CINA Pulmonary Embolism is a triage application to accurately detect pulmonary embolism on chest CTA exams. Compared to most competitor applications, our algorithms are trained using data arising from over 200 centers across 43 states in the US. Ground-truth annotations were performed via consensus by 2 US board-certified radiologists. CINA Pulmonary Embolism is a robust AI application for your clinical environment.

Value Proposition

A key to successful implementation of real-world AI applications is the ability to accurately detect positive cases despite the relative low true disease incidence. To ensure minimal false positive notifications, we have carefully designed our application to account for the low disease incidence in the population in addition to recognition of key imaging artifacts and distractors. Combined with fast and accurate detection algorithms, our value proposition includes: 1. Faster Patient Care 2. Reduced Error Rates 3. Improved Physician Efficiency

Narrative

Missed and/or delayed diagnosis of pulmonary embolism (PE) is one of the most common causes of preventable death in hospitalized patients. However, detection of PE is challenging given the high volume and pace of emergency imaging as well as the tedious and error-prone nature of carefully evaluating every pulmonary arterial vessel on high-resolution CT angiograms. With the CINA Pulmonary Embolism tool, patients with positive findings can be quickly flagged and treated with improved efficiency.

Intended Use

CINA CHEST is a radiological computer aided triage and notification software indicated for use in the analysis of Chest and Thoraco-abdominal CT angiography. The device is intended to assist hospital networks and trained radiologists in workflow triage by flagging and communicating suspected positive findings of (1) Chest CT angiography for Pulmonary Embolism (PE) and (2)  Chest or Thoraco-abdominal CT angiography for Aortic Dissection (AD).

CINA CHEST uses an artificial intelligence algorithm to analyze images and highlight cases with detected PE and AD on a standalone Web application in parallel to the ongoing standard of care image interpretation. The user is presented with notifications for cases with suspected PE or AD 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 CHEST 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.

Limitations

CINA Pulmonary embolism may fail to flag and communicate suspected positive findings of Chest CT angiography for Pulmonary Embolism (PE) in the situations below:

o embolus located in subsegmental arteries,
o poor contrast opacification: a minimum HU measurement taken at the main pulmonary embolus must be obtained for algorithm interpretation,
o chronic PE,
o inadequate field of view,
o notable image noise,
o severe motion artifacts,
o severe streak artifacts including IVC beam-hardening artifact

Model performance metrics

Sensitivity and Specificity for the “PE” prioritization and triage application are observed to be 91.1% and 91.8% , respectively. The ROC curve for PE detection showed an AUC of 0.91.

cercle-AI

Avicenna.ai

Avicenna.AI was born in 2018 from the collaboration of Cyril Di Grandi, Software and Medical Device expert and Dr. Peter Chang, Radiologist and AI expert. This collaboration of experts, radiologists and software engineers who believe that your clinical needs should be the only drivers of new technologies. Thanks to a young team with a common goal of innovation, excellence and transmission, we are bringing a new solution to emergency medicine.