본문 바로가기

Deep Learning to Determine the Activity of Pulmonary Tuberculosis on Chest Radiographs

문서 유형
연구출판물 · 학술지 논문
등재
Nature IndexSCIEScopus
저널 순위
JCR Q1Scopus Q1
저널
RADIOLOGY301(2) · pp.435 · 2021
피인용
Web of Science 39Scopus 44
FWCI (Scopus)
3.37
JCR IF
JCR 2020 11.105
ISSN
0033-8419

저자

  1. Lee, Seowoo제1저자Seoul Natl Univ, Seoul Natl Univ Hosp, Dept Radiol, Coll Med, 101 Daehak Ro, Seoul 03080, South Korea
  2. Yim, Jae-JoonSeoul Natl Univ, Dept Internal Med, Div Pulm & Crit Med, Coll Med, Seoul, South Korea
  3. Kwak, NakwonSeoul Natl Univ, Dept Internal Med, Div Pulm & Crit Med, Coll Med, Seoul, South Korea
  4. Lee, Yeon JooSeoul Natl Univ, Dept Internal Med, Div Pulm & Crit Care Med, Bundang Hosp, Seongnam, South Korea
  5. Lee, Jung-KyuSeoul Natl Univ, Dept Internal Med, Div Pulm & Crit Care Med, Boramae Med Ctr,Seoul Metropolitan Govt, Seoul, South Korea
  6. Lee, Ji YeonNatl Med Ctr, Dept Internal Med, Div Pulm & Crit Care Med, Seoul, South Korea
  7. Kim, Ju SangCatholic Univ Korea, Coll Med, Dept Internal Med, Div Pulm & Crit Care Med,Incheon St Marys Hosp, Incheon, South Korea
  8. Kang, Young AeYonsei Univ, Severance Hosp, Dept Internal Med, Div Pulm & Crit Care Med,Coll Med, Seoul, South Korea
  9. 전두수Pusan Natl Univ, Sch Med, Dept Internal Med, Yangsan Hosp, Yangsan, South Korea
  10. Jang, Myoung-jinSeoul Natl Univ Hosp, Med Res Collaborating Ctr, Seoul, South Korea
  11. Goo, Jin MoSeoul Natl Univ, Seoul Natl Univ Hosp, Dept Radiol, Coll Med, 101 Daehak Ro, Seoul 03080, South Korea
  12. Yoon, Soon Ho교신저자Seoul Natl Univ, Seoul Natl Univ Hosp, Dept Radiol, Coll Med, 101 Daehak Ro, Seoul 03080, South Korea

초록

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 radio-graphs) 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 +/- standard deviation, 55 years +/- 19; 1884 men) with pulmonary tuberculosis and 3182 normal radiographs from as many patients (mean age, 53 years +/- 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. (C) RSNA, 2021.

키워드

SEQUELAE

식별자

Scopus EID
2-s2.0-85118106952
WoS UID
000710995100043