Deep learning in mammography images segmentation and classification: Automated CNN approach

In this work, a new framework for breast cancer image segmentation and classification is proposed. Different models including InceptionV3, DenseNet121, ResNet50, VGG16 and MobileNetV2 models, are applied to classify Mammographic Image Analysis Society (MIAS), Digital Database for Screening Mammograp...

Full description

Bibliographic Details
Main Authors: Wessam M. Salama, Moustafa H. Aly
Format: Article
Language:English
Published: Elsevier 2021-10-01
Series:Alexandria Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016821002027
_version_ 1819295417618137088
author Wessam M. Salama
Moustafa H. Aly
author_facet Wessam M. Salama
Moustafa H. Aly
author_sort Wessam M. Salama
collection DOAJ
description In this work, a new framework for breast cancer image segmentation and classification is proposed. Different models including InceptionV3, DenseNet121, ResNet50, VGG16 and MobileNetV2 models, are applied to classify Mammographic Image Analysis Society (MIAS), Digital Database for Screening Mammography (DDSM) and the Curated Breast Imaging Subset of DDSM (CBIS-DDSM) into benign and malignant. Moreover, the trained modified U-Net model is utilized to segment breast area from the mammogram images. This method will aid as a radiologist's assistant in early detection and improve the efficiency of our system. The Cranio Caudal (CC) vision and Mediolateral Oblique (MLO) view are widely used for the identification and diagnosis of breast cancer. The accuracy of breast cancer diagnosis will be improved as the number of views is increased. Our proposed frame work is based on MLO view and CC view to enhance the system performance. In addition, the lack of tagged data is a big challenge. Transfer learning and data augmentation are applied to overcome this problem. Three mammographic datasets; MIAS, DDSM and CBIS-DDSM, are utilized in our evaluation. End-to-end fully convolutional neural networks (CNNs) are introduced in this paper. The proposed technique of applying data augmentation with modified U-Net model and InceptionV3 achieves the best result, specifically with the DDSM dataset. This achieves 98.87% accuracy, 98.88% area under the curve (AUC), 98.98% sensitivity, 98.79% precision, 97.99% F1 score, and a computational time of 1.2134 s on DDSM datasets.
first_indexed 2024-12-24T04:41:53Z
format Article
id doaj.art-3edf7e99ba4141eb9977fe3ff3c8ed0f
institution Directory Open Access Journal
issn 1110-0168
language English
last_indexed 2024-12-24T04:41:53Z
publishDate 2021-10-01
publisher Elsevier
record_format Article
series Alexandria Engineering Journal
spelling doaj.art-3edf7e99ba4141eb9977fe3ff3c8ed0f2022-12-21T17:14:48ZengElsevierAlexandria Engineering Journal1110-01682021-10-0160547014709Deep learning in mammography images segmentation and classification: Automated CNN approachWessam M. Salama0Moustafa H. Aly1Department of Basic Science, Faculty of Engineering, Pharos University, Alexandria, Egypt; Corresponding author at: Department of Electronics and Communications, College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Alexandria, Egypt.Department of Electronics and Communications Engineering, College of Engineering and Technology, Arab Academy for Science, Technology and Maritime Transport, Alexandria, EgyptIn this work, a new framework for breast cancer image segmentation and classification is proposed. Different models including InceptionV3, DenseNet121, ResNet50, VGG16 and MobileNetV2 models, are applied to classify Mammographic Image Analysis Society (MIAS), Digital Database for Screening Mammography (DDSM) and the Curated Breast Imaging Subset of DDSM (CBIS-DDSM) into benign and malignant. Moreover, the trained modified U-Net model is utilized to segment breast area from the mammogram images. This method will aid as a radiologist's assistant in early detection and improve the efficiency of our system. The Cranio Caudal (CC) vision and Mediolateral Oblique (MLO) view are widely used for the identification and diagnosis of breast cancer. The accuracy of breast cancer diagnosis will be improved as the number of views is increased. Our proposed frame work is based on MLO view and CC view to enhance the system performance. In addition, the lack of tagged data is a big challenge. Transfer learning and data augmentation are applied to overcome this problem. Three mammographic datasets; MIAS, DDSM and CBIS-DDSM, are utilized in our evaluation. End-to-end fully convolutional neural networks (CNNs) are introduced in this paper. The proposed technique of applying data augmentation with modified U-Net model and InceptionV3 achieves the best result, specifically with the DDSM dataset. This achieves 98.87% accuracy, 98.88% area under the curve (AUC), 98.98% sensitivity, 98.79% precision, 97.99% F1 score, and a computational time of 1.2134 s on DDSM datasets.http://www.sciencedirect.com/science/article/pii/S1110016821002027MammographyBreast cancerSegmentationDeep learningU-NetTransfer learning
spellingShingle Wessam M. Salama
Moustafa H. Aly
Deep learning in mammography images segmentation and classification: Automated CNN approach
Alexandria Engineering Journal
Mammography
Breast cancer
Segmentation
Deep learning
U-Net
Transfer learning
title Deep learning in mammography images segmentation and classification: Automated CNN approach
title_full Deep learning in mammography images segmentation and classification: Automated CNN approach
title_fullStr Deep learning in mammography images segmentation and classification: Automated CNN approach
title_full_unstemmed Deep learning in mammography images segmentation and classification: Automated CNN approach
title_short Deep learning in mammography images segmentation and classification: Automated CNN approach
title_sort deep learning in mammography images segmentation and classification automated cnn approach
topic Mammography
Breast cancer
Segmentation
Deep learning
U-Net
Transfer learning
url http://www.sciencedirect.com/science/article/pii/S1110016821002027
work_keys_str_mv AT wessammsalama deeplearninginmammographyimagessegmentationandclassificationautomatedcnnapproach
AT moustafahaly deeplearninginmammographyimagessegmentationandclassificationautomatedcnnapproach