Comparing efficiency of an attention-based deep learning network with contemporary radiological workflow for pulmonary embolism detection on CTPA: A retrospective study
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.
Authors
- Tej Phatak (ORCID: https://orcid.org/0000-0002-0245-7843)
- Prateek Prasanna (ORCID: https://orcid.org/0000-0002-3068-3573)
- Luke Partyka
- Nicole Sakla (ORCID: https://orcid.org/0000-0001-9607-0406)
- Tejasvi Kainth (ORCID: https://orcid.org/0000-0002-0116-6702)
- Gagandeep Singh (ORCID: https://orcid.org/0000-0003-4291-9026)
- Annie Singh (ORCID: https://orcid.org/0000-0002-6907-2825)
- Sudhir Suman
Institutions
- Newark Beth Israel Medical Center (US)
- MedStar Washington Hospital Center (US)
- Columbia University Irving Medical Center (US)
- Atal Bihari Vajpayee Institute of Medical Sciences and Dr. Ram Manohar Lohia Hospital (IN)
- MemorialCare Health System (US)
- Institute of Medical Sciences (IN)
- Stony Brook University (US)
Publication Details
- Journal
- European Journal of Radiology Open
- Published
- 2025-05-09
- DOI
- https://doi.org/10.1016/j.ejro.2025.100657
- Primary Topic
- Venous Thromboembolism Diagnosis and Management
- Type
- article
- Field-Weighted Citation Impact
- 0.00