Anomaly Detection using Generative Models and Sum-Product Networks in Mammography Scans
This work addresses the challenge of detecting anomalies in medical imaging without extensive annotations, which is crucial for improving diagnostic efficiency in healthcare, though it appears incremental as it builds on existing autoencoder and generative model techniques.
The paper tackled the problem of unsupervised anomaly detection in mammography scans by proposing a novel combination of generative models and probabilistic graphical models, achieving superior performance over standalone models and state-of-the-art methods in medical data anomaly detection.
Unsupervised anomaly detection models which are trained solely by healthy data, have gained importance in the recent years, as the annotation of medical data is a tedious task. Autoencoders and generative adversarial networks are the standard anomaly detection methods that are utilized to learn the data distribution. However, they fall short when it comes to inference and evaluation of the likelihood of test samples. We propose a novel combination of generative models and a probabilistic graphical model. After encoding image samples by autoencoders, the distribution of data is modeled by Random and Tensorized Sum-Product Networks ensuring exact and efficient inference at test time. We evaluate different autoencoder architectures in combination with Random and Tensorized Sum-Product Networks on mammography images using patch-wise processing and observe superior performance over utilizing the models standalone and state-of-the-art in anomaly detection for medical data.