Benchmarking Deep Learning for Future Liver Remnant Segmentation in Colorectal Liver Metastasis

View PDF HTML (experimental) Abstract:Accurate segmentation of the future liver remnant (FLR) is critical for surgical planning in colorectal liver metastases (CRLM) to prevent fatal post-hepatectomy liver failure. However, this segmentation task is technically challenging due to complex resection boundaries, convoluted hepatic vasculature and diffuse metastatic lesions. A primary bottleneck in developing automated AI tools has been the lack of high-fidelity, validated data. We address this gap by manually refining all 197 volumes from the public CRLM-CT-Seg dataset, creating the first open-source, validated benchmark for this task. We then establish the first segmentation baselines, comparing cascaded (Liver->CRLM->FLR) and end-to-end (E2E) strategies using nnU-Net, SwinUNETR, and STU-Net. We find a cascaded nnU-Net achieves the best final FLR segmentation Dice (0.767), while the pretrained STU-Net provides superior CRLM segmentation (0.620 Dice) and is significantly more robust to cascaded errors. This work provides the first validated benchmark and a reproducible framework to accelerate research in AI-assisted surgical planning. Comments: Accepted at the 2026 International Symposium on Biomedical Imaging (ISBI) Oral 4-page paper presentation Subjects: Machine Learning (cs.LG) ACM classes: I.2.1 Cite as: arXiv:2604.07999 [cs.LG] (or arXiv:2604.07999v1 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2604.07999 arXiv-issued DOI via DataCite (pending registration) Submission history From: Anthony Wu [view email] [v1] Thu, 9 Apr 2026 09:05:59 UTC (1,112 KB)