Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networks

Breast cancer is cancer that forms in the cells of the breasts and is a severe health issue that affects many people around the world, especially since it is the most deadly cancer in women. By finding it early and using new treatments, patients can overcome this challenge and get back to a healthie...

Full description

Saved in:
Bibliographic Details
Main Authors: Huong Hoang Luong, Hai Thanh Nguyen, Nguyen Thai-Nghe
Format: Article
Language:English
Published: Taylor & Francis Group 2025-04-01
Series:Journal of Information and Telecommunication
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/24751839.2024.2415033
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850128738462728192
author Huong Hoang Luong
Hai Thanh Nguyen
Nguyen Thai-Nghe
author_facet Huong Hoang Luong
Hai Thanh Nguyen
Nguyen Thai-Nghe
author_sort Huong Hoang Luong
collection DOAJ
description Breast cancer is cancer that forms in the cells of the breasts and is a severe health issue that affects many people around the world, especially since it is the most deadly cancer in women. By finding it early and using new treatments, patients can overcome this challenge and get back to a healthier life. This study proposed a procedure to fine-tune the Convolutional Neural Networks (CNN) model with data preprocessing and augmentation in classifying mammogram images called the Hybrid Mammogram Classification and Detection Pipeline (HMCaD). After using CNN for classification because it brings higher confidence in classifying tasks, the YOLOv8 has been applied for localization subtask to detect abnormal positions with predicted bounding boxes. The database is provided by the Mammographic Image Analysis Society (MIAS) and is protected by the United Kingdom. It comprises 330 samples, including 79 benign, 54 malignant, and 207 normal images. As a result, the classification in our model based on the custom EfficientNetB3 model and seam carving technique received a great validation accuracy, test accuracy, and F1 score throughout three scenarios at 96.73%, 97.59%, and 97.58%, respectively. Furthermore, the area under the Receiver Operating Characteristic (ROC) curve also has a surprise result of 0.96 (i.e. [Formula: see text]). Moreover, YOLOv8 for detecting abnormal positions in our study achieved 83.22% in Intersection over Union (IoU). This led to the research reaching good results in classifying and detecting breast cancer by considering several performance metrics.
format Article
id doaj-art-95ea48cb40a3485c862d1d435c4e4ff8
institution OA Journals
issn 2475-1839
2475-1847
language English
publishDate 2025-04-01
publisher Taylor & Francis Group
record_format Article
series Journal of Information and Telecommunication
spelling doaj-art-95ea48cb40a3485c862d1d435c4e4ff82025-08-20T02:33:11ZengTaylor & Francis GroupJournal of Information and Telecommunication2475-18392475-18472025-04-019220923610.1080/24751839.2024.2415033Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networksHuong Hoang Luong0Hai Thanh Nguyen1Nguyen Thai-Nghe2College of ICT, Can Tho University, Can Tho, VietnamCollege of ICT, Can Tho University, Can Tho, VietnamCollege of ICT, Can Tho University, Can Tho, VietnamBreast cancer is cancer that forms in the cells of the breasts and is a severe health issue that affects many people around the world, especially since it is the most deadly cancer in women. By finding it early and using new treatments, patients can overcome this challenge and get back to a healthier life. This study proposed a procedure to fine-tune the Convolutional Neural Networks (CNN) model with data preprocessing and augmentation in classifying mammogram images called the Hybrid Mammogram Classification and Detection Pipeline (HMCaD). After using CNN for classification because it brings higher confidence in classifying tasks, the YOLOv8 has been applied for localization subtask to detect abnormal positions with predicted bounding boxes. The database is provided by the Mammographic Image Analysis Society (MIAS) and is protected by the United Kingdom. It comprises 330 samples, including 79 benign, 54 malignant, and 207 normal images. As a result, the classification in our model based on the custom EfficientNetB3 model and seam carving technique received a great validation accuracy, test accuracy, and F1 score throughout three scenarios at 96.73%, 97.59%, and 97.58%, respectively. Furthermore, the area under the Receiver Operating Characteristic (ROC) curve also has a surprise result of 0.96 (i.e. [Formula: see text]). Moreover, YOLOv8 for detecting abnormal positions in our study achieved 83.22% in Intersection over Union (IoU). This led to the research reaching good results in classifying and detecting breast cancer by considering several performance metrics.https://www.tandfonline.com/doi/10.1080/24751839.2024.2415033Breast cancer predictionTransfer learningYolov8EfficientNetB3
spellingShingle Huong Hoang Luong
Hai Thanh Nguyen
Nguyen Thai-Nghe
Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networks
Journal of Information and Telecommunication
Breast cancer prediction
Transfer learning
Yolov8
EfficientNetB3
title Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networks
title_full Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networks
title_fullStr Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networks
title_full_unstemmed Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networks
title_short Detection and classification of breast cancer in mammographic images with fine-tuned convolutional neural networks
title_sort detection and classification of breast cancer in mammographic images with fine tuned convolutional neural networks
topic Breast cancer prediction
Transfer learning
Yolov8
EfficientNetB3
url https://www.tandfonline.com/doi/10.1080/24751839.2024.2415033
work_keys_str_mv AT huonghoangluong detectionandclassificationofbreastcancerinmammographicimageswithfinetunedconvolutionalneuralnetworks
AT haithanhnguyen detectionandclassificationofbreastcancerinmammographicimageswithfinetunedconvolutionalneuralnetworks
AT nguyenthainghe detectionandclassificationofbreastcancerinmammographicimageswithfinetunedconvolutionalneuralnetworks