, split colon, topogram, external, unrolled, and double contrast visualization. |
| Automatic report creation facility. | Included. |
| Compatibility with DICOM compliant CT scans. | Uses DICOM data from advanced multislice scanners. |
| Compatibility with PACS systems. | Tested and found to work smoothly with different PACS systems. |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 30 patient cases.
- Data Provenance: Not explicitly stated, but the study was a clinical validation performed by a radiologist, implying real patient data. It is retrospective since it involved comparing the device's output to that of a predicate device.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications of Those Experts
- Number of Experts: One radiologist.
- Qualifications of Experts: "a radiologist." No specific experience level (e.g., "10 years of experience") is mentioned.
4. Adjudication Method (e.g., 2+1, 3+1, none) for the Test Set
- Adjudication Method: None explicitly stated or implied. The single radiologist evaluated and compared results from both devices. There was no mention of multiple readers or a consensus process.
5. 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 was a direct comparison of the new device's output with a predicate device, as evaluated by a single radiologist. The study focused on the equivalence of the device's output, not on the improvement of human readers with or without AI assistance.
6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) was done
- Standalone Performance: This device is a software for display and visualization, assisting radiologists. The "clinical validation" involved a radiologist reviewing the images. While the software has automated features (segmentation, path planning), the evaluation was within the context of a radiologist's use. Therefore, a purely "algorithm only" standalone performance assessment separate from human review is not detailed in this section. The focus was on the output's quality as perceived by an expert user.
7. The Type of Ground Truth Used (expert consensus, pathology, outcomes data, etc.)
- Type of Ground Truth: The ground truth appears to be the results obtained from the predicate device (GE Navigator). The radiologist evaluated "normal anatomy and pathologic findings" and directly compared the images produced by the Gentle Colon to those from the predicate device to determine "its quality and effectiveness." This is a comparative study against an established method, effectively using the predicate device's output as the point of reference for evaluation.
8. The Sample Size for the Training Set
- Sample Size for Training Set: Not mentioned or implied anywhere in the provided text. The document describes a clinical validation using a test set of 30 cases.
9. How the Ground Truth for the Training Set was Established
- How Ground Truth for Training Set was Established: Not applicable, as no information on a training set or its ground truth establishment is 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).