Diagnostic Performance of a Deep Learning-Powered Application for Aortic Dissection Triage Prioritization and
Vladimir Laletin1, Angela Ayobi1, Peter D Chang2,3
1Avicenna.AI, 375 Avenue du Mistral, 13600 La Ciotat, France.
Diagnostics (Basel, Switzerland)
|September 14, 2024
Summary
A deep learning tool accurately detects and classifies aortic dissections (ADs) on CT angiography scans. This AI application shows high sensitivity and specificity, potentially speeding up diagnosis for urgent cases.
Area of Science:
- Radiology
- Artificial Intelligence
- Cardiovascular Imaging
Background:
- Aortic dissection (AD) is a life-threatening condition requiring rapid diagnosis.
- CT angiography (CTA) is a primary imaging modality for AD detection.
- Deep learning (DL) offers potential for improving diagnostic accuracy and efficiency in medical imaging.
Purpose of the Study:
- To evaluate the diagnostic performance of a DL-based application (CINA-CHEST (AD)) for detecting and classifying aortic dissections on chest and thoraco-abdominal CTA scans.
- To compare the DL application's performance against a radiologist-adjudicated ground truth.
- To assess the clinical effectiveness by measuring the DL algorithm's time to notification.
Main Methods:
- A multicenter retrospective study analyzed 1303 CTA scans from over 200 cities.
- CTA scans were processed by the CINA-CHEST (AD) deep learning device.
- Diagnostic performance was benchmarked against a consensus of three U.S. board-certified radiologists.
Main Results:
- The DL application achieved a sensitivity of 94.2% and specificity of 97.3% for detecting AD.
- Classification accuracy for AD types was 99.5% for Type A and 97.5% for Type B.
- The mean time for processing and notifying potential AD cases was 27.9 seconds.
Conclusions:
- The deep learning application demonstrates strong diagnostic performance in detecting and classifying aortic dissections.
- The AI tool shows potential for enabling faster triage of urgent aortic dissection cases in clinical practice.
- The application's speed and accuracy suggest a valuable role in improving patient outcomes for AD.
Related Concept Videos
01:19Assessing Blood pressure using a doppler ultrasound
To obtain accurate blood pressure measurements in clinical settings, especially when traditional methods are insufficient, healthcare professionals utilize the Doppler ultrasound technique. This method uses high-frequency sound waves to detect blood flow within the arteries, which is crucial for patients with conditions that complicate circulatory system assessment.
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:
Pre-Procedural Guidelines for Doppler Ultrasound Blood Pressure Assessment:
Preparation of Equipment:
01:21Peripheral Arterial Disease II: Clinical Manifestations and Diagnostic Evaluation
Clinical manifestationsPeripheral Arterial Disease (PAD) manifests through a range of symptoms, from the characteristic intermittent claudication to atypical presentations and severe complications in advanced stages. Intermittent claudication, a hallmark symptom of PAD, presents as exercise-induced muscle pain that typically resolves within minutes of rest. This pain is reproducible and stems from inadequate blood flow, leading to the accumulation of lactic acid produced during anaerobic...