Performance Deterioration of Deep Learning Models after Clinical Deployment: A Case Study with Auto-segmentation for Definitive Prostate Cancer Radiotherapy.
Biling WangMichael DohopolskiTi BaiJunjie WuRaquibul HannanNeil DesaiAurelie GarantDan NguyenXinlei WangMu-Han LinRobert TimmermanSteve JiangPublished in: CoRR (2022)
Keyphrases
- prostate cancer
- learning models
- cancer patients
- image guided
- prostate segmentation
- mr images
- treatment planning
- computer aided
- survival data
- loss function
- dce mri
- deformable registration
- machine learning
- medical images
- accurate segmentation
- learning tasks
- medical image analysis
- learning algorithm
- conditional random fields
- semi supervised learning
- radiation therapy
- segmentation method
- learning problems
- level set
- classification models
- image analysis
- machine learning algorithms
- segmentation algorithm
- treatment plan
- medical imaging
- magnetic resonance spectroscopy
- image segmentation
- data points
- radiotherapy treatment
- segmentation result
- clinical data
- magnetic resonance images
- automatic segmentation
- magnetic resonance
- pairwise
- support vector