Related Experiment Video
Updated: Jan 11, 2026
09:32
Measurement of Pulse Propagation Velocity, Distensibility and Strain in an Abdominal Aortic Aneurysm Mouse Model
Published on: February 23, 2020
6.7K
Deep Learning-Enabled Diagnosis of Abdominal Aortic Aneurysm Using Pulse Volume Recording Waveforms: An In Silico
Sina Masoumi Shahrbabak1, Byeng Dong Youn2,3, Hao-Min Cheng4
1Mechanical Engineering, University of Maryland, College Park, MD 20742, USA.
Sensors (Basel, Switzerland)
|November 13, 2025
Summary
Deep learning analysis of non-invasive pulse volume recording (PVR) signals shows promise for diagnosing abdominal aortic aneurysm (AAA). This cost-effective approach could enable accessible AAA screening using point-of-care technologies.
Area of Science:
- Biomedical Engineering
- Artificial Intelligence in Medicine
- Cardiovascular Diagnostics
Background:
- Abdominal aortic aneurysm (AAA) diagnosis often relies on invasive or complex imaging techniques.
- Non-invasive methods for early AAA detection are crucial for improving patient outcomes.
- Pulse waveform analysis offers a potential avenue for accessible cardiovascular assessment.
Purpose of the Study:
- To investigate the feasibility of diagnosing abdominal aortic aneurysm (AAA) using deep learning (DL) analysis of non-invasive pulse volume recording (PVR) signals.
- To develop and evaluate a DL algorithm for estimating AAA severity from PVR waveforms.
- To compare the performance of a PVR-based DL algorithm against one trained on invasive arterial blood pressure (BP) signals.
Main Methods:
- Generated synthetic arterial blood pressure (BP) and pulse volume recording (PVR) waveform signals using a systemic arterial circulation model.
- Simulated various severities of abdominal aortic aneurysm (AAA) within the synthetic cohort.
- Developed a convolutional neural network (CNN) with continuous property-adversarial regularization for AAA severity estimation from PVR signals.
- Validated the synthetic data against in vivo findings and compared DL algorithm performance with invasive BP data.
Main Results:
- The DL-enabled PVR-based algorithm demonstrated robust AAA detection with an area under the ROC curve >0.89.
- The algorithm showed reasonable accuracy in estimating AAA severity from PVR signals (MAE: 12.6%).
- Performance was comparable, though slightly lower than, an identical CNN trained on invasive arterial BP signals (MAE: 10.3%).
Conclusions:
- Deep learning analysis of non-invasive PVR waveform signals presents a feasible, cost-effective method for AAA diagnosis.
- This approach has the potential to facilitate accessible AAA screening.
- Operator-agnostic, point-of-care PVR analysis could significantly enhance early detection and management of AAA.
Related Concept Videos
01:21Aneurysm II: Clinical Manifestations and Diagnostic Studies
258
Thoracic, aortic arch and abdominal aneurysms are significant vascular conditions that can present with various clinical manifestations and lead to serious complications. Understanding these manifestations and the appropriate diagnostic studies is essential for effective management and treatment.Thoracic Aortic AneurysmsThoracic aortic aneurysms often remain asymptomatic until they reach a size that impinges on adjacent structures. They typically cause deep, diffuse chest pain that radiates to...
258
01:21Peripheral Arterial Disease II: Clinical Manifestations and Diagnostic Evaluation
339
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...
339