Employing transfer learning for breast cancer detection using deep learning models

Frimpong Twum, Charlyne Carol Eyram Ahiable, Stephen Opoku Oppong, Linda Banning and Kwabena Owusu-Agyemang

PLOS Digital Health, 2025, vol. 4, issue 6, 1-22

Abstract: Breast cancer remains a critical global health concern, affecting countless lives worldwide. Early and accurate detection plays a vital role in improving patient outcomes. The challenge lies with the limitations of traditional diagnostic methods in terms of accuracy. This study proposes a novel model based on the four pretrained deep learning models, Mobilenetv2, Inceptionv3, ResNet50, and VGG16, which were also used as feature extractors and fed on multiple supervised learning models using the BUSI dataset. Mobiletnetv2, inceptionv3, ResNet50 and VGG16 achieved an accuracy of 85.6%, 90.8%, 89.7% and 88.06%, respectively, with Logistic Regression and Light Gradient Boosting Machine being the best performing classifiers. Using transfer learning, the top layers of the model were frozen, and additional layers were added. A GlobalAveragePooling2D layer was employed to reduce spatial dimensions of the input image. After training and testing based on the accuracy, ResNet50 performed the best with 95.5%, followed by Inceptionv3 92.5%, VGG16 86.5% and lastly Mobilenetv2 84%.Author summary: Breast cancer is one of the leading causes of mortality among women worldwide, and early detection plays a crucial role in improving survival rates. In this study, we explore the use of transfer learning, a technique that leverages pretrained deep learning models, to improve breast cancer classification using ultrasound images. We compare four well-established models—MobileNetV2, InceptionV3, ResNet50, and VGG16—evaluating their effectiveness in both feature extraction and fine-tuning approaches. Our findings show that ResNet50 and InceptionV3 outperform other models in accuracy, specificity, and robustness, making them strong candidates for clinical applications. MobileNetV2, while slightly less accurate, offers computational efficiency, making it suitable for real-time or resource-limited settings. By providing a comprehensive comparison of these models, our study contributes to the development of AI-driven breast cancer detection tools that can aid in faster, more reliable diagnoses.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0000907 (text/html)
https://journals.plos.org/digitalhealth/article/fi ... 00907&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pdig00:0000907

DOI: 10.1371/journal.pdig.0000907

Access Statistics for this article

More articles in PLOS Digital Health from Public Library of Science
Bibliographic data for series maintained by digitalhealth ().