Improving the Robustness of Deep Learning Models in Predicting Hematoma Expansion from Admission Head CT
Adversarial training and inclusion of threshold-based segmentation as an additional input can improve deep learning model robustness in prediction of HE from admission head CTs in acute ICH.
Authors
- Tran Anh Tuan (ORCID: https://orcid.org/0000-0001-9994-8077)
- Santosh B. Murthy (ORCID: https://orcid.org/0000-0002-4950-0992)
- Adnan Iqbal Qureshi (ORCID: https://orcid.org/0000-0003-4962-540X)
- Ajay Malhotra (ORCID: https://orcid.org/0000-0001-9223-6640)
- Shahram Majidi (ORCID: https://orcid.org/0000-0003-2971-6216)
- Guido J. Falcone (ORCID: https://orcid.org/0000-0002-6407-0302)
- Kevin Navin Sheth (ORCID: https://orcid.org/0000-0003-2003-5473)
- Seyedmehdi Payabvash (ORCID: https://orcid.org/0000-0003-4628-0370)
- Despina Kontos (ORCID: https://orcid.org/0000-0001-9031-5126)
- Gaby Abou Karam (ORCID: https://orcid.org/0009-0003-3540-7185)
- Dorin Zeevi
- Soojin Park (ORCID: https://orcid.org/0000-0002-3688-7307)
Institutions
- Cornell University (US)
- Columbia University Irving Medical Center (US)
- Yale University (US)
- Mount Sinai Hospital (US)
- Rehabilitation Institute of Kansas City (US)
- Yale New Haven Health System (US)
- CentraCare Health System (US)
- University of Missouri (US)
- Columbia University (US)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- American Journal of Neuroradiology
- Published
- 2025-01-10
- DOI
- https://doi.org/10.3174/ajnr.a8650
- Citations
- 3
- Primary Topic
- Intracerebral and Subarachnoid Hemorrhage Research
- Type
- article
- Field-Weighted Citation Impact
- 4.17