U-Net: Convolutional Networks for Biomedical Image Segmentation

18 May 2015Olaf RonnebergerPhilipp FischerThomas Brox

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently... (read more)

PDF Abstract

Code


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) U-Net Dice 0.4606 # 6
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) U-Net IoU 0.3447 # 5
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) U-Net Precision 0.5994 # 3
Lesion Segmentation Anatomical Tracings of Lesions After Stroke (ATLAS) U-Net Recall 0.4449 # 6
Retinal Vessel Segmentation CHASE_DB1 U-Net F1 score 0.7783 # 5
Retinal Vessel Segmentation CHASE_DB1 U-Net AUC 0.9772 # 5
Pancreas Segmentation CT-150 U-Net Dice Score 0.814 # 2
Pancreas Segmentation CT-150 U-Net Precision 0.848 # 2
Pancreas Segmentation CT-150 U-Net Recall 0.806 # 2
Cell Segmentation DIC-HeLa U-Net Mean IoU 0.7756 # 1
Retinal Vessel Segmentation DRIVE U-Net F1 score 0.8142 # 5
Retinal Vessel Segmentation DRIVE U-Net AUC 0.9755 # 5
Medical Image Segmentation ISBI 2012 EM Segmentation U-Net Warping Error 0.000353 # 1
Skin Cancer Segmentation Kaggle Skin Lesion Segmentation U-Net F1 score 0.8682 # 3
Skin Cancer Segmentation Kaggle Skin Lesion Segmentation U-Net AUC 0.9371 # 3
Lung Nodule Segmentation LUNA U-Net F1 score 0.9658 # 3
Lung Nodule Segmentation LUNA U-Net AUC 0.9784 # 3
Cell Segmentation PhC-U373 U-Net Mean IoU 0.9203 # 1
Electron Microscopy Image Segmentation SNEMI3D U-Net AUC 0.8676 # 2
Retinal Vessel Segmentation STARE U-Net F1 score 0.8373 # 3
Retinal Vessel Segmentation STARE U-Net AUC 0.9898 # 2
Pancreas Segmentation TCIA Pancreas-CT Dataset U-Net Dice Score 0.820 # 3