A Unified Framework for Joint Detection of Lacunes and Enlarged Perivascular Spaces
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910042184220672 |
|---|---|
| author | He, Lucas Li, Krinos Zhang, Hanyuan He, Runlong Ingala, Silvia Lorenzini, Luigi de Bruijne, Marleen Barkhof, Frederik Davies, Rhodri Sudre, Carole |
| author_facet | He, Lucas Li, Krinos Zhang, Hanyuan He, Runlong Ingala, Silvia Lorenzini, Luigi de Bruijne, Marleen Barkhof, Frederik Davies, Rhodri Sudre, Carole |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04243 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Unified Framework for Joint Detection of Lacunes and Enlarged Perivascular Spaces He, Lucas Li, Krinos Zhang, Hanyuan He, Runlong Ingala, Silvia Lorenzini, Luigi de Bruijne, Marleen Barkhof, Frederik Davies, Rhodri Sudre, Carole Computer Vision and Pattern Recognition 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. |
| title | A Unified Framework for Joint Detection of Lacunes and Enlarged Perivascular Spaces |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.04243 |