Zehnder Philip, Feng Jeffrey, Fuji Reina N, Sullivan Ruth, Hu Fangyao
Department of Safety Assessment, Genentech Inc., 1 DNA Way, South San Francisco, CA 94080, USA.
J Pathol Inform. 2022 May 26;13:100102. doi: 10.1016/j.jpi.2022.100102. eCollection 2022.
Automated anomaly detection is an important tool that has been developed for many real-world applications, including security systems, industrial inspection, and medical diagnostics. Despite extensive use of machine learning for anomaly detection in these varied contexts, it is challenging to generalize and apply these methods to complex tasks such as toxicologic histopathology (TOXPATH) assessment (i.e.,finding abnormalities in organ tissues). In this work, we introduce an anomaly detection method using deep learning that greatly improves model generalizability to TOXPATH data.
We evaluated a one-class classification approach that leverages novel regularization and perceptual techniques within generative adversarial network (GAN) and autoencoder architectures to accurately detect anomalous histopathological findings of varying degrees of complexity. We also utilized multiscale contextual data and conducted a thorough ablation study to demonstrate the efficacy of our method. We trained our models on data from normal whole slide images (WSIs) of rat liver sections and validated on WSIs from three anomalous classes. Anomaly scores are collated into heatmaps to localize anomalies within WSIs and provide human-interpretable results.
Our method achieves 0.953 area under the receiver operating characteristic on a real-worldTOXPATH dataset. The model also shows good performance at detecting a wide variety of anomalies demonstrating our method's ability to generalize to TOXPATH data.
Anomalies in both TOXPATH histological and non-histological datasets were accurately identified with our method, which was only trained with normal data.
自动异常检测是一种重要工具，已被开发用于许多实际应用，包括安全系统、工业检测和医学诊断。尽管机器学习在这些不同背景下被广泛用于异常检测，但将这些方法推广并应用于诸如毒理学组织病理学（TOXPATH）评估（即发现器官组织中的异常）等复杂任务仍具有挑战性。在这项工作中，我们介绍了一种使用深度学习的异常检测方法，该方法大大提高了模型对TOXPATH数据的通用性。
我们评估了一种单类分类方法，该方法在生成对抗网络（GAN）和自动编码器架构中利用新颖的正则化和感知技术，以准确检测不同程度复杂性的异常组织病理学发现。我们还利用了多尺度上下文数据并进行了全面的消融研究，以证明我们方法的有效性。我们在大鼠肝脏切片的正常全切片图像（WSIs）数据上训练模型，并在来自三个异常类别的WSIs上进行验证。异常分数被整理成热图，以在WSIs内定位异常并提供可人工解释的结果。
我们的方法在一个真实世界的TOXPATH数据集上的受试者工作特征曲线下面积达到0.953。该模型在检测各种异常方面也表现出良好的性能，证明了我们的方法能够推广到TOXPATH数据。
我们的方法仅使用正常数据进行训练，却能准确识别TOXPATH组织学和非组织学数据集中的异常。
