AUTHOR=Liu Yujian , Tang Kun , Cai Weiwei , Chen Aibin , Zhou Guoxiong , Li Liujun , Liu Runmin TITLE=MPC-STANet: Alzheimer’s Disease Recognition Method Based on Multiple Phantom Convolution and Spatial Transformation Attention Mechanism JOURNAL=Frontiers in Aging Neuroscience VOLUME=Volume 14 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2022.918462 DOI=10.3389/fnagi.2022.918462 ISSN=1663-4365 ABSTRACT=The Alzheimer’s disease (AD) is a progressive neurodegenerative disease with insidious and irreversible onset. The recognition of the disease stage of AD and the administration of effective interventional treatment are important to slow down and control the progression of the disease. However, due to the unbalanced distribution of the acquired data volume, and the problem that the features change inconspicuously in different disease stages of AD and the scattered and narrow area of the feature areas (hippocampal region, medial temporal lobe, etc.), effective recognition of AD remains a critical unmet need. Therefore, we first employ class-balancing operation using data enhancement and Synthetic Minority Over-sampling Technique (SMOTE) to avoid the AD MRI dataset being affected by classification imbalance in the training. Subsequently, a recognition network based on Multi-Phantom Convolution (MPC) and Space Conversion Attention Mechanism (MPC-STANet) with ResNet50 as the backbone network is proposed for the recognition of disease stages of AD. In this paper, multi-phantom convolution is proposed, and based on this, Multi-Phantom Residual Block (MPRB) that includes Multi-Conv Block and Multi-Identity Block is proposed to recognize the scattered and tiny disease features. Meanwhile, the weight coefficients are extracted from both vertical and horizontal directions using the Space Conversion Attention Mechanism (SCAM) to better recognize subtle structural changes in the AD MRI images. The experimental results show that our proposed method achieves an average recognition accuracy of 96.25%, F1 score of 95% and mAP of 93%, and the number of parameters is only 1.69 M more than ResNet50.