Combining generative and discriminative models for semantic segmentation of CT scans via active learning

Mathematics

• Active Learning 100%
• Computed Tomography 90%
• Generative Models 89%
• Segmentation 76%
• Training 67%
• Semantics 54%
• Anatomy 35%
• Model 20%
• 3D Image 19%
• Quantitative Evaluation 19%
• Supervised Learning 18%
• Markov Random Field 16%
• Probabilistic Model 14%
• Classifier 14%
• Maximise 11%
• Divergence 11%
• Decrease 11%
• Smoothness 10%
• Framework 7%
• Subset 7%

Engineering & Materials Science

• Problem-Based Learning 72%
• Tomography 60%
• Semantics 43%
• Pathology 24%
• Supervised learning 22%
• Statistical Models 19%
• Classifiers 14%