We present a system for anomaly detection in histopathological images. In histology, normal samples are usually abundant, whereas anomalous (pathological) cases are scarce or not available. Under such settings, one-class classifiers trained on healthy data can detect out-of-distribution anomalous samples. Such approaches combined with pre-trained Convolutional Neural Network (CNN) representations of images were previously employed for anomaly detection (AD). However, pre-trained off-the-shelf CNN representations may not be sensitive to abnormal conditions in tissues, while natural variations of healthy tissue may result in distant representations. To adapt representations to relevant details in healthy tissue we propose training a CNN on an auxiliary task that discriminates healthy tissue of different species, organs, and staining reagents. Almost no additional labeling workload is required, since healthy samples come automatically with aforementioned labels. During training we enforce compact image representations with a center-loss term, which further improves representations for AD. The proposed system outperforms established AD methods on a published dataset of liver anomalies. Moreover, it provided comparable results to conventional methods specifically tailored for quantification of liver anomalies. We show that our approach can be used for toxicity assessment of candidate drugs at early development stages and thereby may reduce expensive late-stage drug attrition.

翻译：我们提出了一种用于组织病理学图像异常检测的系统。在组织学中，正常样本通常数量充足，而异常（病理）样本则稀少或难以获取。在此条件下，基于健康数据训练的单类分类器可检测分布外异常样本。这类方法结合预训练卷积神经网络（CNN）图像表示，此前已被用于异常检测。然而，预训练的通用CNN表示可能对组织异常状况不敏感，而健康组织的自然变异可能导致表征差异过大。为使表示适应健康组织中的相关细节，我们提出在辅助任务上训练CNN，该任务需区分不同物种、器官和染色剂下的健康组织。由于健康样本可自动关联上述标签，几乎无需额外标注工作。训练过程中，我们通过中心损失项强制生成紧凑的图像表示，进一步优化了异常检测性能。在已公开的肝脏异常数据集上，所提系统优于现有异常检测方法，且与专为肝脏异常量化设计的传统方法性能相当。研究表明，该方法可用于候选药物早期开发阶段的毒性评估，从而降低后期昂贵药物研发的失败风险。