arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.21673cs.CV
收藏

多模态视觉代理压缩用于阿尔茨海默病分类

Multimodal Visual Surrogate Compression for Alzheimer's Disease Classification

Macquarie University(麦考瑞大学);Federation University Australia(联邦大学澳大利亚);The Hong Kong Polytechnic University(香港理工大学);University of California at Merced(加州大学默塞德分校)

Dexuan Ding, Ciyuan Peng, Endrowednes Kuantama, Jingcai Guo, Jia Wu, Jian Yang, Amin Beheshti, Ming-Hsuan Yang, Yuankai Qi

AI总结:

MVSC通过压缩和适应大尺寸3D sMRI体积为紧凑的2D视觉代理,提升阿尔茨海默病分类性能。

摘要:

高维结构磁共振成像(sMRI)图像被广泛用于阿尔茨海默病(AD)诊断。现有大多数sMRI表示学习方法依赖于3D架构(如3D CNNs),逐层特征提取并进行后期聚合,或应用无训练特征提取方法使用2D基础模型(如DINO)。然而,这三种范式分别面临计算成本高、跨切片关系丢失以及提取判别性特征能力有限的问题。为解决这些挑战,我们提出了多模态视觉代理压缩(MVSC)。它学习将大尺寸3D sMRI体积压缩并适应为紧凑的2D特征,称为视觉代理,这些特征更符合冻结的2D基础模型以提取强大的表示用于最终的AD分类。MVSC有两个关键组件:一个体积上下文编码器,它在文本引导下捕捉全局跨切片上下文,以及一个自适应切片融合模块,该模块以文本增强的方式按补丁方式进行切片级信息聚合。在三个大规模阿尔茨海默病基准上的广泛实验表明,我们的MVSC在二分类和多分类任务中相比最先进的方法表现更优。

英文摘要:

High-dimensional structural MRI (sMRI) images are widely used for Alzheimer's Disease (AD) diagnosis. Most existing methods for sMRI representation learning rely on 3D architectures (e.g., 3D CNNs), slice-wise feature extraction with late aggregation, or apply training-free feature extractions using 2D foundation models (e.g., DINO). However, these three paradigms suffer from high computational cost, loss of cross-slice relations, and limited ability to extract discriminative features, respectively. To address these challenges, we propose Multimodal Visual Surrogate Compression (MVSC). It learns to compress and adapt large 3D sMRI volumes into compact 2D features, termed as visual surrogates, which are better aligned with frozen 2D foundation models to extract powerful representations for final AD classification. MVSC has two key components: a Volume Context Encoder that captures global cross-slice context under textual guidance, and an Adaptive Slice Fusion module that aggregates slice-level information in a text-enhanced, patch-wise manner. Extensive experiments on three large-scale Alzheimer's disease benchmarks demonstrate our MVSC performs favourably on both binary and multi-class classification tasks compared against state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑