Multilabel Classification for Lung Disease Detection: Integrating Deep Learning and Natural Language Processing

TL;DR

This paper introduces a transfer learning model combining deep learning and NLP techniques to improve multi-label lung disease classification from chest radiographs, demonstrating promising accuracy for clinical use.

Contribution

The study presents a novel integration of RadGraph parsing and NLP to enhance multi-label lung disease classification accuracy using deep learning on the CheXpert dataset.

Findings

F1 score of 0.69 achieved

AUROC of 0.86 achieved

NLP improves classification certainty

Abstract

Classifying chest radiographs is a time-consuming and challenging task, even for experienced radiologists. This provides an area for improvement due to the difficulty in precisely distinguishing between conditions such as pleural effusion, pneumothorax, and pneumonia. We propose a novel transfer learning model for multi-label lung disease classification, utilizing the CheXpert dataset with over 12,617 images of frontal radiographs being analyzed. By integrating RadGraph parsing for efficient annotation extraction, we enhance the model's ability to accurately classify multiple lung diseases from complex medical images. The proposed model achieved an F1 score of 0.69 and an AUROC of 0.86, demonstrating its potential for clinical applications. Also explored was the use of Natural Language Processing (NLP) to parse report metadata and address uncertainties in disease classification. By comparing uncertain reports with more certain cases, the NLP-enhanced model improves its ability to conclusively classify conditions. This research highlights the connection between deep learning and NLP, underscoring their potential to enhance radiological diagnostics and aid in the efficient analysis of chest radiographs.