Enhancing breast pectoral muscle segmentation performance by using skip connections in fully convolutional network

The precise detection and segmentation of pectoral muscle areas in mediolateral oblique (MLO) views is an essential step in the development of a computer‐aided diagnosis system to access breast malignant lesions or parenchyma. The goal of this article is to develop a robust and fully automatic algor...

Full description

Saved in:
Bibliographic Details
Published in:International journal of imaging systems and technology 2020-12, Vol.30 (4), p.1108-1118
Main Authors: Ali, Muhammad Junaid, Raza, Basit, Shahid, Ahmad Raza, Mahmood, Fahad, Yousuf, Muhammad Adil, Dar, Amir Hanif, Iqbal, Uzair
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial neural networks
Breast
Computer architecture
digital mammography
Ground truth
Image enhancement
Image quality
Image segmentation
Model testing
Muscles
pectoral muscle segmentation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The precise detection and segmentation of pectoral muscle areas in mediolateral oblique (MLO) views is an essential step in the development of a computer‐aided diagnosis system to access breast malignant lesions or parenchyma. The goal of this article is to develop a robust and fully automatic algorithm for pectoral muscle segmentation from mammography images. This paper presents an image enhancement approach that improves the quality of mammogram scans and a convolutional neural network‐based fully convolutional network architecture enhanced with residual connections for automatic segmentation of the pectoral muscle from the MLO views of a digital mammogram. For this purpose, the model is tested and trained on three different mammogram datasets named MIAS, INBREAST, and DDSM. The ground truth labels of the pectoral muscle were identified under the supervision of experienced radiologists. For training and testing, 10‐fold cross‐validation was used. The proposed model was compared with baseline U‐Net‐based architecture. Finally, we used a postprocessing step to find the actual boundary of the pectoral muscle. Our presented architecture generated a mean Intersection over Union (IoU) of 97%, dice similarity coefficient (DSC) of 96% and 98% accuracy on testing data. The proposed architecture for pectoral muscle segmentation from the MLO views of mammogram images with high accuracy and dice score can be quickly merged with the breast tumor segmentation problem.
ISSN:0899-9457
1098-1098
DOI:10.1002/ima.22410