SAPSAM - Sparsely Annotated Pathological Sign Activation Maps - A novel approach to train Convolutional Neural Networks on lung CT scans using binary labels only.
Mario ZusagSujal R. DesaiMarcello Di PaoloThomas SempleAnand ShahElsa D. AngeliniPublished in: CoRR (2019)
Keyphrases
- ct scans
- convolutional neural networks
- ct images
- computed tomography
- x ray
- ct data
- convolutional network
- computer aided diagnosis
- automated segmentation
- medical images
- computer tomography
- ground truth labels
- rigid registration
- registration process
- region of interest
- computer aided detection
- registration accuracy
- low dose
- treatment planning
- pairwise
- pulmonary nodules
- image reconstruction
- training data
- computer aided
- medical imaging
- multiscale
- abdominal organs