胰腺癌是一种高度恶性的癌症类型，其死亡率很高。由于此癌症类型没有明显的症状，因此大多数诊断都是在患者处于晚期时进行的。在本研究中，我们提出了一种基于对比增强 CT 图像的多实例学习的自动化方法，用于胰腺癌的有效早期诊断。在这种方法中，通过基于解剖结构的形状标准化以及实例级对比学习来改善诊断结果的稳定性和一般性。具体而言，我们开发了解剖学引导的形状标准化，通过空间变换重建胰腺感兴趣区域，考虑这些区域中更大的肿瘤部分，从而增强胰腺特征的提取。此外，我们采用实例级对比学习，将不同类型的肿瘤特征聚合到多实例学习框架中。这种学习方法可以保持肿瘤特征的完整性，并增强诊断结果的稳定性。最后，我们设计了一个平衡调整策略，以缓解肿瘤样本稀缺导致的类别不平衡问题。广泛的实验结果表明，我们的方法在内部数据集上进行交叉验证以及在两个未见数据集（一个包含316个样本的私人测试集和一个包含281个样本的公开测试集）上进行独立测试时表现出显着的性能。提出的策略也大大提高了一般性。此外，通过两个独立测试结果进一步验证了所提出方法的临床意义，其中识别直径小于2厘米的肿瘤的准确率分别为80.9%和90.1%。总的来说，我们的方法提供了一个可能成功的用于胰腺癌早期诊断的工具。我们的源代码将在 https://github.com/SJTUBME-QianLab/MIL_PAdiagnosis 上发布。版权所有© 2023 Elsevier B.V.。

Pancreatic cancer is a highly malignant cancer type with a high mortality rate. As no obvious symptoms are associated with this cancer type, most of the diagnoses are made when the patients are already in a late stage. In this work, we propose an automated method for effective early diagnosis of pancreatic cancer based on multiple instance learning with contrast-enhanced CT images. In this method, diagnosis stability and generalizability were improved through shape normalization based on anatomical structures as well as instance-level contrastive learning. Specifically, anatomically-guided shape normalization were developed to reconstruct the pancreatic regions of interest by spatial transformations, account for larger tumor parts in these regions, and hence enhance the extraction of pancreatic features. Moreover, instance-level contrastive learning was employed to aggregate different types of tumor features within the multiple instance learning framework. This learning approach can maintain the tumor feature integrity and enhance the diagnosis stability. Finally, a balance-adjustment strategy was designed to alleviate the class imbalance problem caused by the scarcity of tumor samples. Extensive experimental results demonstrated remarkable performance of our method when conducted cross-validation on an in-house dataset with 310 patients and independent test on two unseen datasets (a private test set with 316 and a publicly-available test set with 281). The proposed strategies also led to significant improvements in generalizability. Besides, the clinical significance of the proposed method was further verified through two independent test results in which tumors smaller than 2 cm in diameter were identified at accuracies of 80.9% and 90.1%, respectively. Overall, our method provides a potentially successful tool for early diagnosis of pancreatic cancer. Our source codes will be released at https://github.com/SJTUBME-QianLab/MIL_PAdiagnosis.Copyright © 2023 Elsevier B.V. All rights reserved.