Department of Pathology, The First Affiliated Hospital of Guangxi Medical University, Nanning, Guangxi, China.
Cancer Med. 2024 Apr;13(7):e6947. doi: 10.1002/cam4.6947.
This retrospective observational study aims to develop and validate artificial intelligence (AI) pathomics models based on pathological Hematoxylin-Eosin (HE) slides and pathological immunohistochemistry (Ki67) slides for predicting the pathological staging of colorectal cancer. The goal is to enable AI-assisted accurate pathological staging, supporting healthcare professionals in making efficient and precise staging assessments.
This study included a total of 267 colorectal cancer patients (training cohort: n = 213; testing cohort: n = 54). Logistic regression algorithms were used to construct the models. The HE image features were used to build the HE model, the Ki67 image features were used for the Ki67 model, and the combined model included features from both the HE and Ki67 images, as well as tumor markers (CEA, CA724, CA125, and CA242). The predictive results of the HE model, Ki67 model, and tumor markers were visualized through a nomogram. The models were evaluated using ROC curve analysis, and their clinical value was estimated using decision curve analysis (DCA).
A total of 260 deep learning features were extracted from HE or Ki67 images. The AUC for the HE model and Ki67 model in the training cohort was 0.885 and 0.890, and in the testing cohort, it was 0.703 and 0.767, respectively. The combined model and nomogram in the training cohort had AUC values of 0.907 and 0.926, and in the testing cohort, they had AUC values of 0.814 and 0.817. In clinical DCA, the net benefit of the Ki67 model was superior to the HE model. The combined model and nomogram showed significantly higher net benefits compared to the individual HE model or Ki67 model.
The combined model and nomogram, which integrate pathomics multi-modal data and clinical-pathological variables, demonstrated superior performance in distinguishing between Stage I-II and Stage III colorectal cancer. This provides valuable support for clinical decision-making and may improve treatment strategies and patient prognosis. Furthermore, the use of immunohistochemistry (Ki67) slides for pathomics modeling outperformed HE slide, offering new insights for future pathomics research.
本回顾性观察研究旨在开发和验证基于病理苏木精-伊红（HE）切片和病理免疫组织化学（Ki67）切片的人工智能（AI）病理组学模型，以预测结直肠癌的病理分期。目标是实现 AI 辅助的准确病理分期，为医疗保健专业人员提供高效、准确的分期评估支持。
本研究共纳入 267 例结直肠癌患者（训练队列：n=213；测试队列：n=54）。使用逻辑回归算法构建模型。使用 HE 图像特征构建 HE 模型，Ki67 图像特征构建 Ki67 模型，联合模型包含 HE 和 Ki67 图像特征以及肿瘤标志物（CEA、CA724、CA125 和 CA242）。通过列线图可视化 HE 模型、Ki67 模型和肿瘤标志物的预测结果。通过 ROC 曲线分析评估模型，并使用决策曲线分析（DCA）评估其临床价值。
从 HE 或 Ki67 图像中提取了 260 个深度学习特征。HE 模型和 Ki67 模型在训练队列中的 AUC 分别为 0.885 和 0.890，在测试队列中分别为 0.703 和 0.767。联合模型和列线图在训练队列中的 AUC 值分别为 0.907 和 0.926，在测试队列中的 AUC 值分别为 0.814 和 0.817。在临床 DCA 中，Ki67 模型的净获益优于 HE 模型。联合模型和列线图与单独的 HE 模型或 Ki67 模型相比，具有显著更高的净获益。
整合病理组学多模态数据和临床病理变量的联合模型和列线图在区分 I-II 期和 III 期结直肠癌方面表现出优异的性能。这为临床决策提供了有价值的支持，并可能改善治疗策略和患者预后。此外，免疫组织化学（Ki67）切片在病理组学建模中的应用优于 HE 切片，为未来的病理组学研究提供了新的见解。
