An Attention-Based CoT-ResNet With Channel Shuffle Mechanism for Classification of Alzheimer’s Disease Levels

Abstract

Detection of early morphological changes in the brain and early diagnosis are important for Alzheimer’s disease (AD), and high-resolution magnetic resonance imaging (MRI) can be used to help diagnose and predict the disease. In this paper, we proposed two improved ResNet algorithms that introduced the Contextual Transformer (CoT) module, group convolution, and Channel Shuffle mechanism into the traditional ResNet residual blocks. The CoT module is used to replace the 3 × 3 convolution in the residual block to enhance the feature extraction capability of the residual block, while the Channel Shuffle mechanism is used to reorganize the feature maps of different groups in the input layer to improve the communication between the feature maps from different groups. Images of 503 subjects, including 116 healthy controls (HC), 187 subjects with mild cognitive impairment (MCI), and 200 subjects with AD, were selected and collated from the ADNI database, and then, the data were pre-processed and sliced. After that, 10,060 slices were obtained and the three groups of AD, MCI and HC were classified using the improved algorithms. The experiments showed that the refined ResNet-18-based algorithm improved the top-1 accuracy by 2.06%, 0.33%, 1.82%, and 1.52% over the traditional ResNet-18 algorithm for four medical image classification tasks, namely AD: MCI, AD: HC, MCI: HC, and AD: MCI: HC, respectively. The enhanced ResNet-50-based algorithm improved the top-1 accuracy by 1.02%, 2.92%, 3.30%, and 1.31%, respectively, over the traditional ResNet-50 algorithm in four medical image classification tasks, demonstrating the effectiveness of the CoT module replacement and the inclusion of the channel shuffling mechanism, as well as the competitiveness of the improved algorithms.

Computational modeling of aging-related gene networks: a review

“…However, their implementation has raised ethical and cultural concerns (119). Initially introduced by Vaswani et al (120) for language translation, transformers are now widely used in text generation to predict the next word in a sentence. The transformer architecture's main innovation is the "attention mechanism, " which enables it to associate words that refer to the same concept.…”

Understanding the Role of Self-Attention in a Transformer Model for the Discrimination of SCD From MCI Using Resting-State EEG

“…Based on the present results, we speculate that our framework could serve not only to enhance the interpretability of a black-box model which achieves state-of-the-art classification performances, thus addressing the problem of the trade-off between accuracy and trustworthiness [65], but also as a guide for experts to facilitate the extraction of rsEEG markers of cognitive decay. A recent work employed the attention mechanism to design an EEG channel interpolation algorithm [66]. Similarly, our method could be exploited also in different applications to select relevant domain-specific information by taking into account short and long temporal dependencies of the signal.…”

STAE‐YOLO: Intelligent detection algorithm for risk management of construction machinery intrusion on transmission lines based on visual perception

“…The cross‐channel fusion attention module first groups the dimensions of channels into sub‐features, and for each sub‐feature, a Shuffle unit is used to describe the spatial and channel correlation of the features. After that, all the sub‐features are aggregated and the “Channel Shuffle” [32] operator is used to communicate information between the different sub‐features. The multi‐branch structure allows the model to become deeper and easier to train.…”