(89 days)
CINA-iPE is a radiological computer-aided triage and notification software indicated for use in patients undergoing contrast-enhanced CT scans (not dedicated CTPA protocol) for other clinical indications than pulmonary embolism suspicion, including at least a part of the lung. The device is intended to assist hospital networks and appropriately trained radiologists in workflow triage by flagging and communicating suspected positive findings for incidental Pulmonary Embolism (iPE). The device is indicated for adults and transitional adolescents (18 to 21 years old but treated as adults).
CINA-iPE uses an artificial intelligence algorithm to analyze images and highlight cases with detected incidental PE on a standalone application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected incidental PE findings. The device is not designed to detect PE in subsegmental arteries.
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-iPE are intended to be used in conjunction with other patient information and based on their 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-iPE is a radiological computer aided triage and notification software device.
CINA-iPE runs on a standard "off the shelf" server/workstation and consists of an Image Processing Application, which can be integrated, deployed, and used with the CINA Platform (cleared under K200855) or other medical image communications devices. CINA-iPE receives contrast-enhanced CT scans (not dedicated CTPA protocol) including at least a part of the lung identified by the CINA Platform or other medical image communications device, processes them using deep learning algorithms involving the execution of multiple computational steps to identify the suspected presence of an incidental pulmonary embolism and generates results files to be transferred by CINA Platform or a similar medical image communications device for output to a PACS system or worklist prioritization.
To identify the suspected presence of pulmonary embolisms, the device uses a deep learning model trained end-to-end on 5.429 cases acquired from US and France, representing a distribution of PE sizes, locations and acquisition protocols, including multiple scanner models from Siemens, Philips, GE and Canon/Toshiba. Additional models are used to locate the aorta and main pulmonary artery, enabling assessment of the contrast timing. The lung's parenchyma is segmented to evaluate both the presence of the lungs in the field of view and to limit the region of interest for detecting the presence of pulmonary embolisms.
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 an incidental Pulmonary Embolism (iPE), 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 contrast-enhanced CT studies received by CINA-iPE device are displayed in the worklist and those on which the algorithms have detected finding are marked with an icon (i.e., passive 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 radiologist with notification facilitates earlier triage by allowing prioritization of images in the PACS. Thus, the suspect case receives attention earlier than would have been the case in the standard of care image interpretation practice alone.
The CINA platform is an example of medical image communications platform for integrating and deploying the CINA-iPE 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, storing, 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 in which notifications from the CINA-iPE Image Processing application are received.
The provided text describes the acceptance criteria and the study conducted to prove that the CINA-iPE device meets these criteria.
Here's an organized breakdown of the requested information:
1. Table of Acceptance Criteria and Reported Device Performance
The primary acceptance criteria for the CINA-iPE device were its Sensitivity and Specificity in identifying incidental Pulmonary Embolism (iPE), measured against a performance goal of 80%.
| Metric | Acceptance Criteria (Performance Goal) | Reported Device Performance [95% CI] |
|---|---|---|
| Sensitivity | ≥ 80% | 87.8% [82.2% - 92.2%] |
| Specificity | ≥ 80% | 92.0% [87.3% - 95.4%] |
Additional Performance Data (Sub-group Analysis):
| Arterial Segment | Sensitivity [95% CI] |
|---|---|
| Main (N = 55) | 96.3% [87.5% - 99.6%] |
| Interlobar (N = 73) | 94.5% [86.6% - 98.5%] |
| Lobar (N = 127) | 92.9% [87.0% - 96.7%] |
| Segmental (N = 179) | 88.3% [82.6% - 92.6%] |
Time-to-Notification:
| Metric | MEAN ± SD | MEDIAN | 95% CI | MIN | MAX |
|---|---|---|---|---|---|
| CINA-iPE All cases | |||||
| (N = 381) | 1.5 ± 0.5 | 1.4 | [1.4 - 1.5] | 0.3 | 2.7 |
| CINA-iPE True Positive cases | |||||
| (N = 159) | 1.5 ± 0.4 | 1.5 | [1.4 - 1.6] | 0.7 | 3.1 |
2. Sample Size Used for the Test Set and Data Provenance
- Sample Size for Test Set: 381 clinical anonymized cases.
- Data Provenance: Retrospective, multinational study.
- Country of Origin: Data was acquired from multiple U.S. and OUS (Outside US) clinical sites. Specifically, 56.4% (215) of cases came from U.S. clinical sources.
- Retrospective/Prospective: Retrospective.
- Independence: The independence of the standalone validation dataset from the training data was ensured using data from independent sites and different time periods.
- Patient Demographics: 53.5% Male and 46.7% Female. Mean ± SD age: 64.5 ± 15.8 years (range: 18 - 99 years).
- Scanner Diversity: Acquired primarily by 4 different scanner makers (GE-31.5%, Philips-28.3%, Siemens-26%, and Canon-13.9%) and 39 different scanner models.
3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications
- Number of Experts: Three (3)
- Qualifications of Experts: US-board-certified expert radiologists.
4. Adjudication Method for the Test Set
The ground truth was established by consensus of the three US-board-certified expert radiologists. While the specific mechanism of reaching consensus (e.g., 2 majority, discussion, etc.) is not detailed, the term "consensus" implies agreement among the experts.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- Was an MRMC study done? The provided text does not explicitly state that a multi-reader multi-case (MRMC) comparative effectiveness study was done to evaluate how human readers improve with AI vs. without AI assistance. The study focuses on the standalone performance of the algorithm and its time-to-notification effectiveness for triage/prioritization.
- Effect Size of Human Improvement: Not applicable, as an MRMC comparative effectiveness study was not described.
6. Standalone (Algorithm Only) Performance Study
- Was a standalone study done? Yes, a standalone performance testing study was conducted.
- Details: The study evaluated the CINA-iPE application's performance in identifying incidental pulmonary embolisms (iPE) on contrast-enhanced CT images. The primary endpoint was the device's Sensitivity and Specificity.
7. Type of Ground Truth Used
- Ground Truth Type: Expert Consensus. The ground truth was established by the consensus of three US-board-certified expert radiologists.
8. Sample Size for the Training Set
- Sample Size for Training Set: 5,429 cases.
9. How the Ground Truth for the Training Set Was Established
- Method: The deep learning model was "trained end-to-end on 5.429 cases acquired from US and France, representing a distribution of PE sizes, locations and acquisition protocols." The precise method for establishing ground truth for training is not explicitly detailed but it's implied that these cases were labeled with PE sizes and locations, likely through expert review similar to the test set, but this is not explicitly stated.
§ 892.2080 Radiological computer aided triage and notification software.
(a)
Identification. Radiological computer aided triage and notification software is an image processing prescription device intended to aid in prioritization and triage of radiological medical images. The device notifies a designated list of clinicians of the availability of time sensitive radiological medical images for review based on computer aided image analysis of those images performed by the device. The device does not mark, highlight, or direct users' attention to a specific location in the original image. The device does not remove cases from a reading queue. The device operates in parallel with the standard of care, which remains the default option for all cases.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the notification and triage algorithms and all underlying image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, how the algorithm affects or relates to clinical practice or patient care, and any algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will provide effective triage (
e.g., improved time to review of prioritized images for pre-specified clinicians).(iii) Results from performance testing that demonstrate that the device will provide effective triage. The performance assessment must be based on an appropriate measure to estimate the clinical effectiveness. The test dataset must contain sufficient numbers of cases from important cohorts (
e.g., subsets defined by clinically relevant confounders, effect modifiers, associated diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals for these individual subsets can be characterized with the device for the intended use population and imaging equipment.(iv) Stand-alone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; description of verification and validation activities including system level test protocol, pass/fail criteria, and results).(2) Labeling must include the following:
(i) A detailed description of the patient population for which the device is indicated for use;
(ii) A detailed description of the intended user and user training that addresses appropriate use protocols for the device;
(iii) Discussion of warnings, precautions, and limitations must include situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality for certain subpopulations), as applicable;(iv) A detailed description of compatible imaging hardware, imaging protocols, and requirements for input images;
(v) Device operating instructions; and
(vi) A detailed summary of the performance testing, including: test methods, dataset characteristics, triage effectiveness (
e.g., improved time to review of prioritized images for pre-specified clinicians), diagnostic accuracy of algorithms informing triage decision, and results with associated statistical uncertainty (e.g., confidence intervals), including a summary of subanalyses on case distributions stratified by relevant confounders, such as lesion and organ characteristics, disease stages, and imaging equipment.