본문 바로가기

Development and validation of a deep learning-based algorithm for quantifying bronchiolitis obliterans in paediatric computed tomography

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q1Scopus Q1
저널
BRITISH JOURNAL OF RADIOLOGY99(1178) · pp.319 · 2026
피인용
Web of Science 0Scopus 0
FWCI (Scopus)
0
JCR IF
JCR 2024 3.4
ISSN
0007-1285

저자

  1. Rhee, Chanyoung제1저자Seoul Natl Univ, Seoul Natl Univ Hosp, Coll Med, Dept Radiol, 101 Daehak Ro, Seoul 03080, South Korea
  2. Hwang, Jae-YeonSeoul Natl Univ, Seoul Natl Univ Hosp, Coll Med, Dept Radiol, 101 Daehak Ro, Seoul 03080, South Korea
  3. 하지영Pusan Natl Univ, Pusan Natl Univ Yangsan Hosp, Coll Med, Dept Radiol, Busan 50612, South Korea
  4. Choi, Jae WonSeoul Natl Univ, Seoul Natl Univ Hosp, Coll Med, Dept Radiol, 101 Daehak Ro, Seoul 03080, South Korea
  5. Cho, Yeon JinSeoul Natl Univ, Seoul Natl Univ Hosp, Coll Med, Dept Radiol, 101 Daehak Ro, Seoul 03080, South Korea
  6. Lee, SeunghyunSeoul Natl Univ, Seoul Natl Univ Hosp, Coll Med, Dept Radiol, 101 Daehak Ro, Seoul 03080, South Korea
  7. Cheon, Jung-EunSeoul Natl Univ, Seoul Natl Univ Hosp, Coll Med, Dept Radiol, 101 Daehak Ro, Seoul 03080, South Korea
  8. Suh, Dong InSeoul Natl Univ, Seoul Natl Univ Hosp, Dept Pediat, Coll Med, Seoul 03080, South Korea
  9. Choi, Young Hun교신저자Seoul Natl Univ, Seoul Natl Univ Hosp, Coll Med, Dept Radiol, 101 Daehak Ro, Seoul 03080, South Korea

초록

Objectives: To develop and validate a deep learning-based algorithm for quantifying bronchiolitis obliterans (BO) on paediatric chest CT. Methods: This retrospective study included 86 children (39 males; median age, 10 years) diagnosed with BO who underwent both inspiratory and expiratory CT between January 2018 and November 2021. The deep learning-based BO quantification model was trained on 26 CT scans using a 3D nnU-Net, with radiologist-segmented low attenuation regions (LARs) serving as ground truth. Model performance was evaluated through internal test with 4 CT scans and external test with 6 CT scans. Intra-vendor robustness was assessed using 22 CT scans with varying reconstruction methods, kernel types, and slice thicknesses. Comparison with semiquantitative radiologist grading was performed using 28 CT scans. Dice similarity coefficient (DSC), sensitivity, and precision were used to evaluate model performance. Results: The model achieved a DSC of 85.41 +/- 3.28%, sensitivity of 85.14 +/- 7.66%, and precision of 86.21 +/- 3.92% in the internal test, and 82.53 +/- 4.34%, 82.17 +/- 6.15%, and 84.15 +/- 3.16% in the external test, respectively. For intra-vendor robustness, no significant differences in BO quantification were observed across different reconstruction methods, kernel types, and slice thicknesses (all P > .05). Compared to radiologists' grading, the model demonstrated strong to very strong correlations across all lung lobes (all P < .001). Conclusion: The model demonstrated accurate quantification of BO on paediatric CT, with good agreement with the radiologist-segmented ground truth.

키워드

bronchiolitis obliteranslow attenuation regionpaediatriccomputed tomographydeep learning3D nnU-NetCT

식별자

Scopus EID
2-s2.0-105031525342
WoS UID
001614021500001