Deep learning to determine the activity of pulmonary tuberculosis on chest radiographs

Seowoo Lee, Jae Joon Yim, Nakwon Kwak, Yeon Joo Lee, Jung Kyu Lee, Ji Yeon Lee, Ju Sang Kim, Young Ae Kang, Doosoo Jeon, Myoung Jin Jang, Jin Mo Goo, Soon Ho Yoon

Research output: Contribution to journalArticlepeer-review

12 Citations (Scopus)

Abstract

Background: Determining the activity of pulmonary tuberculosis on chest radiographs is difficult. Purpose: To develop a deep learning model to identify active pulmonary tuberculosis on chest radiographs. Materials and Methods: Chest radiographs were retrospectively gathered from a multicenter consecutive cohort with pulmonary tuberculosis who were successfully treated between 2011 and 2017, along with normal radiographs to enrich a negative class. The pretreatment and posttreatment radiographs were labeled as positive and negative classes, respectively. A neural network was trained with those radiographs to calculate the probability of active versus healed tuberculosis. A single-center consecutive cohort (test set 1; 89 patients, 148 radiographs) and data from one multicenter randomized controlled trial (test set 2; 366 patients, 3774 radiographs) were used to test the model. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of the model and of the four expert readers. Results: In total, 6654 pre- and posttreatment radiographs from 3327 patients (mean age 6 standard deviation, 55 years 6 19; 1884 men) with pulmonary tuberculosis and 3182 normal radiographs from as many patients (mean age, 53 years 6 14; 1629 men) were gathered. For test set 1, the model showed a higher AUC (0.83; 95% CI: 0.73, 0.89) than one pulmonologist (0.69; 95% CI: 0.61, 0.76; P , .001) and performed similarly to the other readers (AUC, 0.79–0.80; P = .14–.23). For 200 randomly selected radiographs from test set 2, the model had a higher AUC (0.84) than the pulmonologists (0.71 and 0.74; P , .001 and .01, respectively) and performed similarly to the radiologists (0.79 and 0.80; P = .08 and .06, respectively). The model output increased by 0.30 on average with a higher degree of smear positivity (95% CI: 0.20, 0.39; P , .001) and decreased during treatment (baseline, 3 months, and 6 months: 0.85, 0.51, and 0.26, respectively). Conclusion: A deep learning model performed similarly to radiologists for accurately determining the activity of pulmonary tuberculosis on chest radiographs; it also was able to follow posttreatment changes.

Original languageEnglish
Pages (from-to)435-442
Number of pages8
JournalRadiology
Volume301
Issue number2
DOIs
Publication statusPublished - 2021 Nov

Bibliographical note

Publisher Copyright:
© 2021 Radiological Society of North America Inc.. All rights reserved.

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging

Fingerprint

Dive into the research topics of 'Deep learning to determine the activity of pulmonary tuberculosis on chest radiographs'. Together they form a unique fingerprint.

Cite this