Artificial Intelligence Assisting the Early Detection of Active Pulmonary Tuberculosis From Chest X-Rays: A Population-Based Study

Abstract

As a major infectious disease, tuberculosis (TB) still poses a threat to people's health in China. As a triage test for TB, reading chest radiography with traditional approach ends up with high inter-radiologist and intra-radiologist variability, moderate specificity and a waste of time and medical resources. Thus, this study established a deep convolutional neural network (DCNN) based artificial intelligence (AI) algorithm, aiming at diagnosing TB on posteroanterior chest X-ray photographs in an effective and accurate way. Altogether, 5,000 patients with TB and 4,628 patients without TB were included in the study, totaling to 9,628 chest X-ray photographs analyzed. Splitting the radiographs into a training set (80.4%) and a testing set (19.6%), three different DCNN algorithms, including ResNet, VGG, and AlexNet, were trained to classify the chest radiographs as images of pulmonary TB or without TB. Both the diagnostic accuracy and the area under the receiver operating characteristic curve were used to evaluate the performance of the three AI diagnosis models. Reaching an accuracy of 96.73% and marking the precise TB regions on the radiographs, ResNet algorithm-based AI outperformed the rest models and showed excellent diagnostic ability in different clinical subgroups in the stratification analysis. In summary, the ResNet algorithm-based AI diagnosis system provided accurate TB diagnosis, which could have broad prospects in clinical application for TB diagnosis, especially in poor regions with high TB incidence.

Keywords: artificial intelligence; chest radiograph; deep convolutional neural network; machine learning; tuberculosis.

FIGURE 1

The workflow of the study.

FIGURE 2

Overall structure of the DCNN-based AI diagnosis system. The workflow of the system could be divided into two parts: image segmentation network (U-Net), image classification network (ResNet or VGG or AlexNet). Regions of the lung in the original chest X-ray photographs were recognized by the U-Net. Then, the cropped and resized lung region images served as an input for image classification algorithms, which generated diagnoses.

FIGURE 3

Diagnostic ability of the AI models. (A) ROC curves of three different AI models of the training set. (B) ROC curves of three different AI models of the testing set. (C) Diagnostic ability of ResNet algorithm visualized by t-SNE algorithm. Blue and orange dots indicated TB and non-TB cases of the testing set, respectively.

FIGURE 4

Stratification analysis. Subgrouping by important clinical characteristics, including sex (A,D), age (B,E) and respiratory symptoms (C,F), AUC values of the three models were calculated and compared in both sets. Young: under 65 years old. Old: 65 years old or over 65 years old.

FIGURE 5

CAMs generated by ResNet matched the precise regions of TB abnormalities. Bounding boxes [in (A,C,E)] meant the regions of abnormalities identified by doctors and hot regions [in (B,D,F)] showed the discriminative regions generated by AI algorithm.