Label-Efficient Cross-Modality Generalization for Liver Segmentation in Multi-Phase MRI
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918444613500928 |
|---|---|
| author | Bui-Tran, Quang-Khai Dinh, Minh-Toan Nguyen, Thanh-Huy Lam, Ba-Thinh Vu, Mai-Anh Bagci, Ulas |
| author_facet | Bui-Tran, Quang-Khai Dinh, Minh-Toan Nguyen, Thanh-Huy Lam, Ba-Thinh Vu, Mai-Anh Bagci, Ulas |
| contents | Accurate liver segmentation in multi-phase MRI is vital for liver fibrosis assessment, yet labeled data is often scarce and unevenly distributed across imaging modalities and vendor systems. We propose a label-efficient segmentation approach that promotes cross-modality generalization under real-world conditions, where GED4 hepatobiliary-phase annotations are limited, non-contrast sequences (T1WI, T2WI, DWI) are unlabeled, and spatial misalignment and missing phases are common. Our method integrates a foundation-scale 3D segmentation backbone adapted via fine-tuning, co-training with cross pseudo supervision to leverage unlabeled volumes, and a standardized preprocessing pipeline. Without requiring spatial registration, the model learns to generalize across MRI phases and vendors, demonstrating robust segmentation performance in both labeled and unlabeled domains. Our results exhibit the effectiveness of our proposed label-efficient baseline for liver segmentation in multi-phase, multi-vendor MRI and highlight the potential of combining foundation model adaptation with co-training for real-world clinical imaging tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04705 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Label-Efficient Cross-Modality Generalization for Liver Segmentation in Multi-Phase MRI Bui-Tran, Quang-Khai Dinh, Minh-Toan Nguyen, Thanh-Huy Lam, Ba-Thinh Vu, Mai-Anh Bagci, Ulas Computer Vision and Pattern Recognition Accurate liver segmentation in multi-phase MRI is vital for liver fibrosis assessment, yet labeled data is often scarce and unevenly distributed across imaging modalities and vendor systems. We propose a label-efficient segmentation approach that promotes cross-modality generalization under real-world conditions, where GED4 hepatobiliary-phase annotations are limited, non-contrast sequences (T1WI, T2WI, DWI) are unlabeled, and spatial misalignment and missing phases are common. Our method integrates a foundation-scale 3D segmentation backbone adapted via fine-tuning, co-training with cross pseudo supervision to leverage unlabeled volumes, and a standardized preprocessing pipeline. Without requiring spatial registration, the model learns to generalize across MRI phases and vendors, demonstrating robust segmentation performance in both labeled and unlabeled domains. Our results exhibit the effectiveness of our proposed label-efficient baseline for liver segmentation in multi-phase, multi-vendor MRI and highlight the potential of combining foundation model adaptation with co-training for real-world clinical imaging tasks. |
| title | Label-Efficient Cross-Modality Generalization for Liver Segmentation in Multi-Phase MRI |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.04705 |