Breast Pectoral Muscle Segmentation in Mammograms using a Modified Holistically-nested Edge Detection Network

Authors: Andrik Rampun Karen López-Linares Román Philip J. Morrow Bryan W. Scotney Hui Wang Grégory Maclair Reyes Zwiggelaar Miguel A. González Ballester Iván Macía Oliver

Date: 01.10.2019

Medical Image Analysis


Abstract

This paper presents a method for automatic breast pectoral muscle segmentation in mediolateral oblique mammograms using a Convolutional Neural Network (CNN) inspired by the Holistically-nested Edge Detection (HED) network. Most of the existing methods in the literature are based on hand-crafted models such as straight-line, curve-based techniques or a combination of both. Unfortunately, such models are insufficient when dealing with complex shape variations of the pectoral muscle boundary and when the boundary is unclear due to overlapping breast tissue. To compensate for these issues, we propose a neural network framework that incorporates multi-scale and multi-level learning, capable of learning complex hierarchical features to resolve spatial ambiguity in estimating the pectoral muscle boundary. For this purpose, we modified the HED network architecture to specifically find ‘contour-like’ objects in mammograms. The proposed framework produced a probability map that can be used to estimate the initial pectoral muscle boundary. Subsequently, we process these maps by extracting morphological properties to find the actual pectoral muscle boundary. Finally, we developed two different post-processing steps to find the actual pectoral muscle boundary. Quantitative evaluation results show that the proposed method is comparable with alternative state-of-the-art methods producing on average values of 94.8 ± 8.5% and 97.5 ± 6.3% for the Jaccard and Dice similarity metrics, respectively, across four different databases.

BIB_text

@Article {
title = {Breast Pectoral Muscle Segmentation in Mammograms using a Modified Holistically-nested Edge Detection Network},
journal = {Medical Image Analysis},
pages = {1-17},
volume = {57},
keywds = {
Breast mammography Pectoral Muscle Segmentation Computer Aided Diagnosis Convolutional Neural Networks Deep learning
}
abstract = {

This paper presents a method for automatic breast pectoral muscle segmentation in mediolateral oblique mammograms using a Convolutional Neural Network (CNN) inspired by the Holistically-nested Edge Detection (HED) network. Most of the existing methods in the literature are based on hand-crafted models such as straight-line, curve-based techniques or a combination of both. Unfortunately, such models are insufficient when dealing with complex shape variations of the pectoral muscle boundary and when the boundary is unclear due to overlapping breast tissue. To compensate for these issues, we propose a neural network framework that incorporates multi-scale and multi-level learning, capable of learning complex hierarchical features to resolve spatial ambiguity in estimating the pectoral muscle boundary. For this purpose, we modified the HED network architecture to specifically find ‘contour-like’ objects in mammograms. The proposed framework produced a probability map that can be used to estimate the initial pectoral muscle boundary. Subsequently, we process these maps by extracting morphological properties to find the actual pectoral muscle boundary. Finally, we developed two different post-processing steps to find the actual pectoral muscle boundary. Quantitative evaluation results show that the proposed method is comparable with alternative state-of-the-art methods producing on average values of 94.8 ± 8.5% and 97.5 ± 6.3% for the Jaccard and Dice similarity metrics, respectively, across four different databases.


}
doi = {https://doi.org/10.1016/j.media.2019.06.007},
date = {2019-10-01},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (Spain)

+(34) 943 309 230

Zorrotzaurreko Erribera 2, Deusto,
48014 Bilbao (Spain)

close overlay

Behavioral advertising cookies are necessary to load this content

Accept behavioral advertising cookies