IRUNet for medical image segmentation

作者：

Highlights：

• A new architecture, IRUNet, for medical image segmentation.

• Integration of EfficientNet, ResNet and Inception layers into the UNet.

• Multiscale feature extraction for better segmentation.

• Introducing a new weighted Loss function.

• Improving the results by conditional random field (CRF).

摘要

•A new architecture, IRUNet, for medical image segmentation.•Integration of EfficientNet, ResNet and Inception layers into the UNet.•Multiscale feature extraction for better segmentation.•Introducing a new weighted Loss function.•Improving the results by conditional random field (CRF).

论文关键词：Semantic segmentation,Microscopic images,IRUNet,Inception block,Residual block,EfficientNet,Anthrax disease

论文评审过程：Received 30 April 2021, Revised 28 August 2021, Accepted 10 December 2021, Available online 16 December 2021, Version of Record 31 December 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116399