Search papers, labs, and topics across Lattice.
This study addresses the challenge of ovarian segmentation in MRI for endometriosis by introducing a dual branch framework that leverages transvaginal ultrasound (TVUS) prototype priors. By aligning feature representations across TVUS and MRI, the method significantly enhances segmentation accuracy, achieving over 5 percentage points improvement compared to existing state-of-the-art techniques. The findings underscore the effectiveness of using unpaired modality data to improve anatomical segmentation in complex medical imaging scenarios.
Achieving over 5% improvement in ovarian segmentation accuracy by leveraging cross-modal insights from TVUS and MRI could redefine standards in medical imaging for endometriosis.
Transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI) provide complementary information for endometriosis image analysis, yet existing studies mainly focus on single-modality analysis or disease classification, leaving cross-modal ovarian segmentation largely unexplored. In this work, to tackle the increased difficulty of ovary segmentation in MRI due to ovaries'small target size and ambiguous boundaries with surrounding pelvic structures, we propose a dual branch framework for ovary segmentation across TVUS and MRI. More specifically, by adapting MedSAM3 with TVUS-derived prototype bank, we aim to align anatomically consistent feature representations across both modalities. Extensive experiments are conducted on endometriosis-related TVUS and MRI datasets. We observe quantitative and qualitative improvements of over 5 percentage points for the proposed dual-branch approach compared with multiple state-of-the-art methods. Furthermore, our ablation study shows the contribution of individual components such as the prototype bank and the importance of warm-up pretraining in the source TVUS domain.
