Detection of neonatal pneumoperitoneum on radiographs using deep multi-task learning

Changhyun Park; Jinwha Choi; Jisun Hwang; Hana Jeong; Pyeong Hwa Kim; Young Ah Cho; Byong Sop Lee; Euiseok Jung; Se Hwa Kwon; Minsung Kim; Haesung Jun; Yoojin Nam; Namkug Kim; Hee Mang Yoon

doi:10.1016/j.compbiomed.2025.110945

Detection of neonatal pneumoperitoneum on radiographs using deep multi-task learning

Comput Biol Med. 2025 Sep;196(Pt C):110945. doi: 10.1016/j.compbiomed.2025.110945. Epub 2025 Aug 20.

Authors

Changhyun Park¹, Jinwha Choi², Jisun Hwang³, Hana Jeong⁴, Pyeong Hwa Kim⁴, Young Ah Cho⁴, Byong Sop Lee⁵, Euiseok Jung⁵, Se Hwa Kwon⁵, Minsung Kim⁶, Haesung Jun⁶, Yoojin Nam⁶, Namkug Kim⁷, Hee Mang Yoon⁸

Affiliations

¹ Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea; Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
² Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea; Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea; Department of Medical Science, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
³ Department of Radiology, Ajou University Hospital, Ajou University School of Medicine, Suwon, Republic of Korea.
⁴ Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Republic of Korea.
⁵ Department of Pediatrics, Asan Medical Center Children's Hospital, University of Ulsan College of Medicine, Seoul, Republic of Korea.
⁶ Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
⁷ Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea; Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Republic of Korea.
⁸ Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Republic of Korea. Electronic address: espoirhm@gmail.com.

PMID: 40839935
DOI: 10.1016/j.compbiomed.2025.110945

Abstract

Neonatal pneumoperitoneum is a life-threatening condition requiring prompt diagnosis, yet its subtle radiographic signs pose diagnostic challenges, especially in emergency settings. To develop and validate a deep multi-task learning model for diagnosing neonatal pneumoperitoneum on radiographs and to assess its clinical utility across clinicians of varying experience levels. Retrospective diagnostic study using internal and external datasets. Internal data were collected between January 1995 and August 2018, while external data were sourced from 11 neonatal intensive care units. Tertiary hospital and multicenter validation settings. Internal dataset: 204 neonates (546 radiographs), external dataset: 378 radiographs (125 pneumoperitoneum cases, 214 non-pneumoperitoneum cases). Radiographs were reviewed by two pediatric radiologists. A reader study involved 4 physicians with varying experience levels. A deep multi-task learning model combining classification and segmentation tasks for pneumoperitoneum detection. The primary outcomes included diagnostic accuracy, area under the receiver operating characteristic curve (AUC), and inter-reader agreement. AI-assisted and unassisted reader performance metrics were compared. The AI model achieved an AUC of 0.98 (95 % CI, 0.94-1.00) and accuracy of 94 % (95 % CI, 85.1-99.6) in internal validation, and AUC of 0.89 (95 % CI, 0.85-0.92) with accuracy of 84.1 % (95 % CI, 80.4-87.8) in external validation. AI assistance improved reader accuracy from 82.5 % to 86.6 % (p < .001) and inter-reader agreement (kappa increased from 0.33 to 0.71 to 0.54-0.86). The multi-task learning model demonstrated excellent diagnostic performance and improved clinicians' diagnostic accuracy and agreement, suggesting its potential to enhance care in neonatal intensive care settings. All code is available at https://github.com/brody9512/NEC_MTL.

Keywords: Artificial intelligence; Multi-task learning; Neonatal intensive care unit (NICU); Neonatal pneumoperitoneum; Radiograph.

Publication types

Multicenter Study
Observational Study

MeSH terms

Deep Learning*
Female
Humans
Infant, Newborn
Male
Pneumoperitoneum* / diagnostic imaging
Radiographic Image Interpretation, Computer-Assisted* / methods
Radiography*
Retrospective Studies