ResUNet++: An Advanced Architecture for Medical Image Segmentation

16 Nov 2019Debesh JhaPia H. SmedsrudMichael A. RieglerDag JohansenThomas de LangePal HalvorsenHavard D. Johansen

Accurate computer-aided polyp detection and segmentation during colonoscopy examinations can help endoscopists resect abnormal tissue and thereby decrease chances of polyps growing into cancer. Towards developing a fully automated model for pixel-wise polyp segmentation, we propose ResUNet++, which is an improved ResUNet architecture for colonoscopic image segmentation... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Medical Image Segmentation Kvasir-SEG ResUNet++ mean Dice 0.8133 # 4

Methods used in the Paper