Anatomically-guided masked autoencoder pre-training for aneurysm detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910850967666688 |
|---|---|
| author | Ceballos-Arroyo, Alberto Mario Kim, Jisoo Lin, Chu-Hsuan Qin, Lei Young, Geoffrey S. Jiang, Huaizu |
| author_facet | Ceballos-Arroyo, Alberto Mario Kim, Jisoo Lin, Chu-Hsuan Qin, Lei Young, Geoffrey S. Jiang, Huaizu |
| contents | Intracranial aneurysms are a major cause of morbidity and mortality worldwide, and detecting them manually is a complex, time-consuming task. Albeit automated solutions are desirable, the limited availability of training data makes it difficult to develop such solutions using typical supervised learning frameworks. In this work, we propose a novel pre-training strategy using more widely available unannotated head CT scan data to pre-train a 3D Vision Transformer model prior to fine-tuning for the aneurysm detection task. Specifically, we modify masked auto-encoder (MAE) pre-training in the following ways: we use a factorized self-attention mechanism to make 3D attention computationally viable, we restrict the masked patches to areas near arteries to focus on areas where aneurysms are likely to occur, and we reconstruct not only CT scan intensity values but also artery distance maps, which describe the distance between each voxel and the closest artery, thereby enhancing the backbone's learned representations. Compared with SOTA aneurysm detection models, our approach gains +4-8% absolute Sensitivity at a false positive rate of 0.5. Code and weights will be released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_21244 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Anatomically-guided masked autoencoder pre-training for aneurysm detection Ceballos-Arroyo, Alberto Mario Kim, Jisoo Lin, Chu-Hsuan Qin, Lei Young, Geoffrey S. Jiang, Huaizu Computer Vision and Pattern Recognition Intracranial aneurysms are a major cause of morbidity and mortality worldwide, and detecting them manually is a complex, time-consuming task. Albeit automated solutions are desirable, the limited availability of training data makes it difficult to develop such solutions using typical supervised learning frameworks. In this work, we propose a novel pre-training strategy using more widely available unannotated head CT scan data to pre-train a 3D Vision Transformer model prior to fine-tuning for the aneurysm detection task. Specifically, we modify masked auto-encoder (MAE) pre-training in the following ways: we use a factorized self-attention mechanism to make 3D attention computationally viable, we restrict the masked patches to areas near arteries to focus on areas where aneurysms are likely to occur, and we reconstruct not only CT scan intensity values but also artery distance maps, which describe the distance between each voxel and the closest artery, thereby enhancing the backbone's learned representations. Compared with SOTA aneurysm detection models, our approach gains +4-8% absolute Sensitivity at a false positive rate of 0.5. Code and weights will be released. |
| title | Anatomically-guided masked autoencoder pre-training for aneurysm detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.21244 |