Medical image anomaly detection improved with quasi-binarized autoencoders
Quasi-Binarized Autoencoders: An Architecture-Independent Information Bottleneck for Medical Image Anomaly Detection
Computer Vision and Pattern Recognition
Summary
Detecting unusual features in medical images is important but hard when only normal images are available for training. The authors introduce a method called quasi-binarized autoencoders that limits how much information passes through the network, preventing it from just copying the image and missing anomalies. Their approach uses a special layer that controls information flow mathematically and adds noise to improve detection. Tested on multiple medical datasets, this method performed better than others that use a fixed design for all data.
What this means in practice
- •For medical image analysts: Enhance unsupervised detection of anomalies in diverse medical imaging datasets using a stable, architecture-independent model.
- •For computer vision engineers: Implement tighter control of information flow in encoder-decoder networks to prevent identity mapping in anomaly detection tasks.
Authors
Shouhei Hanaoka, Takahiro Nakao, Atsushi Takamatsu, Takeharu Yoshikawa, Osamu Abe
Abstract
Unsupervised anomaly detection, which learns only from normal images, is a central task in medical image analysis and remains an open problem. Reconstruction-based methods pass an image through an encoder-decoder network trained on normal data and detect anomalies from the residual between the image and its reconstruction. This works only if the information passed from the encoder to the decoder is limited; otherwise the network learns an identity mapping and reconstructs anomalies too. This limit is usually imposed through architectural choices, tuned per dataset, that cannot be stated in bits. We introduce the quasi-binarizing (QB) layer, which squashes each latent element into [0, 1] and adds Laplace noise of scale 1/epsilon. Each element is then epsilon-locally differentially private, and the mutual information between an image and its reconstruction is bounded by a quantity that depends only on epsilon and the number of QB elements, whatever the encoder and decoder. Placing a QB layer on every encoder-decoder path, including all skip connections, we build QBAE, a seven-level attention U-Net with 32,768 QB elements. On the seven datasets of the MedIAnomaly benchmark, QBAE with one architecture and one configuration reaches a mean image-level AUROC of 0.828, the highest among methods that do not adapt to each dataset, and the best reported results on BraTS2021 (AUROC 0.911, pixel-level AP 0.838). The noise is kept at test time, so that every reconstruction satisfies the bound. Without input corruption, the bottleneck alone prevents identity collapse (mean AUROC 0.805 vs. 0.590). Code is available at https://github.com/hanaokalog/MedIAnomalyQB.