Study on the TB and Non-TB Diagnosis Using Two-Step Deep Learning-Based Binary Classifier

Published

Journal of Instrumentation, 2020, 15.10: P10011

Authors

Seung Hoon Yoo¹, GengHui Geng¹, Tin Lok Chiu¹, Siu Ki Yu¹, Dae Chul Cho², Jin Heo², Min Sung Choi², Il Hyun Cho², Cong Cung Van³, Nguen Viet Nhung³, and Byung Jun Min⁴

Affiliations

¹Medical Physics and Research Department, Hong Kong Sanatorium & Hospital,
2 Village Road, Happy Valley, Hong Kong, China
²Division of Artificial Intelligent Clinical Research, Radisen,
128, Gongduk B/D, Saechang-ro, Mapo-gu, Seoul, Korea
³National Tuberculosis Programme, Vietnam National Lung Hospital,
Hanoi, Vietnam
⁴Department of Radiation Oncology, Chungbuk National University Hospital,
776, 1 Sunhwan-ro, Seowon-gu, Cheongju, Korea

Abstract

A deep learning-based binary classifier was proposed to diagnose tuberculosis (TB) and non-TB disease using a chest X-ray radiograph. The proposed classifier comprised two-step binary decision trees, each trained by a deep learning model with convolution neural network (CNN) based on the PyTorch frame. Normal and abnormal images of chest X-ray was classified in the first step. The abnormal images were predicted to be classified into TB and non-TB disease by the second step of the process. The accuracies of first and second step were 98% and 80% respectively. Moreover, re-training could improve the stability of prediction accuracy for images in different data groups.