The contrast-enhanced MRI can be substituted by unenhanced MRI in identifying and automatically segmenting primary nasopharyngeal carcinoma with the aid of deep learning models: An exploratory study in large-scale population of endemic area.
Yishu DengChaofeng LiXing LvWeixiong XiaLujun ShenBing-Zhong JingBin LiXiang GuoYing SunChuanmiao XieLiangru KePublished in: Comput. Methods Programs Biomed. (2022)
Keyphrases
- learning models
- automatically segmenting
- adipose tissue
- mr images
- magnetic resonance imaging
- mri data
- contrast enhanced
- automatic segmentation
- manual segmentation
- carotid artery
- medical images
- magnetic resonance images
- learning tasks
- learning algorithm
- ct data
- medical imaging
- magnetic resonance
- machine learning
- loss function
- computed tomography
- semi supervised learning
- real world
- magnetic resonance angiography
- nonrigid registration
- high resolution
- white matter
- image data
- data sets