A Deep Residual U-Net Algorithm for Automatic Detection and Quantification of Ascites on Abdominopelvic Computed Tomography Images Acquired in the Emergency Department: Model Development and Validation.
Hoon KoJimi HuhKyoung Won KimHeewon ChungYousun KoJai Keun KimJei Hee LeeJin Seok LeePublished in: Journal of medical Internet research (2022)
We propose a deep residual U-Net-based AI algorithm for automatic detection and quantification of ascites on abdominopelvic CT scans, which provides excellent performance.
Keyphrases
- deep learning
- computed tomography
- machine learning
- emergency department
- artificial intelligence
- dual energy
- contrast enhanced
- convolutional neural network
- positron emission tomography
- loop mediated isothermal amplification
- neural network
- image quality
- magnetic resonance imaging
- cell free
- real time pcr
- label free
- optical coherence tomography
- sensitive detection