AREPAS: Anomaly Detection in Fine-Grained Anatomy with Reconstruction-Based Semantic Patch-Scoring
This work addresses anomaly detection for medical imaging, particularly in infectious disease and stroke lesion segmentation, but it is incremental as it builds on existing reconstruction-based methods with specific improvements.
The paper tackled the challenge of anomaly detection in fine-grained anatomy, such as pulmonary tissue, by proposing a generative approach with reconstruction and patch similarity scoring, resulting in improved pixel-level segmentation with relative DICE score gains of +1.9% in chest CTs and +4.4% in brain MRIs compared to state-of-the-art methods.
Early detection of newly emerging diseases, lesion severity assessment, differentiation of medical conditions and automated screening are examples for the wide applicability and importance of anomaly detection (AD) and unsupervised segmentation in medicine. Normal fine-grained tissue variability such as present in pulmonary anatomy is a major challenge for existing generative AD methods. Here, we propose a novel generative AD approach addressing this issue. It consists of an image-to-image translation for anomaly-free reconstruction and a subsequent patch similarity scoring between observed and generated image-pairs for precise anomaly localization. We validate the new method on chest computed tomography (CT) scans for the detection and segmentation of infectious disease lesions. To assess generalizability, we evaluate the method on an ischemic stroke lesion segmentation task in T1-weighted brain MRI. Results show improved pixel-level anomaly segmentation in both chest CTs and brain MRIs, with relative DICE score improvements of +1.9% and +4.4%, respectively, compared to other state-of-the-art reconstruction-based methods.