Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany.
Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany.
Histopathology. 2024 Jun;84(7):1139-1153. doi: 10.1111/his.15159. Epub 2024 Feb 26.
Artificial intelligence (AI) has numerous applications in pathology, supporting diagnosis and prognostication in cancer. However, most AI models are trained on highly selected data, typically one tissue slide per patient. In reality, especially for large surgical resection specimens, dozens of slides can be available for each patient. Manually sorting and labelling whole-slide images (WSIs) is a very time-consuming process, hindering the direct application of AI on the collected tissue samples from large cohorts. In this study we addressed this issue by developing a deep-learning (DL)-based method for automatic curation of large pathology datasets with several slides per patient.
We collected multiple large multicentric datasets of colorectal cancer histopathological slides from the United Kingdom (FOXTROT, N = 21,384 slides; CR07, N = 7985 slides) and Germany (DACHS, N = 3606 slides). These datasets contained multiple types of tissue slides, including bowel resection specimens, endoscopic biopsies, lymph node resections, immunohistochemistry-stained slides, and tissue microarrays. We developed, trained, and tested a deep convolutional neural network model to predict the type of slide from the slide overview (thumbnail) image. The primary statistical endpoint was the macro-averaged area under the receiver operating curve (AUROCs) for detection of the type of slide.
In the primary dataset (FOXTROT), with an AUROC of 0.995 [95% confidence interval [CI]: 0.994-0.996] the algorithm achieved a high classification performance and was able to accurately predict the type of slide from the thumbnail image alone. In the two external test cohorts (CR07, DACHS) AUROCs of 0.982 [95% CI: 0.979-0.985] and 0.875 [95% CI: 0.864-0.887] were observed, which indicates the generalizability of the trained model on unseen datasets. With a confidence threshold of 0.95, the model reached an accuracy of 94.6% (7331 classified cases) in CR07 and 85.1% (2752 classified cases) for the DACHS cohort.
Our findings show that using the low-resolution thumbnail image is sufficient to accurately classify the type of slide in digital pathology. This can support researchers to make the vast resource of existing pathology archives accessible to modern AI models with only minimal manual annotations.
人工智能（AI）在病理学中有许多应用，可支持癌症的诊断和预后。然而，大多数 AI 模型都是基于高度选择的数据进行训练的，通常每个患者只有一个组织切片。实际上，特别是对于大型手术切除标本，每个患者可能有几十个切片。手动对全切片图像（WSI）进行分类和标记是一个非常耗时的过程，这阻碍了 AI 在大型队列收集的组织样本上的直接应用。在这项研究中，我们通过开发一种基于深度学习（DL）的方法来解决这个问题，该方法用于自动整理每个患者有多个切片的大型病理学数据集。
我们从英国（FOXTROT，N=21384 张切片；CR07，N=7985 张切片）和德国（DACHS，N=3606 张切片）收集了多个大型多中心结直肠癌组织学幻灯片数据集。这些数据集包含多种类型的组织切片，包括肠切除术标本、内镜活检、淋巴结切除、免疫组织化学染色切片和组织微阵列。我们开发、训练和测试了一种深度卷积神经网络模型，以从幻灯片概述（缩略图）图像中预测幻灯片的类型。主要的统计终点是检测幻灯片类型的接收器工作特征曲线（ROC）下的面积的宏观平均值（AUROCs）。
在主要数据集（FOXTROT）中，算法的 AUROC 为 0.995[95%置信区间（CI）：0.994-0.996]，表现出较高的分类性能，并且能够仅从缩略图图像准确预测幻灯片的类型。在两个外部测试队列（CR07、DACHS）中，观察到的 AUROCs 分别为 0.982[95%CI：0.979-0.985]和 0.875[95%CI：0.864-0.887]，表明训练模型在未见数据集上具有可推广性。在置信度阈值为 0.95 时，该模型在 CR07 中达到了 94.6%（7331 个分类病例）的准确率，在 DACHS 队列中达到了 85.1%（2752 个分类病例）。
我们的研究结果表明，使用低分辨率缩略图图像足以准确分类数字病理学中的幻灯片类型。这可以支持研究人员使现有的大量病理学档案对现代 AI 模型开放，而只需进行最小限度的手动注释。
