Deep Learning for Automatic Pneumonia Detection

TL;DR

This paper presents a deep learning approach combining single-shot detectors, squeeze-and-excitation networks, and multi-task learning for automatic pneumonia detection in chest X-rays, aiming to improve diagnostic accuracy and reduce radiologist disagreement.

Contribution

It introduces a novel deep learning framework for pneumonia detection that integrates multiple advanced techniques and demonstrates competitive performance in a major challenge.

Findings

Achieved top results in the RSNA Pneumonia Detection Challenge.

Improved accuracy over traditional methods.

Validated effectiveness of combined deep learning techniques.

Abstract

Pneumonia is the leading cause of death among young children and one of the top mortality causes worldwide. The pneumonia detection is usually performed through examine of chest X-ray radiograph by highly-trained specialists. This process is tedious and often leads to a disagreement between radiologists. Computer-aided diagnosis systems showed the potential for improving diagnostic accuracy. In this work, we develop the computational approach for pneumonia regions detection based on single-shot detectors, squeeze-and-excitation deep convolution neural networks, augmentations and multi-task learning. The proposed approach was evaluated in the context of the Radiological Society of North America Pneumonia Detection Challenge, achieving one of the best results in the challenge.