Scholarlink

Alzheimer’s disease (AD) is an irreversible neurodegenerative disorder, and the early diagnosis is crucial for prognosis and delaying progression. Multi-modal neuroimaging, particularly T1-weighted (T1w) magnetic resonance imaging (MRI) and diffusion MRI (dMRI)​, has been widely adopted for the early diagnosis of AD. ​T1w MRI captures ​cortical atrophy patterns, while ​dMRI​ reveals ​microstructural degeneration​ (e.g., myelin damage and axonal loss), with both modalities demonstrating ​strong diagnostic potential​ and ​high inter-modal correlation. Existing multi-modal deep learning models benefit from large-scale, multi-site datasets, they often neglect the site-specific biases that may compromise model performance. Meanwhile, image-level harmonization approaches are generally ​challenging​ to integrate directly into diagnostic pipelines and are limited in their ability to handle multi-modal data effectively. To address this issue, we propose an end-to-end deep learning framework for Alzheimer's Disease diagnosis by using multi-site and multi-modal MRI data, which includes an multi-site adversarial harmonization module (MAHM) and a mild cognitive impairment (MCI) enhancement module (MCIEM). Specifically, MAHM mitigates site-specific data shifts by aligning data from different sites to a pseudo target domain, while adversarially preserving the model’s ability to recognize site-specific features, thus enhancing its domain adaptation capabilities. Additionally, the MCIEM includes feature-level adaptive boundary loss and a classifier-level penalty term, which are used to increase the margin between MCI and Natural Control (NC)​. In summary, our framework mitigates site-related biases in multi-site MRI data, improving diagnostic accuracy. Evaluated on a multi-site dataset MCADI (N = 860, 7 sites) with T1w MRI and dMRI, it achieved advanced performance in NC/MCI/AD classification, outperforming existing methods. Code is publicly available at https://github.com/AI4DMR/3MAD .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An End-to-End Deep Learning Framework for Alzheimer's Disease Diagnosis by Using Multi-site and Multi-modal MRI Data

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Qichen Zhang,
  • Yunhui Yue,
  • Di Zhang,
  • Kun Zhao,
  • Alan Wang,
  • Bing Xue,
  • Yong Liu,
  • Fangrong Zong

摘要

Alzheimer’s disease (AD) is an irreversible neurodegenerative disorder, and the early diagnosis is crucial for prognosis and delaying progression. Multi-modal neuroimaging, particularly T1-weighted (T1w) magnetic resonance imaging (MRI) and diffusion MRI (dMRI)​, has been widely adopted for the early diagnosis of AD. ​T1w MRI captures ​cortical atrophy patterns, while ​dMRI​ reveals ​microstructural degeneration​ (e.g., myelin damage and axonal loss), with both modalities demonstrating ​strong diagnostic potential​ and ​high inter-modal correlation. Existing multi-modal deep learning models benefit from large-scale, multi-site datasets, they often neglect the site-specific biases that may compromise model performance. Meanwhile, image-level harmonization approaches are generally ​challenging​ to integrate directly into diagnostic pipelines and are limited in their ability to handle multi-modal data effectively. To address this issue, we propose an end-to-end deep learning framework for Alzheimer's Disease diagnosis by using multi-site and multi-modal MRI data, which includes an multi-site adversarial harmonization module (MAHM) and a mild cognitive impairment (MCI) enhancement module (MCIEM). Specifically, MAHM mitigates site-specific data shifts by aligning data from different sites to a pseudo target domain, while adversarially preserving the model’s ability to recognize site-specific features, thus enhancing its domain adaptation capabilities. Additionally, the MCIEM includes feature-level adaptive boundary loss and a classifier-level penalty term, which are used to increase the margin between MCI and Natural Control (NC)​. In summary, our framework mitigates site-related biases in multi-site MRI data, improving diagnostic accuracy. Evaluated on a multi-site dataset MCADI (N = 860, 7 sites) with T1w MRI and dMRI, it achieved advanced performance in NC/MCI/AD classification, outperforming existing methods. Code is publicly available at https://github.com/AI4DMR/3MAD .