ResUNet++: An Advanced Architecture for Medical Image Segmentation

TL;DR

This paper introduces ResUNet++, an advanced deep learning architecture designed for precise polyp segmentation in colonoscopy images, significantly outperforming existing models like U-Net and ResUNet on benchmark datasets.

Contribution

ResUNet++ is a novel improved architecture that enhances polyp segmentation accuracy in colonoscopy images compared to prior models.

Findings

Achieved dice coefficient of 81.33% on Kvasir-SEG dataset

Achieved mIoU of 79.27% on Kvasir-SEG dataset

Outperformed U-Net and ResUNet architectures

Abstract

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. Our experimental evaluations show that the suggested architecture produces good segmentation results on publicly available datasets. Furthermore, ResUNet++ significantly outperforms U-Net and ResUNet, two key state-of-the-art deep learning architectures, by achieving high evaluation scores with a dice coefficient of 81.33%, and a mean Intersection over Union (mIoU) of 79.27% for the Kvasir-SEG dataset and a dice coefficient of 79.55%, and a mIoU of 79.62% with CVC-612 dataset.