Usefulness of fine-tuning for deep learning based multi-organ regions segmentation method from non-contrast CT volumes using small training dataset.
Yuichiro HayashiChen ShenHolger R. RothMasahiro OdaKazunari MisawaMasahiro JinzakiMasahiro HashimotoKanako K. KumamaruShigeki AokiKensaku MoriPublished in: Medical Imaging: Computer-Aided Diagnosis (2020)
Keyphrases
- segmentation method
- fine tuning
- deep learning
- training dataset
- segmentation scheme
- watershed segmentation
- medical images
- training data
- unsupervised learning
- segmentation algorithm
- region growing
- object segmentation
- active contours
- image segmentation
- energy function
- superpixels
- weakly supervised
- machine learning
- ct images
- training samples
- shape prior
- computed tomography
- medical imaging
- region of interest
- input image
- training set
- mental models
- small number
- automatic segmentation
- deformable models
- anatomical structures
- x ray
- feature space
- image processing