Comparing efficiency of an attention-based deep learning network with contemporary radiological workflow for pulmonary embolism detection on CTPA: A retrospective study.
Authors
Affiliations (6)
Affiliations (6)
- Department of Radiology, Columbia University Irving Medical Center, NY, USA.
- Atal Bihari Vajpayee Institute of Medical Sciences, New Delhi, India.
- Department of Psychiatry, BronxCare Health System, NY, USA.
- Department of Biomedical Informatics, Stony Brook University, USA.
- Department of Radiology, MedStar Washington Hospital Center, DC, USA.
- Department of Radiology, Rutgers-Newark Beth Israel Medical Center, NJ, USA.
Abstract
Pulmonary embolism (PE) is the third most fatal cardiovascular disease in the United States. Currently, Computed Tomography Pulmonary Angiography (CTPA) serves as diagnostic gold standard for detecting PE. However, its efficacy is limited by factors such as contrast bolus timing, physician-dependent diagnostic accuracy, and time taken for scan interpretation. To address these limitations, we propose an AI-based PE triaging model (AID-PE) designed to predict the presence and key characteristics of PE on CTPA. This model aims to enhance diagnostic accuracy, efficiency, and the speed of PE identification. We trained AID-PE on the RSNA-STR PE CT (RSPECT) Dataset, N = 7279 and subsequently tested it on an in-house dataset (n = 106). We evaluated efficiency in a separate dataset (D<sub>4</sub>, n = 200) by comparing the time from scan to report in standard PE detection workflow versus AID-PE. A comparative analysis showed that AID-PE had an AUC/accuracy of 0.95/0.88. In contrast, a Convolutional Neural Network (CNN) classifier and a CNN-Long Short-Term Memory (LSTM) network without an attention module had an AUC/accuracy of 0.5/0.74 and 0.88/0.65, respectively. Our model achieved AUCs of 0.82 and 0.95 for detecting PE on the validation dataset and the independent test set, respectively. On D<sub>4</sub>, AID-PE took an average of 1.32 s to screen for PE across 148 CTPA studies, compared to an average of 40 min in contemporary workflow. AID-PE outperformed a baseline CNN classifier and a single-stage CNN-LSTM network without an attention module. Additionally, its efficiency is comparable to the current radiological workflow.