Clinical validation of AI assisted animal ultrasound models for diagnosis of early liver trauma.
Authors
Affiliations (9)
Affiliations (9)
- Department of Ultrasound, First Medical Center of General Hospital of Chinese PLA, Beijing, 100853, China.
- Department of Ultrasound, Seventh Medical Center, General Hospital of Chinese PLA, Beijing, 100700, China.
- School of Information Sciences and Technology, Northwest University, Xi'an, 710127, Shaanxi Province, China.
- CAS Key Laboratory of Molecular Imaging, State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China.
- Department of Ultrasound, Shandong Province Maternal and Child Health Care Hospital, Jinan, 250014, China.
- Department of Ultrasound, Second Medical Center, General Hospital of Chinese PLA, Beijing, 100700, China.
- Beijing Da Wang Lu Emergency Hospital, Beijing, China.
- Department of Ultrasound, First Medical Center of General Hospital of Chinese PLA, Beijing, 100853, China. [email protected].
- CAS Key Laboratory of Molecular Imaging, State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China. [email protected].
Abstract
The study aimed to develop an AI-assisted ultrasound model for early liver trauma identification, using data from Bama miniature pigs and patients in Beijing, China. A deep learning model was created and fine-tuned with animal and clinical data, achieving high accuracy metrics. In internal tests, the model outperformed both Junior and Senior sonographers. External tests showed the model's effectiveness, with a Dice Similarity Coefficient of 0.74, True Positive Rate of 0.80, Positive Predictive Value of 0.74, and 95% Hausdorff distance of 14.84. The model's performance was comparable to Junior sonographers and slightly lower than Senior sonographers. This AI model shows promise for liver injury detection, offering a valuable tool with diagnostic capabilities similar to those of less experienced human operators.