Application of attention-based Siamese composite neural network in medical image recognition

TL;DR

This paper introduces an attention-based Siamese neural network model tailored for medical image recognition, particularly effective in few-shot and fine-grained scenarios, demonstrated on COVID-19 lung samples.

Contribution

It proposes a novel combination of attention mechanisms with Siamese neural networks to enhance few-shot and fine-grained medical image recognition.

Findings

Model performs better with fewer samples compared to traditional neural networks.

Attention mechanism improves classification accuracy in challenging conditions.

Effective on COVID-19 lung image recognition.

Abstract

Medical image recognition often faces the problem of insufficient data in practical applications. Image recognition and processing under few-shot conditions will produce overfitting, low recognition accuracy, low reliability and insufficient robustness. It is often the case that the difference of characteristics is subtle, and the recognition is affected by perspectives, background, occlusion and other factors, which increases the difficulty of recognition. Furthermore, in fine-grained images, the few-shot problem leads to insufficient useful feature information in the images. Considering the characteristics of few-shot and fine-grained image recognition, this study has established a recognition model based on attention and Siamese neural network. Aiming at the problem of few-shot samples, a Siamese neural network suitable for classification model is proposed. The Attention-Based neural network is used as the main network to improve the classification effect. Covid- 19 lung samples have been selected for testing the model. The results show that the less the number of image samples are, the more obvious the advantage shows than the ordinary neural network.