# MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation

## TL;DR

MultiResUNet introduces modifications to the classic U-Net architecture, significantly enhancing segmentation performance on challenging multimodal medical images across various datasets.

## Contribution

The paper proposes the MultiResUNet architecture, a novel improvement over U-Net, tailored for better segmentation of complex multimodal medical images.

## Key findings

- Remarkable performance gains on challenging images
- Relative improvement up to 10.15% across datasets
- Slight improvements on ideal images

## Abstract

In recent years Deep Learning has brought about a breakthrough in Medical Image Segmentation. U-Net is the most prominent deep network in this regard, which has been the most popular architecture in the medical imaging community. Despite outstanding overall performance in segmenting multimodal medical images, from extensive experimentations on challenging datasets, we found out that the classical U-Net architecture seems to be lacking in certain aspects. Therefore, we propose some modifications to improve upon the already state-of-the-art U-Net model. Hence, following the modifications we develop a novel architecture MultiResUNet as the potential successor to the successful U-Net architecture. We have compared our proposed architecture MultiResUNet with the classical U-Net on a vast repertoire of multimodal medical images. Albeit slight improvements in the cases of ideal images, a remarkable gain in performance has been attained for challenging images. We have evaluated our model on five different datasets, each with their own unique challenges, and have obtained a relative improvement in performance of 10.15%, 5.07%, 2.63%, 1.41%, and 0.62% respectively.