AI辅助早期发现胰腺癌，提升CT影像判读精度
PanDx: AI-assisted Early Detection of Pancreatic Ductal Adenocarcinoma on Contrast-enhanced CT
- 分层集成+峰值增强定位，提升模型泛化与定位能力
- 在挑战赛中达0.9263的AUROC，领先第二名超10个百分点
- 适合临床医生做影像筛查辅助，也供医学AI研究参考
胰腺导管腺癌（PDAC）是侵袭性极强的胰腺癌类型，常因早期影像征象微弱而延误诊断。为实现更早检测并支持临床决策，我们提出一种粗到细的AI辅助框架PanDx，用于识别增强CT上的PDAC。该方法融合两项新技术：(1) 分布感知的分层集成，提升对病灶变异的泛化能力；(2) 峰值缩放的病灶候选提取，增强定位精度。PanDx作为PANORAMA挑战赛的一部分进行开发与评估，在官方测试集上取得0.9263的AUROC和0.7243的AP，位列第一。我们还联合放射科医生分析失败案例，揭示当前AI模型在此任务中的局限，并探讨未来改进方向。代码与模型已公开于https://github.com/han-liu/PanDx。
原文摘要 · Abstract (English)
Pancreatic ductal adenocarcinoma (PDAC) is one of the most aggressive forms of pancreatic cancer and is often diagnosed at an advanced stage due to subtle early imaging signs. To enable earlier detection and improve clinical decision-making, we propose a coarse-to-fine AI-assisted framework named PanDx for identifying PDAC on contrast-enhanced CT scans. Our approach integrates two novel techniques: (1) distribution-aware stratified ensembling to improve generalization across lesion variations, and (2) peak-scaled lesion candidate extraction to enhance lesion localization precision. PanDx is developed and evaluated as part of the PANORAMA challenge, where it ranked 1st place on the official test set with an AUROC of 0.9263 and an AP of 0.7243. Furthermore, we analyzed failure cases with a radiologist to identify the limitations of AI models on this task and discussed potential future directions for model improvement. Our code and models are publicly available at https://github.com/han-liu/PanDx.
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。