Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET
This work addresses the challenge of validating anomaly detection methods in medical imaging without ground truth data, which is incremental as it builds on existing pseudo-healthy reconstruction approaches.
The paper tackles the problem of evaluating pseudo-healthy image reconstruction methods for unsupervised anomaly detection in medical imaging, proposing a simulation-based evaluation procedure when ground truth lesion masks are unavailable, and applies it to 3D brain FDG PET for early detection of dementia markers like Alzheimer's disease, achieving validation without clinician input.
Over the past years, pseudo-healthy reconstruction for unsupervised anomaly detection has gained in popularity. This approach has the great advantage of not requiring tedious pixel-wise data annotation and offers possibility to generalize to any kind of anomalies, including that corresponding to rare diseases. By training a deep generative model with only images from healthy subjects, the model will learn to reconstruct pseudo-healthy images. This pseudo-healthy reconstruction is then compared to the input to detect and localize anomalies. The evaluation of such methods often relies on a ground truth lesion mask that is available for test data, which may not exist depending on the application. We propose an evaluation procedure based on the simulation of realistic abnormal images to validate pseudo-healthy reconstruction methods when no ground truth is available. This allows us to extensively test generative models on different kinds of anomalies and measuring their performance using the pair of normal and abnormal images corresponding to the same subject. It can be used as a preliminary automatic step to validate the capacity of a generative model to reconstruct pseudo-healthy images, before a more advanced validation step that would require clinician's expertise. We apply this framework to the reconstruction of 3D brain FDG PET using a convolutional variational autoencoder with the aim to detect as early as possible the neurodegeneration markers that are specific to dementia such as Alzheimer's disease.