Multiclass deep active learning for detecting red blood cell subtypes in brightfield microscopy

Keyphrases

• Active Learning Framework 33%
• Annotated Dataset 33%
• Annotated Images 33%
• Biomedical Images 33%
• Blood Disorders 33%
• Bright-field Image 33%
• Bright-field Microscopy 100%
• Cell Speed 33%
• Cell Subtypes 100%
• Confidence Score 33%
• Deep Active Learning 100%
• Deep Learning Methods 33%
• Detection Problem 33%
• Dropout 33%
• Efficient Annotation 33%
• Expert Annotation 33%
• Faster R-CNN 33%
• Image Object 33%
• Large Set 33%
• Multi-class 100%
• Multi-class Detection 33%
• Natural Images 33%
• Object Annotation 33%
• Prediction Accuracy 33%
• Red Blood Cells 100%
• Relevant Images 33%
• Single Cell Classification 33%
• Single Cell Identification 33%
• Single-cell Detection 33%
• Training Data 66%
• Variational Inference 33%

Computer Science

• Active Learning 16%
• Annotation 100%
• Cell Identification 16%
• Confidence Score 16%
• Convolutional Neural Network 16%
• Deep Active Learning 100%
• Deep Learning Method 16%
• Learning Approach 16%
• Learning Framework 16%
• Prediction Accuracy 16%
• Speed-up 16%
• Training Data 33%

Biochemistry, Genetics and Molecular Biology

• Hemocyte 100%