Purpose In this study, we address the problem of automatic liver resection planning for major surgical procedures, including hemi-hepatectomy and extended hemi-hepatectomy, using deep learning. Motivated by clinical practice, where Couinaud liver segments are routinely used to describe tumor location and guide surgical decision-making, we investigate whether incorporating this anatomical information can improve model performance and clinical relevance. Methods We propose a point cloud-based geometric deep learning approach based on a modified RandLA-Net architecture to predict liver resection zones. The model was trained and evaluated on 70 hemi-hepatectomy cases from Johannes Gutenberg University, Mainz, Germany (internal dataset). Two composite loss functions were evaluated: cross-entropy (CE) combined with intersection over union (IoU) and CE combined with Dice loss. For each loss function, models were trained with and without Couinaud segment information. Generalizability was assessed on an external dataset of 30 hemi-hepatectomy cases from the colorectal liver metastases (CRLM) cohort. Results Both loss functions achieved comparable performance across the evaluated datasets, with CE <InlineEquation ID="IEq1"> <EquationSource Format="TEX">$+$</EquationSource> <EquationSource Format="MATHML"><math> <mo>+</mo> </math></EquationSource> </InlineEquation> IoU consistently outperforming CE <InlineEquation ID="IEq2"> <EquationSource Format="TEX">$+$</EquationSource> <EquationSource Format="MATHML"><math> <mo>+</mo> </math></EquationSource> </InlineEquation> Dice. On the internal test set, incorporating Couinaud segment information increased the IoUmean from 0.787 to 0.804 and the F1-score from 0.864 to 0.870. A Wilcoxon signed-rank test on 15 paired cases confirmed a statistically significant improvement in IoUmean (p = 0.030), with 80% of cases showing improvement. On the external dataset, IoUmean improved from 0.666 to 0.702 and F1-score from 0.786 to 0.799 when Couinaud information was included. Excluding five anatomically complex cases, a Wilcoxon signed-rank test on the remaining 25 paired cases showed a significant improvement in IoUmean (p = 0.019), with 68% of cases demonstrating improved performance. Conclusion Explicit integration of Couinaud segment information improves both quantitative performance and clinical relevance in automatic major liver resection planning, particularly by better preserving critical vascular structures.

Couinaud segment-aware deep learning on point clouds for major liver resection planning

期刊论文
出版模式：

开放获取
发表日期：

2026年5月8日

查看全文

Joy Rakshit,
Janine Rothert,
Georg Hille,
Tobias Huber,
Hauke Lang,
Rabea Margies,
Florentine Huettl,
Sylvia Saalfeld

摘要

Purpose

In this study, we address the problem of automatic liver resection planning for major surgical procedures, including hemi-hepatectomy and extended hemi-hepatectomy, using deep learning. Motivated by clinical practice, where Couinaud liver segments are routinely used to describe tumor location and guide surgical decision-making, we investigate whether incorporating this anatomical information can improve model performance and clinical relevance.

Methods

We propose a point cloud-based geometric deep learning approach based on a modified RandLA-Net architecture to predict liver resection zones. The model was trained and evaluated on 70 hemi-hepatectomy cases from Johannes Gutenberg University, Mainz, Germany (internal dataset). Two composite loss functions were evaluated: cross-entropy (CE) combined with intersection over union (IoU) and CE combined with Dice loss. For each loss function, models were trained with and without Couinaud segment information. Generalizability was assessed on an external dataset of 30 hemi-hepatectomy cases from the colorectal liver metastases (CRLM) cohort.

Results

Both loss functions achieved comparable performance across the evaluated datasets, with CE $+$ $+$ IoU consistently outperforming CE $+$ $+$ Dice. On the internal test set, incorporating Couinaud segment information increased the IoU_mean from 0.787 to 0.804 and the F1-score from 0.864 to 0.870. A Wilcoxon signed-rank test on 15 paired cases confirmed a statistically significant improvement in IoU_mean (p = 0.030), with 80% of cases showing improvement. On the external dataset, IoU_mean improved from 0.666 to 0.702 and F1-score from 0.786 to 0.799 when Couinaud information was included. Excluding five anatomically complex cases, a Wilcoxon signed-rank test on the remaining 25 paired cases showed a significant improvement in IoU_mean (p = 0.019), with 68% of cases demonstrating improved performance.

Conclusion

Explicit integration of Couinaud segment information improves both quantitative performance and clinical relevance in automatic major liver resection planning, particularly by better preserving critical vascular structures.