Pneumonia Detection in Chest X-Rays using Neural Networks

TL;DR

This paper proposes a simple CNN model with transfer learning for pneumonia detection in chest X-rays, achieving competitive results on RSNA datasets with limited computational resources.

Contribution

Introduces a non-complex CNN approach combined with transfer learning techniques to efficiently classify pneumonia in chest X-rays, aiming for RSNA benchmark performance.

Findings

Mask R-CNN achieved MAP score of 0.15 on stratified sample

YoloV3 achieved MAP score of 0.32 without hyperparameter tuning

Further training could improve model performance

Abstract

With the advancement in AI, deep learning techniques are widely used to design robust classification models in several areas such as medical diagnosis tasks in which it achieves good performance. In this paper, we have proposed the CNN model (Convolutional Neural Network) for the classification of Chest X-ray images for Radiological Society of North America Pneumonia (RSNA) datasets. The study also tries to achieve the same RSNA benchmark results using the limited computational resources by trying out various approaches to the methodologies that have been implemented in recent years. The proposed method is based on a non-complex CNN and the use of transfer learning algorithms like Xception, InceptionV3/V4, EfficientNetB7. Along with this, the study also tries to achieve the same RSNA benchmark results using the limited computational resources by trying out various approaches to the methodologies that have been implemented in recent years. The RSNA benchmark MAP score is 0.25, but using the Mask RCNN model on a stratified sample of 3017 along with image augmentation gave a MAP score of 0.15. Meanwhile, the YoloV3 without any hyperparameter tuning gave the MAP score of 0.32 but still, the loss keeps decreasing. Running the model for a greater number of iterations can give better results.