Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation

20 Feb 2018Md Zahangir AlomMahmudul HasanChris YakopcicTarek M. TahaVijayan K. Asari

Deep learning (DL) based semantic segmentation methods have been providing state-of-the-art performance in the last few years. More specifically, these techniques have been successfully applied to medical image classification, segmentation, and detection tasks... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK LEADERBOARD
Retinal Vessel Segmentation CHASE_DB1 R2U-Net F1 score 0.7928 # 4
AUC 0.9815 # 4
Skin Cancer Segmentation Kaggle Skin Lesion Segmentation R2U-Net F1 score 0.8920 # 1
AUC 0.9419 # 1
Retinal Vessel Segmentation STARE R2U-Net F1 score 0.8475 # 1
AUC 0.9914 # 1