Anatomically-guided Masked Autoencoder with Domain-Adaptive Prompting (AMAP) for multimodal cerebral aneurysm detection and segmentation - Takeaways - MDSpire

Anatomically-guided Masked Autoencoder with Domain-Adaptive Prompting (AMAP) for multimodal cerebral aneurysm detection and segmentation

  • By

  • Mingxuan Huang

  • Tiantian Liu

  • Jiayin Zhang

  • Xiaoming Su

  • Hanlin Chen

  • Miao Li

  • Jinghan Guo

  • Kaiyang Zu

  • Xiaofeng Chen

  • Yanguo Su

  • Hengri Cong

  • Long Yan

  • Tianyi Yan

  • Yiming Deng

  • December 8, 2025

  • 0 min

Share

  • 1

    AMAP is an anatomically-guided Masked Autoencoder framework designed for reliable detection and segmentation of cerebral aneurysms.

  • 2

    The framework incorporates anatomy-guided MAE pretraining, domain-adaptive prompting, and boundary-aware contrastive learning.

  • 3

    AMAP outperforms existing CNN, Transformer, and foundation models, achieving 3−5% higher Dice scores and reducing false positives by about 20%.

  • 4

    Qualitative results indicate AMAP's superior boundary preservation and consistent detection of small aneurysms often missed by other methods.

  • 5

    The findings suggest AMAP enhances the clinical applicability of AI in aneurysm screening, addressing critical challenges in current detection methods.

Original Source(s)

Anatomically-guided Masked Autoencoder with Domain-Adaptive Prompting (AMAP) for multimodal cerebral aneurysm detection and segmentation

  • by Mingxuan Huang, Tiantian Liu, Jiayin Zhang, Xiaoming Su, Hanlin Chen, Miao Li, Jinghan Guo, Kaiyang Zu, Xiaofeng Chen, Yanguo Su, Hengri Cong, Long Yan, Tianyi Yan, Yiming Deng

  • December 8, 2025

Related Content

A generalizable 3D framework and model for self-supervised learning in medical imaging

PAM: a propagation-based model for segmenting any 3D objects across multi-modal medical images

HemaContour: explicit parametric contour learning for robust ICH segmentation on non-contrast CT