PACT-3D, a deep learning algorithm for pneumoperitoneum detection in abdominal CT scans.

Autor: Chiu IM; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA. outofray@hotmail.com.; Department of Emergency Medicine, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan. outofray@hotmail.com., Huang TY; Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan., Ouyang D; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA., Lin WC; Department of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan.; Thyroid Head and Neck Ablation Center, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.; School of Medicine, College of Medicine, National Sun Yat-Sen University, Kaohsiung, Taiwan., Pan YJ; Department of Psychiatry, Far Eastern Memorial Hospital, Banciao, Taiwan.; Department of Chemical Engineering and Materials Science, Yuan Ze University, Taoyuan, Taiwan., Lu CY; Department of Diagnostic Radiology, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan., Kuo KH; Division of Medical Image, Far Eastern Memorial Hospital, Banciao, Taiwan. goman178@gmail.com.; National Yang Ming Chiao Tung University School of Medicine, Taipei, Taiwan. goman178@gmail.com.
Jazyk: angličtina
Zdroj: Nature communications [Nat Commun] 2024 Nov 07; Vol. 15 (1), pp. 9660. Date of Electronic Publication: 2024 Nov 07.
DOI: 10.1038/s41467-024-54043-1
Abstrakt: Delays or misdiagnoses in detecting pneumoperitoneum can significantly increase mortality and morbidity. We developed and validated a deep learning model designed to identify pneumoperitoneum in computed tomography images. The model is trained on abdominal scans from Far Eastern Memorial Hospital (January 2012-December 2021) and evaluated using a simulated test set (14,039 scans) and a prospective test set (6351 scans) collected from the same center between December 2022 and May 2023. External validation included 480 scans from Cedars-Sinai Medical Center. Overall, the model achieves a sensitivity of 0.81-0.83 and a specificity of 0.97-0.99 across retrospective, prospective, and external validation; sensitivity improves to 0.92-0.98 when cases with a small amount of free air (total volume <10 ml) are excluded. These findings suggest that the model can deliver accurate and consistent predictions for pneumoperitoneum in computed tomography scans with segmented masks, potentially accelerating diagnostic and treatment workflows in emergency care.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: