Machine learning and machine learned prediction in chest X-ray images

TL;DR

This paper compares the performance of CNN and DenseNet-121 in predicting patient ailments from 5824 chest X-ray images, demonstrating DenseNet-121's superior focus on relevant image regions.

Contribution

The study applies and compares CNN and DenseNet-121 models for chest X-ray classification, highlighting DenseNet-121's improved interpretability and accuracy.

Findings

DenseNet-121 outperforms baseline CNN in accuracy.

Gradient-weighted class activation mapping shows better focus of DenseNet-121.

Both models perform well in binary classification of chest X-ray images.

Abstract

Machine learning and artificial intelligence are fast-growing fields of research in which data is used to train algorithms, learn patterns, and make predictions. This approach helps to solve seemingly intricate problems with significant accuracy without explicit programming by recognizing complex relationships in data. Taking an example of 5824 chest X-ray images, we implement two machine learning algorithms, namely, a baseline convolutional neural network (CNN) and a DenseNet-121, and present our analysis in making machine-learned predictions in predicting patients with ailments. Both baseline CNN and DenseNet-121 perform very well in the binary classification problem presented in this work. Gradient-weighted class activation mapping shows that DenseNet-121 correctly focuses on essential parts of the input chest X-ray images in its decision-making more than the baseline CNN.