Convolution Neural Networks and Self-Attention Learners for Alzheimer Dementia Diagnosis from Brain MRI

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 3; p. 1694
• Main Authors: Carcagnì, Pierluigi, Leo, Marco, Del Coco, Marco, Distante, Cosimo, De Salve, Andrea
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.02.2023; MDPI
• Subjects: Alzheimer Disease - diagnostic imaging; Alzheimer's disease; assistive technology; Brain; Brain - diagnostic imaging; Brain research; Classification; Clinical medicine; Cognitive ability; Computational linguistics; computer-aided diagnosis; Datasets; Deep Learning; Dementia; Humans; Language processing; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; masked auto-encoders; medical image analysis; Medical imaging equipment; MRI; Natural language interfaces; Neural networks; Neural Networks, Computer; Registration; Tomography; masked auto-encoders; deep learning; MRI; vision transformers; assistive technology; computer-aided diagnosis; medical image analysis
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23031694

Alzheimer’s disease (AD) is the most common form of dementia. Computer-aided diagnosis (CAD) can help in the early detection of associated cognitive impairment. The aim of this work is to improve the automatic detection of dementia in MRI brain data. For this purpose, we used an established pipeline that includes the registration, slicing, and classification steps. The contribution of this research was to investigate for the first time, to our knowledge, three current and promising deep convolutional models (ResNet, DenseNet, and EfficientNet) and two transformer-based architectures (MAE and DeiT) for mapping input images to clinical diagnosis. To allow a fair comparison, the experiments were performed on two publicly available datasets (ADNI and OASIS) using multiple benchmarks obtained by changing the number of slices per subject extracted from the available 3D voxels. The experiments showed that very deep ResNet and DenseNet models performed better than the shallow ResNet and VGG versions tested in the literature. It was also found that transformer architectures, and DeiT in particular, produced the best classification results and were more robust to the noise added by increasing the number of slices. A significant improvement in accuracy (up to 7%) was achieved compared to the leading state-of-the-art approaches, paving the way for the use of CAD approaches in real-world applications.