Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound images

Breast cancer remains one of the leading causes of mortality among women worldwide, highlighting the need for timely and accurate diagnostic strategies. This study investigates the integration of artificial intelligence (AI) techniques, specifically deep transfer learning for classification and U-Ne...

Full description

Saved in:
Bibliographic Details
Main Authors: Divine Senanu Ametefe, Dah John, Abdulmalik Adozuka Aliu, George Dzorgbenya Ametefe, Aisha Hamid, Tumani Darboe
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025011223
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713981614194688
author Divine Senanu Ametefe
Dah John
Abdulmalik Adozuka Aliu
George Dzorgbenya Ametefe
Aisha Hamid
Tumani Darboe
author_facet Divine Senanu Ametefe
Dah John
Abdulmalik Adozuka Aliu
George Dzorgbenya Ametefe
Aisha Hamid
Tumani Darboe
author_sort Divine Senanu Ametefe
collection DOAJ
description Breast cancer remains one of the leading causes of mortality among women worldwide, highlighting the need for timely and accurate diagnostic strategies. This study investigates the integration of artificial intelligence (AI) techniques, specifically deep transfer learning for classification and U-Net for segmentation to improve breast cancer diagnosis using ultrasound imaging. A curated dataset of breast ultrasound images, categorized as normal, benign, or malignant, was used for model evaluation. Three pre-trained convolutional neural networks (CNNs), including VGG16, VGG19, and EfficientNet were implemented within a deep transfer learning framework due to their strong feature extraction capabilities. In parallel, the U-Net model, recognized for its effectiveness in medical image segmentation, was employed to delineate tumour boundaries with high spatial precision. Among the CNN models, VGG19 achieved the best performance, with the highest weighted accuracy, precision, and recall. U-Net attained an average Dice Similarity Coefficient of 85.97 %, underscoring its proficiency in segmenting tumour regions across varying lesion types. These AI-based models offer a robust diagnostic pipeline that improves lesion localization, reduces interobserver variability, and supports clinical decision-making. The approach aligns with Sustainable Development Goal (SDG) 3 by promoting early detection and better health outcomes, and SDG 9 through the adoption of innovative AI technologies in healthcare. However, limitations persist, including computational demands, class imbalance, and the lack of dataset diversity, which may affect generalizability. Addressing these challenges is essential for the safe and effective deployment of AI in real-world clinical settings.
format Article
id doaj-art-c7ea6413b28b4bf39bd33132c67cd758
institution DOAJ
issn 2590-1230
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-c7ea6413b28b4bf39bd33132c67cd7582025-08-20T03:13:49ZengElsevierResults in Engineering2590-12302025-06-012610504710.1016/j.rineng.2025.105047Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound imagesDivine Senanu Ametefe0Dah John1Abdulmalik Adozuka Aliu2George Dzorgbenya Ametefe3Aisha Hamid4Tumani Darboe5Wireless Communication Technology Group (WiCOT), College of Engineering, School of Electrical Engineering, Universiti Teknologi MARA (UiTM), 40450 Shah Alam, Selangor, MalaysiaCollege of Computing, Informatics, and Mathematics, Universiti Teknologi MARA (UiTM), 40150 Puncak Perdana, Selangor, MalaysiaCollege of Built Environment, Universiti Teknologi MARA (UiTM), 40450 Shah Alam, Selangor, MalaysiaDepartment of Biotechnology, College of Science, Engineering and Technology, Osun State University, Osogbo, NigeriaSchool of Chemistry and Environment, Faculty of Applied Sciences, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, MalaysiaSchool of Business and Public Administration, University of The Gambia, Kanifing Campus, West Coast Region, The Gambia; Corresponding author.Breast cancer remains one of the leading causes of mortality among women worldwide, highlighting the need for timely and accurate diagnostic strategies. This study investigates the integration of artificial intelligence (AI) techniques, specifically deep transfer learning for classification and U-Net for segmentation to improve breast cancer diagnosis using ultrasound imaging. A curated dataset of breast ultrasound images, categorized as normal, benign, or malignant, was used for model evaluation. Three pre-trained convolutional neural networks (CNNs), including VGG16, VGG19, and EfficientNet were implemented within a deep transfer learning framework due to their strong feature extraction capabilities. In parallel, the U-Net model, recognized for its effectiveness in medical image segmentation, was employed to delineate tumour boundaries with high spatial precision. Among the CNN models, VGG19 achieved the best performance, with the highest weighted accuracy, precision, and recall. U-Net attained an average Dice Similarity Coefficient of 85.97 %, underscoring its proficiency in segmenting tumour regions across varying lesion types. These AI-based models offer a robust diagnostic pipeline that improves lesion localization, reduces interobserver variability, and supports clinical decision-making. The approach aligns with Sustainable Development Goal (SDG) 3 by promoting early detection and better health outcomes, and SDG 9 through the adoption of innovative AI technologies in healthcare. However, limitations persist, including computational demands, class imbalance, and the lack of dataset diversity, which may affect generalizability. Addressing these challenges is essential for the safe and effective deployment of AI in real-world clinical settings.http://www.sciencedirect.com/science/article/pii/S2590123025011223Breast cancer diagnosisDeep transfer learningU-net segmentationMedical image classificationArtificial intelligence in healthcareConvolutional neural network (CNN)
spellingShingle Divine Senanu Ametefe
Dah John
Abdulmalik Adozuka Aliu
George Dzorgbenya Ametefe
Aisha Hamid
Tumani Darboe
Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound images
Results in Engineering
Breast cancer diagnosis
Deep transfer learning
U-net segmentation
Medical image classification
Artificial intelligence in healthcare
Convolutional neural network (CNN)
title Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound images
title_full Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound images
title_fullStr Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound images
title_full_unstemmed Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound images
title_short Advancing breast cancer diagnosis: Integrating deep transfer learning and U-Net segmentation for precise classification and delineation of ultrasound images
title_sort advancing breast cancer diagnosis integrating deep transfer learning and u net segmentation for precise classification and delineation of ultrasound images
topic Breast cancer diagnosis
Deep transfer learning
U-net segmentation
Medical image classification
Artificial intelligence in healthcare
Convolutional neural network (CNN)
url http://www.sciencedirect.com/science/article/pii/S2590123025011223
work_keys_str_mv AT divinesenanuametefe advancingbreastcancerdiagnosisintegratingdeeptransferlearningandunetsegmentationforpreciseclassificationanddelineationofultrasoundimages
AT dahjohn advancingbreastcancerdiagnosisintegratingdeeptransferlearningandunetsegmentationforpreciseclassificationanddelineationofultrasoundimages
AT abdulmalikadozukaaliu advancingbreastcancerdiagnosisintegratingdeeptransferlearningandunetsegmentationforpreciseclassificationanddelineationofultrasoundimages
AT georgedzorgbenyaametefe advancingbreastcancerdiagnosisintegratingdeeptransferlearningandunetsegmentationforpreciseclassificationanddelineationofultrasoundimages
AT aishahamid advancingbreastcancerdiagnosisintegratingdeeptransferlearningandunetsegmentationforpreciseclassificationanddelineationofultrasoundimages
AT tumanidarboe advancingbreastcancerdiagnosisintegratingdeeptransferlearningandunetsegmentationforpreciseclassificationanddelineationofultrasoundimages