BriefCase

BriefCase is an artificial intelligence-powered software intended to enhance radiological workflow by analyzing contrast-enhanced chest CT scans for suspected aortic dissection in adult and older adolescent patients, providing rapid notifications to aid clinicians in triage and case prioritization. Its methodology involves a deep learning algorithm processing DICOM images through a modular system (hospital server, cloud server, desktop application) to deliver informational preview images, operating alongside standard diagnostic practices.

BriefCase is a radiological computer-aided triage and notification software designed for the analysis of CT exams with contrast (CTA and CT with contrast) that include the chest in adults or transitional adolescents aged 18 and older. The device's purpose is to assist hospital networks and appropriately trained medical specialists in workflow triage by flagging and communicating suspected positive cases of aortic dissection (AD) pathology. It employs an artificial intelligence algorithm to analyze images and highlight cases with detected findings on a standalone application, operating in parallel with standard care image interpretation. Users are presented with notifications for suspected cases, which include compressed, non-diagnostic preview images intended for informational purposes only, to aid in prioritization. The device does not alter the original medical image and is not a diagnostic tool. The BriefCase system comprises three modules: an Aidoc Hospital Server for image acquisition, an Aidoc Cloud Server for image processing, and an Aidoc Desktop Application for workflow integration and displaying notifications. DICOM images are received, filtered, de-identified, and processed chronologically by the algorithm. A pivotal multicenter study involving 499 cases demonstrated the software's performance, achieving a sensitivity of 93.23% and a specificity of 92.83% for identifying aortic dissection, with a mean time-to-notification of 38 seconds. The system also offers additional operating points to maximize either sensitivity or specificity and allows users to filter notifications by pathology or medical center, aiming to facilitate earlier triage and reduce turnaround time.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the BriefCase algorithm's performance for aortic dissection detection vary across different CT scanner models and image acquisition parameters not explicitly detailed in the study?; What is the learning curve for medical specialists to effectively integrate BriefCase notifications into their existing triage workflow, and what training is recommended?; Considering the Positive Predictive Value of 25.0%, what strategies are recommended for users to manage the workload associated with reviewing non-AD cases flagged by the system?; How does the system handle concurrent processing of multiple studies, and what is its scalability for high-volume hospital networks?; Are there plans to expand the BriefCase algorithm to detect other acute aortic syndromes or incidental findings on chest CTs beyond aortic dissection?