Three-dimensional affinity learning based multi-branch ensemble network for breast tumor segmentation in MRI

作者：

Highlights：

• We propose a multi-branch network for breast tumor segmentation.

• A trainable 3D affinity learning based segmentation refinement module is designed.

• A hierarchial ensemble strategy is designed to combine two subnetworks comprehensively.

• The state-of-the-art performance for breast tumor segmentation in MRI is achieved.

摘要

•We propose a multi-branch network for breast tumor segmentation.•A trainable 3D affinity learning based segmentation refinement module is designed.•A hierarchial ensemble strategy is designed to combine two subnetworks comprehensively.•The state-of-the-art performance for breast tumor segmentation in MRI is achieved.

论文关键词：Breast tumor segmentation,Three-dimensional affinity learning based refinement,Multi-branch ensemble network

论文评审过程：Received 9 December 2021, Revised 2 April 2022, Accepted 19 April 2022, Available online 22 April 2022, Version of Record 28 April 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108723