Xu Haozhe, Wang Jian, Feng Qianjin, Zhang Yu, Ning Zhenyuan
School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; Department of Radiotherapy, State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou 510515, China; Guangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou 510515, China; Guangdong Province Engineering Laboratory for Medical Imaging and Diagnostic Technology, Southern Medical University, Guangzhou 510515, China.
Department of Radiation Oncology, Nanfang Hospital, Southern Medical University, Guangzhou, China.
Med Image Anal. 2025 Apr;101:103448. doi: 10.1016/j.media.2024.103448. Epub 2025 Jan 6.
Although multi-modality neuroimages have advanced the early diagnosis of Alzheimer's Disease (AD), missing modality issue still poses a unique challenge in the clinical practice. Recent studies have tried to impute the missing data so as to utilize all available subjects for training robust multi-modality models. However, these studies may overlook the modality-specific information inherent in multi-modality data, that is, different modalities possess distinct imaging characteristics and focus on different aspects of the disease. In this paper, we propose a domain-specific information preservation (DSIP) framework, consisting of modality imputation stage and status identification stage, for AD diagnosis with incomplete multi-modality neuroimages. In the first stage, a specificity-induced generative adversarial network (SIGAN) is developed to bridge the modality gap and capture modality-specific details for imputing high-quality neuroimages. In the second stage, a specificity-promoted diagnosis network (SPDN) is designed to promote the inter-modality feature interaction and the classifier robustness for identifying disease status accurately. Extensive experiments demonstrate the proposed method significantly outperforms state-of-the-art methods in both modality imputation and status identification tasks.
尽管多模态神经影像技术推动了阿尔茨海默病（AD）的早期诊断，但在临床实践中，模态缺失问题仍然是一个独特的挑战。最近的研究试图对缺失数据进行插补，以便利用所有可用受试者来训练强大的多模态模型。然而，这些研究可能忽略了多模态数据中固有的模态特定信息，也就是说，不同的模态具有不同的成像特征，并且关注疾病的不同方面。在本文中，我们提出了一种特定领域信息保留（DSIP）框架，该框架由模态插补阶段和状态识别阶段组成，用于利用不完整的多模态神经影像进行AD诊断。在第一阶段，开发了一种特异性诱导生成对抗网络（SIGAN），以弥合模态差距并捕捉模态特定细节，用于插补高质量的神经影像。在第二阶段，设计了一种特异性促进诊断网络（SPDN），以促进模态间特征交互和分类器鲁棒性，从而准确识别疾病状态。大量实验表明，所提出的方法在模态插补和状态识别任务中均显著优于现有方法。
