TRIUNE-Net：在胰腺肿瘤分割中协调尺度、形状与效率

中文摘要 AI 辅助

三维CT图像中的胰腺肿瘤分割面临胰腺和肿瘤极端尺度变异性以及高度不规则的肿瘤形态的挑战。尽管近期研究推动了分割性能的提升，但现有方法并未明确解决这些挑战，且以过高的计算复杂度为代价，限制了其在资源受限的临床环境中的实用性。我们提出TRIUNE-Net，一种轻量级统一架构，通过三项协同创新来协调尺度、形状和效率。多尺度上下文聚合模块采用阶段自适应膨胀卷积，使模型能够推理两个器官中存在的广泛解剖尺度范围。串行线性可变形注意力机制将大的有效感受野与形状自适应可变形卷积相结合，以捕捉不规则的非凸肿瘤形态。最后，信息保留下采样模块完全替代传统最大池化，保留所有空间信息的同时增加可忽略的参数，防止小肿瘤在识别前被丢弃。在MSD胰腺和NVD胰腺数据集上，TRIUNE-Net仅用5.86M参数且无外部预训练即达到最先进结果，在所有关键肿瘤指标上优于所有基线。具体而言，它在肿瘤Dice上超过次优模型0.45%，F1分数高6.0分，灵敏度高6.6分，精确率高3.4分，同时反映了其在临床现实条件下抑制漏检肿瘤和误报的能力。我们的代码可在以下网址获取：this https URL

英文摘要

Pancreatic tumor segmentation in 3D CT volumes is challenged by extreme scale variability across both the pancreas and tumor, and highly irregular tumor morphology. While recent advances have pushed segmentation performance, existing methods do not explicitly address these challenges and come at the cost of excessive computational complexity, limiting their practicality in resource-constrained clinical environments. We propose TRIUNE-Net, a lightweight unified architecture that harmonizes scale, shape, and efficiency through three synergistic innovations. A multi-scale context aggregation module with stage-adaptive dilated convolutions enables the model to reason across the broad range of anatomical scales present in both organs. A serial linear-deformable attention mechanism combines large effective receptive fields with shapeadaptive deformable convolutions to capture irregular, non-convex tumor morphologies. Finally, an information-preserving downsampling module replaces conventional max pooling entirely, retaining all spatial information while adding negligible parameters, preventing small tumors from being discarded before they can be recognized. On both the MSD Pancreas and NVD Pancreas datasets, TRIUNE-Net achieves state-of-theart results with only 5.86 M parameters and no external pre-training, outperforming all baselines across all key tumor metrics. Specifically, it surpasses the next-best model by 0.45% in tumor Dice, 6.0 points in F1 score, 6.6 points in sensitivity, and 3.4 points in precision, simultaneously reflecting its ability to suppress both missed tumors and false alarms in clinically realistic conditions. Our code is available at: https://github.com/abdora-ai/TRIUNE-Net

发表机构

• University of Regensburg（雷根斯堡大学）
• University of California, San Francisco（加利福尼亚大学旧金山分校）
• Northwestern University（西北大学）
• Abdora INC（阿卜多拉公司）

机构由 AI 辅助整理，请以论文原文为准。