计算机科学
人工智能
鉴定(生物学)
深度学习
模式识别(心理学)
模式
缺少数据
图像(数学)
机器学习
模态(人机交互)
特征学习
特征(语言学)
生物
哲学
社会学
植物
语言学
社会科学
作者
Yongsheng Pan,Mingxia Liu,Yong Xia,Dinggang Shen
标识
DOI:10.1109/tpami.2021.3091214
摘要
Incomplete data problem is commonly existing in classification tasks with multi-source data, particularly the disease diagnosis with multi-modality neuroimages, to track which, some methods have been proposed to utilize all available subjects by imputing missing neuroimages. However, these methods usually treat image synthesis and disease diagnosis as two standalone tasks, thus ignoring the specificity conveyed in different modalities, i.e., different modalities may highlight different disease-relevant regions in the brain. To this end, we propose a disease-image-specific deep learning (DSDL) framework for joint neuroimage synthesis and disease diagnosis using incomplete multi-modality neuroimages. Specifically, with each whole-brain scan as input, we first design a Disease-image-Specific Network (DSNet) with a spatial cosine module to implicitly model the disease-image specificity. We then develop a Feature-consistency Generative Adversarial Network (FGAN) to impute missing neuroimages, where feature maps (generated by DSNet) of a synthetic image and its respective real image are encouraged to be consistent while preserving the disease-image-specific information. Since our FGAN is correlated with DSNet, missing neuroimages can be synthesized in a diagnosis-oriented manner. Experimental results on three datasets suggest that our method can not only generate reasonable neuroimages, but also achieve state-of-the-art performance in both tasks of Alzheimer's disease identification and mild cognitive impairment conversion prediction.
科研通智能强力驱动
Strongly Powered by AbleSci AI