Registration-Enhanced Segmentation Method for Prostate Cancer in Ultrasound Images
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910808808620032 |
|---|---|
| author | Sang, Shengtian Jahanandish, Hassan Li, Cynthia Xinran Bhattachary, Indrani Lee, Jeong Hoon Zhang, Lichun Vesal, Sulaiman Ghanouni, Pejman Fan, Richard Sonn, Geoffrey A. Rusu, Mirabela |
| author_facet | Sang, Shengtian Jahanandish, Hassan Li, Cynthia Xinran Bhattachary, Indrani Lee, Jeong Hoon Zhang, Lichun Vesal, Sulaiman Ghanouni, Pejman Fan, Richard Sonn, Geoffrey A. Rusu, Mirabela |
| contents | Prostate cancer is a major cause of cancer-related deaths in men, where early detection greatly improves survival rates. Although MRI-TRUS fusion biopsy offers superior accuracy by combining MRI's detailed visualization with TRUS's real-time guidance, it is a complex and time-intensive procedure that relies heavily on manual annotations, leading to potential errors. To address these challenges, we propose a fully automatic MRI-TRUS fusion-based segmentation method that identifies prostate tumors directly in TRUS images without requiring manual annotations. Unlike traditional multimodal fusion approaches that rely on naive data concatenation, our method integrates a registration-segmentation framework to align and leverage spatial information between MRI and TRUS modalities. This alignment enhances segmentation accuracy and reduces reliance on manual effort. Our approach was validated on a dataset of 1,747 patients from Stanford Hospital, achieving an average Dice coefficient of 0.212, outperforming TRUS-only (0.117) and naive MRI-TRUS fusion (0.132) methods, with significant improvements (p $<$ 0.01). This framework demonstrates the potential for reducing the complexity of prostate cancer diagnosis and provides a flexible architecture applicable to other multimodal medical imaging tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00712 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Registration-Enhanced Segmentation Method for Prostate Cancer in Ultrasound Images Sang, Shengtian Jahanandish, Hassan Li, Cynthia Xinran Bhattachary, Indrani Lee, Jeong Hoon Zhang, Lichun Vesal, Sulaiman Ghanouni, Pejman Fan, Richard Sonn, Geoffrey A. Rusu, Mirabela Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Prostate cancer is a major cause of cancer-related deaths in men, where early detection greatly improves survival rates. Although MRI-TRUS fusion biopsy offers superior accuracy by combining MRI's detailed visualization with TRUS's real-time guidance, it is a complex and time-intensive procedure that relies heavily on manual annotations, leading to potential errors. To address these challenges, we propose a fully automatic MRI-TRUS fusion-based segmentation method that identifies prostate tumors directly in TRUS images without requiring manual annotations. Unlike traditional multimodal fusion approaches that rely on naive data concatenation, our method integrates a registration-segmentation framework to align and leverage spatial information between MRI and TRUS modalities. This alignment enhances segmentation accuracy and reduces reliance on manual effort. Our approach was validated on a dataset of 1,747 patients from Stanford Hospital, achieving an average Dice coefficient of 0.212, outperforming TRUS-only (0.117) and naive MRI-TRUS fusion (0.132) methods, with significant improvements (p $<$ 0.01). This framework demonstrates the potential for reducing the complexity of prostate cancer diagnosis and provides a flexible architecture applicable to other multimodal medical imaging tasks. |
| title | Registration-Enhanced Segmentation Method for Prostate Cancer in Ultrasound Images |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.00712 |