상세 보기
Deep learning-based detection of pneumoperitoneum on computed tomography: performance and clinical feasibility
- Ryu, Hyo Seon;
- Jung, Se Hoon;
- Lee, Inhyeok;
- Han, Jiwon;
- Park, Ye Ryung;
- ... Kwak, Jung-Myun;
- 외 3명
WEB OF SCIENCE
0SCOPUS
0초록
Purpose Early detection of pneumoperitoneum on computed tomography (CT) is critical because delayed diagnosis of gastrointestinal perforation is associated with increased morbidity and mortality. We evaluated the diagnostic performance and clinical applicability of a deep learning model for automated pneumoperitoneum detection on CT. Methods In this retrospective diagnostic accuracy study, CT scans for 263 patients with surgically confirmed gastrointestinal perforation and 78 normal controls from a single tertiary center (January 2010–September 2024) were included. Positive CT scans were divided into training, validation, internal test, and temporally independent external test datasets, with 78 normal controls included in the external test dataset. Free air was manually segmented and verified by surgical and radiological experts. A segmentation-based deep learning model was developed using the no-new-Segment Anything Model (nnSAM)framework and compared with a conventional no-new-Net (nnUNet) model. Segmentation and classification performance were assessed on internal and temporally independent external test datasets. Result In the internal test dataset (n=43 positive cases), the nnSAM model achieved a higher detection rate (97.7% vs. 90.7%) and significantly higher mean Dice similarity coefficient (0.739±0.266 vs. 0.684±0.283; p=0.045) than the nnUNet one. In the external test dataset, nnSAM also showed a higher detection rate in positive cases (97.9% vs. 85.4%) and a significantly higher mean Dice similarity coefficient (0.863±0.189 vs. 0.746±0.208; p=0.003). Conclusion The performance advantage of nnSAM was particularly evident in small-volume pneumoperitoneum cases. The nnSAM-based model showed improved accuracy and robustness for pneumoperitoneum detection on CT, supporting its potential as a clinically useful decision-support tool for emergency radiology workflows and triage of patients with suspected gastrointestinal perforation
키워드
- 제목
- Deep learning-based detection of pneumoperitoneum on computed tomography: performance and clinical feasibility
- 저자
- Ryu, Hyo Seon; Jung, Se Hoon; Lee, Inhyeok; Han, Jiwon; Park, Ye Ryung; Jeong, Rae Yoon; Han, Yeo Eun; Shin, Keewon; Kwak, Jung-Myun
- 발행일
- 2026-10
- 유형
- Article; Early Access
- 언어
- ENG
- 출판사
- SPRINGER
- 발행국가
- 미국
- ISSN
- E 2366-0058
P 2366-004X