SynLiTS: Phase Prompting-Driven Diffusion Synthesis and Context-Aware Fusion for Unaligned Liver Tumor Segmentation
IEEE Transactions on Medical Imaging · 2026-06 · 45 (6) · 2795-2808
DOI: 10.1109/tmi.2026.3663583 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2026-06. Verfasst von Shiyun Chen und 7 weiteren Autor:innen. Hauptthemen laut MEDLINE: Liver Neoplasms, Tomography, X-Ray Computed, Radiographic Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research.
Abstract (Originalsprache)
Given the rich and complementary information contained in multi-phase CT images (CTs), they play an indispensable role in liver cancer diagnosis and prognosis, wherein an important prerequisite is liver tumor segmentation. However, spatial misalignments across phases and the limited availability of high-quality multi-phase CT datasets significantly hinder the performance of liver tumor segmentation. To tackle these challenges, we here propose SynLiTS, a novel multi-phase liver tumor segmentation framework. Its core idea is to synthesize multi-phase CTs with strictly-aligned liver tumors based on pseudo-normal multi-phase CTs. Specifically, an FFC-based Inpainter is first designed to generate pseudo-normal CTs by reconstructing dilated liver tumors. The pseudo-normal CTs and randomly generated tumor masks are then combined via a phase prompting-driven diffusion model to synthesize multi-phase liver tumor CTs with diverse tumor characteristics. In this way, multi-phase CTs with perfectly-aligned liver tumor labels are obtained. We also construct a real multi-phase liver tumor dataset, named MPLiTS. Finally, the synthesized and real multi-phase CTs are used to train a liver tumor segmentation model, which incorporates a context-aware fusion module to effectively learn and integrate multi-phase information. SynLiTS is evaluated on both internal and external datasets, and the results show that it outperforms state-of-the-art methods by large margins. Code will be released at https://github.com/Chyiun/SynLiTS.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Guangdong Basic and Applied Basic Research
- High Level of Special Funds
- Guangdong Key Research and Development Program
- SUSTech Fang Keng Faculty
Zitieren
APA
Chen, S., Lin, L., Jin, Z., Cheng, P., Chen, J., Zhu, H., Wong, K. K. Y., & Tang, X. (2026). SynLiTS: Phase Prompting-Driven Diffusion Synthesis and Context-Aware Fusion for Unaligned Liver Tumor Segmentation. IEEE Transactions on Medical Imaging, 45(6), 2795-2808. https://doi.org/10.1109/tmi.2026.3663583
Vancouver
Chen S, Lin L, Jin Z, Cheng P, Chen J, Zhu H, et al. SynLiTS: Phase Prompting-Driven Diffusion Synthesis and Context-Aware Fusion for Unaligned Liver Tumor Segmentation. IEEE Transactions on Medical Imaging. 2026;45(6):2795-2808. doi:10.1109/tmi.2026.3663583
BibTeX
@article{Chen2026,
author = {Chen, Shiyun and Lin, Li and Jin, Zhicheng and Cheng, Pujin and Chen, Jianjian and Zhu, Haidong and Wong, Kenneth K Y and Tang, Xiaoying},
title = {SynLiTS: Phase Prompting-Driven Diffusion Synthesis and Context-Aware Fusion for Unaligned Liver Tumor Segmentation},
journal = {IEEE Transactions on Medical Imaging},
year = {2026},
volume = {45},
number = {6},
pages = {2795--2808},
doi = {10.1109/tmi.2026.3663583}
}
EUVIMED