No abstract

Multimodal medical image fusion involves the integration of medical images originating from distinct modalities and captured by various sensors, with the aim to enhance image quality, minimize redundant information, and preserve specific features, ultimately leading to increased efficiency and accuracy in clinical diagnoses. In recent years, the emergence of deep learning techniques has propelled significant advancements in image fusion, addressing the limitations of conventional methods that necessitate manual design of activity level measurement and fusion rules. This paper initially presents a systematic description of the multimodal medical image fusion problem, delineating the interrelationships between different fusion modalities while summarizing their characteristics and functions. Subsequently, it reviews the theories and enhancement approaches associated with deep learning in the medical image fusion domain, striving for a comprehensive overview of the state-of-the-art developments in this field from a deep learning perspective. These developments encompass multimodal feature extraction methods based on convolutional techniques, adversarial learning-based methods, convolutional sparse representation and stacked autoencoder-based signal processing methods, and unified models. Lastly, the paper summarizes the enhancement techniques for multimodal medical image fusion methods, highlighting the pressing issues and challenges encountered by deep learning approaches in this domain.

Alzheimer's Disease (AD) is an irreversible neurodegenerative disease common in the elderly. The application of artificial intelligence technology to the early diagnosis of AD can not only improve the accuracy of prediction compared with traditional methods, but also save the complicated manual feature extraction of traditional methods and speed up the diagnosis. This paper reviews various applications of artificial intelligence algorithms in AD diagnosis, including machine learning, convolutional neural network, graph convolutional neural network, cyclic neural network and other mainstream deep learning technologies. The advantages and disadvantages of each approach are discussed, and finally, we discuss limitations and future prospects.