MRI-based Ovarian Lesion Classification via a Foundation Segmentation Model and Multimodal Analysis: A Multicenter Study

Wen-Chi Hsu & Gigin Lin et al.

Combining the Segment Anything Model with a deep learning classifier produced an efficient pipeline for classifying MRI ovarian lesions, improving segmentation speed and matching radiologists’ classification performance.

Links
DOIPubMed
Journal
Radiology
Institutions
Johns Hopkins UniversityLinkou Chang Gung Memorial HospitalCentral South UniversityThe Rogosin Institute
Authors
Wen-Chi Hsu, Yu-Fu Wu, Ruohua Chen, Jhehong Liu, Victoria Shi, Jill S. Chotiyanonta, Ghazal Zandieh, Yeyu Cai, Jeffrey P. Leal, Kenichi Oishi, Atif Zaheer, Robert C. Ward, Gigin Lin
Funding
Regional Oncology Research Center (Risk Factors)Precision Medicine for Neonatal Hypoxic-Ischemic Encephalopathy: Combined Neuroimaging Clinical Approach to Link Phenotypes to PrognosisRegional Oncology Research Center (Risk Factors)Regional Oncology Research Center (Risk Factors)Ministry of Science and Technology, Taiwan Grant NSTC 112-2314-B-182A-127-MY3Chang Gung Medical Foundation Grant SMRPG3K0054

NCI NIH HHS

P30 CA006973

NINDS NIH HHS

R01 NS126549

National Institutions of Health

P30CA006973

National Cancer Institute

P30CA006973