Anomaly Detection in Medical Imaging with Deep Perceptual Autoencoders
This work addresses the challenge of detecting subtle abnormalities in medical imaging for healthcare applications, representing an incremental improvement by refining existing autoencoder methods with a more realistic training setup.
The paper tackled the problem of anomaly detection in complex medical images, such as chest X-rays and lymph node metastases, by introducing a deep perceptual autoencoder method that relaxes the fully unsupervised assumption with minimal anomaly data for hyperparameter tuning. It outperformed state-of-the-art approaches on medical datasets, establishing a new strong baseline for image anomaly detection.
Anomaly detection is the problem of recognizing abnormal inputs based on the seen examples of normal data. Despite recent advances of deep learning in recognizing image anomalies, these methods still prove incapable of handling complex medical images, such as barely visible abnormalities in chest X-rays and metastases in lymph nodes. To address this problem, we introduce a new powerful method of image anomaly detection. It relies on the classical autoencoder approach with a re-designed training pipeline to handle high-resolution, complex images and a robust way of computing an image abnormality score. We revisit the very problem statement of fully unsupervised anomaly detection, where no abnormal examples at all are provided during the model setup. We propose to relax this unrealistic assumption by using a very small number of anomalies of confined variability merely to initiate the search of hyperparameters of the model. We evaluate our solution on natural image datasets with a known benchmark, as well as on two medical datasets containing radiology and digital pathology images. The proposed approach suggests a new strong baseline for image anomaly detection and outperforms state-of-the-art approaches in complex medical image analysis tasks.