ARPM-net: A novel CNN-based adversarial method with Markov Random Field enhancement for prostate and organs at risk segmentation in pelvic CT images.
Zhuangzhuang ZhangTianyu ZhaoHiram GayWeixiong ZhangBaozhou SunPublished in: CoRR (2020)
Keyphrases
- ct images
- markov random field
- energy function
- medical images
- mrf model
- pairwise
- medical imaging
- segmentation method
- image segmentation
- pet ct
- segmentation algorithm
- fully automatic
- ct scans
- higher order
- region of interest
- liver segmentation
- lung nodules
- edge detection
- anatomical knowledge
- treatment planning
- soft tissue
- computed tomography
- region growing
- prior information
- image processing
- graph cuts
- energy minimization
- multiscale
- image analysis
- object reconstruction
- prior knowledge
- similarity measure
- fracture detection