Connectional-style-guided contextual representation learning for brain disease diagnosis | |
Wang, Gongshu3; Jiang, Ning3; Ma, Yunxiao3; Chen, Duanduan3; Wu, Jinglong3; Li, Guoqi2; Liang, Dong1; Yan, Tianyi3 | |
刊名 | NEURAL NETWORKS
![]() |
2024-07-01 | |
卷号 | 175页码:14 |
关键词 | Transformers Brain disease diagnosis Self-supervised MRI |
ISSN号 | 0893-6080 |
DOI | 10.1016/j.neunet.2024.106296 |
通讯作者 | Chen, Duanduan(duanduan@bit.edu.cn) ; Yan, Tianyi(yantianyi@bit.edu.cn) |
英文摘要 | Structural magnetic resonance imaging (sMRI) has shown great clinical value and has been widely used in deep learning (DL) based computer-aided brain disease diagnosis. Previous DL-based approaches focused on local shapes and textures in brain sMRI that may be significant only within a particular domain. The learned representations are likely to contain spurious information and have poor generalization ability in other diseases and datasets. To facilitate capturing meaningful and robust features, it is necessary to first comprehensively understand the intrinsic pattern of the brain that is not restricted within a single data/task domain. Considering that the brain is a complex connectome of interlinked neurons, the connectional properties in the brain have strong biological significance, which is shared across multiple domains and covers most pathological information. In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis. Specifically, it has a vision transformer (ViT) encoder and leverages mask reconstruction as the proxy task and Gram matrices to guide the representation of connectional information. It facilitates the capture of global context and the aggregation of features with biological plausibility. The results indicate that CS-CRL achieves superior accuracy in multiple brain disease diagnosis tasks across six datasets and three diseases and outperforms state-of-the-art models. Furthermore, we demonstrate that CS-CRL captures more brain-network-like properties, and better aggregates features, is easier to optimize, and is more robust to noise, which explains its superiority in theory. |
资助项目 | STI 2030-Major Projects[2022ZD0208500] ; National Natural Science Foundation of China[U20A20191] ; National Natural Science Foundation of China[62336002] ; National Natural Science Foundation of China[62373056] ; Beijing Natural Science Foundation[Z210012] ; Biological & Medical Engineering Core Facilities, Beijing Institute of Technology |
WOS关键词 | CONVOLUTIONAL NEURAL-NETWORKS ; ALZHEIMERS-DISEASE ; GRAY-MATTER ; ORGANIZATION |
WOS研究方向 | Computer Science ; Neurosciences & Neurology |
语种 | 英语 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:001233513000001 |
资助机构 | STI 2030-Major Projects ; National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Biological & Medical Engineering Core Facilities, Beijing Institute of Technology |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/58461] ![]() |
专题 | 数字内容技术与服务研究中心_听觉模型与认知计算 |
通讯作者 | Chen, Duanduan; Yan, Tianyi |
作者单位 | 1.Chinese Acad Sci, Res Ctr Med AI, Shenzhen Inst Adv Technol, Shenzhen, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Beijing Inst Technol, Sch Med Technol, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Wang, Gongshu,Jiang, Ning,Ma, Yunxiao,et al. Connectional-style-guided contextual representation learning for brain disease diagnosis[J]. NEURAL NETWORKS,2024,175:14. |
APA | Wang, Gongshu.,Jiang, Ning.,Ma, Yunxiao.,Chen, Duanduan.,Wu, Jinglong.,...&Yan, Tianyi.(2024).Connectional-style-guided contextual representation learning for brain disease diagnosis.NEURAL NETWORKS,175,14. |
MLA | Wang, Gongshu,et al."Connectional-style-guided contextual representation learning for brain disease diagnosis".NEURAL NETWORKS 175(2024):14. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论