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

• Published in: Nature communications Vol. 15; no. 1; pp. 9660 - 7
• Main Authors: Chiu, I-Min, Huang, Teng-Yi, Ouyang, David, Lin, Wei-Che, Pan, Yi-Ju, Lu, Chia-Yin, Kuo, Kuei-Hong
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 07.11.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 59; 631/114/1305; 692/700/1421/2025; Abdomen; Abdomen - diagnostic imaging; Adult; Aged; Algorithms; Computed tomography; Deep Learning; Emergency medical care; Emergency medical services; Female; Health care facilities; Health services; Humanities and Social Sciences; Humans; Machine learning; Male; Medical imaging; Middle Aged; Morbidity; multidisciplinary; Pneumoperitoneum - diagnostic imaging; Prospective Studies; Radiography, Abdominal - methods; Retrospective Studies; Science; Science (multidisciplinary); Sensitivity and Specificity; Test sets; Tomography; Tomography, X-Ray Computed - methods

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 (J...