Search Results
Found 1 results
510(k) Data Aggregation
(160 days)
CINA-CSpine
CINA-CSpine is a radiological computer aided triage and notification software indicated for use in the analysis of cervical spine CT images.
The device is intended to assist hospital networks and appropriately trained physician specialists by flagging and communication of suspected positive findings compatible with acute cervical spine fractures including non-displaced fracture lines and/or displaced fracture fragments.
CINA-CSpine uses an artificial intelligence algorithm to analyze images and highlight cases with detected findings on a standalone application in parallel to the ongoing standard of care image interpretation. The device is not designed to detect vertebral compression fractures.
The user is presented with notifications for cases with suspected findings. Notifications include compressed preview images that are meant for informational purposes only, and are not intended for diagnostic use beyond notification. The device does not alter the original medical image, and it is not intended to be used as a diagnostic device.
The results of CINA-CSpine are intended to be used in conjunction with other patient information and based on professional judgment to assist with triage/prioritization of medical images.
Notified clinicians are ultimately responsible for reviewing full images per the standard of care.
CINA-CSpine is a radiological computer-assisted triage and notification software device.
CINA-CSpine runs on a standard "off the shelf" server/workstation and consists of CSpine Image Processing Application, which can be integrated, deployed and used with the CINA Platform (cleared under K200855) or other medical image communications devices. CINA-CSpine receives cervical spine CT scans identified by the CINA Platform or other medical image communications device, processes them using deep learning algorithms involving execution of multiple computational steps to identify the suspected positive findings compatible with acute cervical spine fractures and generates results files to be transferred by CINA Platform or a similar medical image communications device for output to a PACS system or workstation for worklist prioritization.
To identify the suspected presence of cervical fractures, the device uses a deep learning model trained end-to-end on 1,338 cases acquired from US and France, representing a distribution of fracture presentations, locations and acquisition protocols, including multiple scanner models from Siemens, Philips, GE and Canon/Toshiba. Additional deep learning models are used to locate the individual vertebrae to exclude images that do not conform to the expected field of view.
DICOM images are received, recorded and filtered before processing. The series are processed chronologically by running algorithms on each series to detect suspected positive findings of a cervical spine fracture, then active notifications on the flagged series are sent to the worklist application.
The Worklist Application displays the active notification of new studies with suspected findings when they come in. All the cervical spine CT studies which include at least 5 visible cervical vertebrae received by CINA-CSpine device are displayed in the worklist and those on which the algorithms have detected a suspected finding are marked with an icon (i.e., active notification). In addition, a compressed, grayscale, unannotated image that is marked "not for diagnostic use" is displayed as a preview function. This compressed preview is meant for informational purposes only, does not contain any marking of the findings, and is not intended for diagnostic use beyond notification.
Presenting the trained physician specialist with notification facilitates earlier triage by allowing image prioritization in the PACS. Thus, the suspect case receives attention earlier than would have been the case in the standard of care practice alone.
The CINA platform is an example of medical image communications platform for integrating and deploying the CINA-CSpine image processing application. The medical image communications device (i.e., the technical platform) provides the necessary requirements for interoperability based on the standardized DICOM protocol and services to communicate with existing systems in the hospital radiology department such as CT modalities or other DICOM nodes (DICOM router or PACS for example). It is responsible for transferring, converting formats, notifying of suspected findings and displaying medical device data such as radiological data. The medical image communications server includes the Worklist client application, which receives notifications from the CINA-CSpine Image Processing application.
1. Table of Acceptance Criteria and Reported Device Performance
| Metric | Acceptance Criteria (Performance Goal) | Reported Device Performance (mean [95% CI]) | Predicate Device Performance (mean [95% CI]) |
|---|---|---|---|
| Sensitivity | ≥ 80% | 90.3% [84.5% - 94.5%] | 91.7% [82.7% - 96.9%] |
| Specificity | ≥ 80% | 91.9% [86.8% - 95.5%] | 88.6% [81.2% - 93.8%] |
| Time-to-Notification (All Cases) | Not specified (Comparable to predicate) | 2.9 minutes [2.7 - 3.0] | Not specified |
| Time-to-Notification (True Positive Cases) | Not specified (Comparable to predicate) | 2.8 minutes [2.6 - 3.0] | 3.9 minutes [3.8 - 4.1] |
2. Sample Size Used for the Test Set and Data Provenance
- Test Set Sample Size: 328 clinical anonymized cases.
- Data Provenance: Retrospective, multicenter, multinational. Data was acquired from:
- US: 60.4% of cases, including a U.S. teleradiology company with a database from various U.S. hospitals across different territories.
- OUS: 39.6% of cases.
- Scanner Manufacturers: GE (31.1%), Philips (21.6%), Siemens (28.7%), Canon (18.3%), and 36 different scanner models.
- Time Periods: The validation dataset was from independent sites and different time periods compared to the training data.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Qualifications
- Number of Experts: Three.
- Qualifications of Experts: US-board-certified expert radiologists.
4. Adjudication Method for the Test Set
The ground truth was established by the consensus of the three US-board-certified expert radiologists. This implies a 3-expert consensus (e.g., all 3 agree, or majority vote if specific rules were defined for disagreement, which is not further detailed).
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
No, an MRMC comparative effectiveness study was not reported. The study focused on the standalone performance of the AI device and compared its performance metrics (Sensitivity, Specificity, Time-to-Notification) to those reported for the predicate device. There is no mention of human readers improving with AI assistance.
6. Standalone Performance (Algorithm Only without Human-in-the-Loop)
Yes, a standalone performance testing was performed. The described study evaluated the software's performance (Sensitivity and Specificity) in detecting cervical spine fractures on non-contrast CT scans without human intervention in the initial detection process.
7. Type of Ground Truth Used
Expert Consensus: The ground truth was established by the consensus of three US-board-certified expert radiologists.
8. Sample Size for the Training Set
The deep learning model was trained end-to-end on 1,338 cases.
9. How the Ground Truth for the Training Set Was Established
The document states that the training data was acquired from US and France, representing a distribution of fracture presentations, locations, and acquisition protocols. However, it does not explicitly detail how the ground truth was established for this training set (e.g., if it was also expert consensus, based on pathology reports, or other methods). It can be inferred that it would likely follow a similar rigorous annotation process to establish "true" fracture presence, but specific details are not provided.
Ask a specific question about this device
Page 1 of 1