Universal conditional networks (UniCoN) for multi-age embryonic cartilage segmentation with Sparsely annotated data

Keyphrases

• Multi-age 100%
• Deep Learning Methods 100%
• Annotated Dataset 100%
• Cartilage Segmentation 100%
• Embryonic Cartilage 100%
• Cartilage 66%
• 3D micro-CT 66%
• Micro-CT Imaging 66%
• Malformation 33%
• Age Groups 33%
• Quality of Life 33%
• Popular 33%
• Mouse Model 33%
• Computation Overhead 33%
• Performance Improvement 33%
• Spatial Data 33%
• Model Performance 33%
• Unseen 33%
• Shape Change 33%
• Embryonic Mice 33%
• Reliable Performance 33%
• Continuous Images 33%
• Acquisition Cost 33%
• Convolutional Neural Network 33%
• Local Shape 33%
• Segmentation Problem 33%
• Child Morbidity 33%
• Age Categories 33%
• Universal Model 33%
• Deep Learning 33%
• Diverse Datasets 33%
• Bone Disorders 33%
• Embryo Age 33%
• Automatic Image Annotation 33%
• Medical Image Analysis 33%
• Dice Score 33%
• Novel Deep Learning Methods 33%
• Segmentation Dataset 33%
• Deep Learning Segmentation 33%

Computer Science

• Deep Learning Method 100%
• Image Analysis 16%
• Performance Improvement 16%
• Spatial Information 16%
• Learning Approach 16%
• Performance Model 16%
• Generalizability 16%
• Image Annotation 16%
• face model 16%
• Segmentation Task 16%
• Convolutional Neural Network 16%
• Universal Model 16%

Biochemistry, Genetics and Molecular Biology

• Micro-Computed Tomography 100%
• Mouse Model 50%