Improving Tuberculosis (TB) Prediction using Synthetically Generated Computed Tomography (CT) Images

TL;DR

This paper demonstrates that using synthetically generated CT images from X-rays enhances tuberculosis detection accuracy and provides better insights into pulmonary disease compared to using X-ray images alone.

Contribution

The study introduces a model that generates CT images from X-rays, improving TB classification accuracy and offering a novel approach for disease analysis in low-resource settings.

Findings

Synthetic CT improves TB detection by 7.50%.

Enhanced differentiation of TB properties by up to 12.16%.

Model aids in better pulmonary disease evaluation.

Abstract

The evaluation of infectious disease processes on radiologic images is an important and challenging task in medical image analysis. Pulmonary infections can often be best imaged and evaluated through computed tomography (CT) scans, which are often not available in low-resource environments and difficult to obtain for critically ill patients. On the other hand, X-ray, a different type of imaging procedure, is inexpensive, often available at the bedside and more widely available, but offers a simpler, two dimensional image. We show that by relying on a model that learns to generate CT images from X-rays synthetically, we can improve the automatic disease classification accuracy and provide clinicians with a different look at the pulmonary disease process. Specifically, we investigate Tuberculosis (TB), a deadly bacterial infectious disease that predominantly affects the lungs, but also other organ systems. We show that relying on synthetically generated CT improves TB identification by 7.50% and distinguishes TB properties up to 12.16% better than the X-ray baseline.