建筑
人工智能
计算机科学
分割
网(多面体)
深度学习
图像(数学)
继任枢机主教
网络体系结构
图像分割
模式识别(心理学)
机器学习
数学
地理
数学分析
几何学
计算机安全
考古
作者
Nabil Ibtehaz,M. Sohel Rahman
标识
DOI:10.1016/j.neunet.2019.08.025
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI