Machine learning pilot study shows promise for COVID-19 classification from X-rays

Researchers have conducted a pilot study using traditional machine learning techniques to classify COVID-19 from other pneumonias using chest X-ray data. By employing texture and gradient-based features with classifiers like logistic regression, random forest, and support vector machines, the study achieved a maximum accuracy of 75.4% and an AUC of 0.755. The findings suggest that while these methods show promise, larger, multi-institutional datasets are needed to develop more advanced multi-modal deep learning architectures, combining convolutional and transformer-based encoders, for improved diagnostic capabilities. AI

IMPACT This research highlights the potential of texture-based machine learning for disease classification, motivating further development of advanced deep learning models for medical imaging diagnostics.

RANK_REASON The item is an academic paper detailing a pilot study on machine learning for medical image classification. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• convolutional neural network
• COVID-19
• Gray Level Co-Occurrence Matrix Texture Analysis of Germinal Center Light Zone Lymphocyte Nuclei: Physiology Viewpoint with Focus on Apoptosis
• Histogram of oriented gradients
• Image Data Collection
• logistic regression model
• random forest
• support vector machine
• Transformer++
• Yogisri Pujitha Chinthoti

• paper
• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →