A Second-Order Subregion Pooling Network for Breast Lesion Segmentation in Ultrasound
Other conference paper

Altmetrics Information
.

Other information
AbstractBreast lesion segmentation in ultrasound images is a fundamental task for clinical diagnosis of the disease. Unfortunately, existing methods mainly rely on the entire image to learn the global context information, which neglects the spatial relation and results in ambiguity in the segmentation results. In this paper, we propose a novel second-order subregion pooling network (S2P -Net) for boosting the breast lesion segmentation in ultrasound images. In our S2P -Net, an attention-weighted subregion pooling (ASP) module is introduced in each encoder block of segmentation network to refine features by aggregating global features from the whole image and local information of subregions. Moreover, in each subregion, a guided multi-dimension second-order pooling (GMP) block is designed to leverage additional guidance information and multiple feature dimensions to learn powerful second-order covariance representations. Experimental results on two datasets demonstrate that our proposed S2P -Net outperforms state-of-the-art methods.
All Author(s) ListZhu L., Chen R., Fu H., Xie C., Wang L., Wan L., Heng P. A.
Name of ConferenceMICCAI 2020
Start Date of Conference04/10/2020
End Date of Conference08/10/2020
Place of ConferencePERU
Country/Region of ConferencePeru
Proceedings TitleLecture Notes in Computer Science
Year2020
Volume Number12266
PublisherSpringer
Pages160 - 170
ISBN978-3-030-59724-5
eISBN978-3-030-59725-2
LanguagesEnglish-United Kingdom
KeywordsUltrasound image, Breast lesion segmentation, Second-order subregion pooling

Last updated on 2021-21-04 at 23:30