Trans-ResNet: Integrating Transformers and CNNs for Alzheimer's disease classification | |
Li C(李超)1,2; Cui Y(崔玥)1,2; Luo N(罗娜)1,2; Liu Y(刘勇)1,2; Bourgeat Pierrick3; Fripp Jurgen3; Jiang TZ(蒋田仔)1,2 | |
2022-03 | |
会议名称 | 2022 IEEE 19th International Symposium on Biomedical Imaging |
会议日期 | 2022-3-28 |
会议地点 | 印度,加尔各答 |
出版者 | Institute of Electrical and Electronics Engineers |
摘要 | Convolutional neural networks (CNNs) have demonstrated excellent performance for brain disease classification from MRI data. However, CNNs lack the ability to capture global dependencies. The recently proposed architecture called Transformer uses attention mechanisms to match or even outperform CNNs on various vision tasks. Transformer’s performance is dependent on access to large training datasets, but sample sizes for most brain MRI datasets are relatively small. To overcome this limitation, we propose Trans-ResNet, a novel architecture which integrates the advantages of both CNNs and Transformers. In addition, we pre-trained our Trans-ResNet on a large-scale dataset on the task of brain age estimation for higher performance. Using three neuroimaging cohorts (UK Biobank, AIBL, ADNI), we demonstrated that our Trans-ResNet achieved higher classification accuracy on Alzheimer disease prediction compared to other state-of-the-art CNN-based methods. |
关键词 | convolutional neural network deep learning structural MRI transfer learning Transformer |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
DOI | 10.1109/ISBI52829.2022.9761549 |
收录类别 | EI |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48876 |
专题 | 脑网络组研究 |
通讯作者 | Jiang TZ(蒋田仔) |
作者单位 | 1.中国科学院自动化研究所脑网络组 2.中国科学院大学 3.CSIRO Health and Biosecurity, Australian e-Health Research Centre CSIRO, Australia |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li C,Cui Y,Luo N,et al. Trans-ResNet: Integrating Transformers and CNNs for Alzheimer's disease classification[C]:Institute of Electrical and Electronics Engineers,2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Trans-ResNet_Integra(3989KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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