Benchmarking Deep Learning for Future Liver Remnant Segmentation in Colorectal Liver Metastasis
This work addresses a critical need for high-fidelity data and benchmarks in AI-assisted surgical planning for colorectal liver metastases, though it is incremental as it builds on existing methods.
The authors tackled the problem of segmenting the future liver remnant for surgical planning in colorectal liver metastases by creating the first open-source, validated benchmark from 197 volumes and establishing segmentation baselines, with a cascaded nnU-Net achieving a Dice score of 0.767 for FLR segmentation.
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.