A Unified Framework for Joint Detection of Lacunes and Enlarged Perivascular Spaces
This work provides a more accurate and robust method for detecting cerebral small vessel disease markers, which is crucial for large-scale population studies and clinical diagnosis.
This paper addresses the challenge of simultaneously detecting lacunes and enlarged perivascular spaces (EPVS) in medical images, which often mimic each other. The proposed framework achieved state-of-the-art performance on the VALDO 2021 dataset, with a lacunae detection precision of 71.1% and an F1-score of 62.6%, outperforming previous task winners.
Cerebral small vessel disease (CSVD) markers, specifically enlarged perivascular spaces (EPVS) and lacunae, present a unique challenge in medical image analysis due to their radiological mimicry. Standard segmentation networks struggle with feature interference and extreme class imbalance when handling these divergent targets simultaneously. To address these issues, we propose a morphology-decoupled framework where Zero-Initialized Gated Cross-Task Attention exploits dense EPVS context to guide sparse lacune detection. Furthermore, biological and topological consistency are enforced via a mixed-supervision strategy integrating Mutual Exclusion and Centerline Dice losses. Finally, we introduce an Anatomically-Informed Inference Calibration mechanism to dynamically suppress false positives based on tissue semantics. Extensive 5-folds cross-validation on the VALDO 2021 dataset (N=40) demonstrates state-of-the-art performance, notably surpassing task winners in lacunae detection precision (71.1%, p=0.01) and F1-score (62.6%, p=0.03). Furthermore, evaluation on the external EPAD cohort (N=1762) confirms the model's robustness for large-scale population studies. Code will be released upon acceptance.