首个非增强CT肝病变分割基准，助力低资源地区AI辅助诊断。
TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT
- 构建多中心150例四期CT数据集，支持非增强CT分割挑战赛。
- 顶尖模型在非增强CT上Dice仅0.57，远低于增强相（0.754）。
- 数据量与预训练策略是性能关键，单纯扩大预训练无效。
非增强计算机断层扫描（NCCT）中肝病变的自动分割在临床中至关重要，但在非洲和亚洲等资源匮乏地区因造影剂稀缺而面临挑战。进展受限于缺乏标注的NCCT基准数据集。本文提出针对造影剂受限条件下肝病变分割的TriALS挑战，基于埃及与中国的多中心数据集，包含150例患者、四期CT扫描共600个体积数据。算法在来自三家机构的70例数据上评估，包括独立外部队列。最佳方法在门静脉期平均Dice达0.754，接近人工水平，但在NCCT上下降至0.57。外部验证显示，领先方法在NCCT上比现成模型最高提升28% Dice。算法性能主要受训练数据规模和预训练策略影响。跨年比较揭示了仅靠扩大预训练无法克服的显著感知障碍。数据、标注与代码已公开于https://github.com/xmed-lab/TriALS。
原文摘要 · Abstract (English)
Automated segmentation of liver lesions on non-contrast computed tomography (NCCT) is clinically important but fundamentally challenging, particularly in low-resource settings across Africa and Asia where contrast agents are frequently unavailable. Progress has been limited by the absence of annotated NCCT benchmarks. Here we describe the TriALS challenge for automated liver lesion segmentation under contrast-limited conditions, supported by a multi-centre dataset of 150 cases with four-phase CT acquisitions (600 volumes) from Egyptian and Chinese institutions. Algorithms were evaluated on 70 cases from three institutions, including an independent external cohort. The top-performing method achieved a mean venous-phase Dice of 0.754, consistent with human-level performance, yet dropped to 0.57 on NCCT. On external validation, the leading method outperformed off-the-shelf models by up to 28% in Dice on NCCT. Algorithm performance was most strongly predicted by training data scale and pre-training strategy. A cross-year comparison exposed a persistent perceptual barrier on NCCT that scaling pre-training alone cannot overcome. Data, annotations, and code are available at https://github.com/xmed-lab/TriALS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。