Departments of Surgery.
Pathology, Amsterdam UMC, location University of Amsterdam.
Am J Surg Pathol. 2024 Sep 1;48(9):1108-1116. doi: 10.1097/PAS.0000000000002270. Epub 2024 Jul 2.
Neoadjuvant therapy (NAT) has become routine in patients with borderline resectable pancreatic cancer. Pathologists examine pancreatic cancer resection specimens to evaluate the effect of NAT. However, an automated scoring system to objectively quantify residual pancreatic cancer (RPC) is currently lacking. Herein, we developed and validated the first automated segmentation model using artificial intelligence techniques to objectively quantify RPC. Digitized histopathological tissue slides were included from resected pancreatic cancer specimens from 14 centers in 7 countries in Europe, North America, Australia, and Asia. Four different scanner types were used: Philips (56%), Hamamatsu (27%), 3DHistech (10%), and Leica (7%). Regions of interest were annotated and classified as cancer, non-neoplastic pancreatic ducts, and others. A U-Net model was trained to detect RPC. Validation consisted of by-scanner internal-external cross-validation. Overall, 528 unique hematoxylin and eosin (H & E) slides from 528 patients were included. In the individual Philips, Hamamatsu, 3DHistech, and Leica scanner cross-validations, mean F1 scores of 0.81 (95% CI, 0.77-0.84), 0.80 (0.78-0.83), 0.76 (0.65-0.78), and 0.71 (0.65-0.78) were achieved, respectively. In the meta-analysis of the cross-validations, the mean F1 score was 0.78 (0.71-0.84). A final model was trained on the entire data set. This ISGPP model is the first segmentation model using artificial intelligence techniques to objectively quantify RPC following NAT. The internally-externally cross-validated model in this study demonstrated robust performance in detecting RPC in specimens. The ISGPP model, now made publically available, enables automated RPC segmentation and forms the basis for objective NAT response evaluation in pancreatic cancer.
新辅助治疗（NAT）已成为边界可切除胰腺癌患者的常规治疗方法。病理学家检查胰腺癌切除标本以评估 NAT 的效果。然而，目前缺乏一种用于客观量化残余胰腺癌（RPC）的自动评分系统。在此，我们使用人工智能技术开发并验证了第一个用于客观量化 RPC 的自动分割模型。纳入了来自欧洲、北美、澳大利亚和亚洲 7 个国家的 14 个中心的切除胰腺癌标本的数字化组织学组织切片。使用了四种不同的扫描仪类型：飞利浦（56%）、滨松（27%）、3DHistech（10%）和徕卡（7%）。标记了感兴趣的区域，并将其分类为癌症、非肿瘤性胰腺导管和其他。使用 U-Net 模型来检测 RPC。验证包括按扫描仪进行的内部-外部交叉验证。总共纳入了 528 名患者的 528 个独特的苏木精和伊红（H&E）切片。在单独的飞利浦、滨松、3DHistech 和徕卡扫描仪交叉验证中，分别获得了 0.81（95%CI，0.77-0.84）、0.80（0.78-0.83）、0.76（0.65-0.78）和 0.71（0.65-0.78）的平均 F1 评分。在交叉验证的荟萃分析中，平均 F1 得分为 0.78（0.71-0.84）。最终模型是在整个数据集上训练的。该 ISGPP 模型是第一个使用人工智能技术客观量化 NAT 后 RPC 的分割模型。本研究中内部-外部交叉验证模型在检测标本中的 RPC 方面表现出稳健的性能。现在公开提供的 ISGPP 模型支持自动 RPC 分割，并为胰腺癌的客观 NAT 反应评估奠定了基础。
