Learning image representations for anomaly detection: application to discovery of histological alterations in drug development

Abstract

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.

arXiv comment18 pages, 8 figures, 6 tables

References in corpus (19)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• A Unifying Review of Deep and Shallow Anomaly Detection
• Deep neural network models for computational histopathology: A survey
• Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology
• Classifying and Segmenting Microscopy Images Using Convolutional Multiple Instance Learning
• Self-Supervised Representation Learning: Introduction, Advances and Challenges
• Learning Deep Features for One-Class Classification
• One-Class Convolutional Neural Network
• Large Batch Optimization for Deep Learning: Training BERT in 76 minutes
• Anomaly Detection in Medical Imaging with Deep Perceptual Autoencoders
• Deep Nearest Neighbor Anomaly Detection
• Student-Teacher Feature Pyramid Matching for Anomaly Detection
• Learning and Evaluating Representations for Deep One-class Classification
• Do Deep Generative Models Know What They Don't Know?
• Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection