CovidExpert: A Triplet Siamese Neural Network framework for the detection of COVID-19

TL;DR

This paper introduces CovidExpert, a triplet Siamese neural network framework that effectively detects COVID-19 from CT scans using few-shot learning, achieving high accuracy with limited data.

Contribution

It presents a novel few-shot learning approach combining pre-trained CNNs and a triplet Siamese network for COVID-19 detection from CT images, suitable for small datasets.

Findings

Achieved 98.72% accuracy in COVID-19 detection.

High specificity and ROC score demonstrate model reliability.

Effective with only 200 images per category.

Abstract

Patients with the COVID-19 infection may have pneumonia-like symptoms as well as respiratory problems which may harm the lungs. From medical images, coronavirus illness may be accurately identified and predicted using a variety of machine learning methods. Most of the published machine learning methods may need extensive hyperparameter adjustment and are unsuitable for small datasets. By leveraging the data in a comparatively small dataset, few-shot learning algorithms aim to reduce the requirement of large datasets. This inspired us to develop a few-shot learning model for early detection of COVID-19 to reduce the post-effect of this dangerous disease. The proposed architecture combines few-shot learning with an ensemble of pre-trained convolutional neural networks to extract feature vectors from CT scan images for similarity learning. The proposed Triplet Siamese Network as the few-shot learning model classified CT scan images into Normal, COVID-19, and Community-Acquired Pneumonia. The suggested model achieved an overall accuracy of 98.719%, a specificity of 99.36%, a sensitivity of 98.72%, and a ROC score of 99.9% with only 200 CT scans per category for training data.