Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network

Abstract Breast cancer is the most prevalent cancer among women globally, with over 2.3 million new cases reported annually, hence, early and accurate diagnosis is crucial in minimizing mortality rates. In light of the limitation on the conventional interpretation of images, this study presents a no...

Full description

Saved in:
Bibliographic Details
Main Authors: Emmanuel Ahishakiye, Fredrick Kanobe
Format: Article
Language:English
Published: Springer 2025-05-01
Series:Discover Artificial Intelligence
Subjects:
Online Access:https://doi.org/10.1007/s44163-025-00335-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850231221332738048
author Emmanuel Ahishakiye
Fredrick Kanobe
author_facet Emmanuel Ahishakiye
Fredrick Kanobe
author_sort Emmanuel Ahishakiye
collection DOAJ
description Abstract Breast cancer is the most prevalent cancer among women globally, with over 2.3 million new cases reported annually, hence, early and accurate diagnosis is crucial in minimizing mortality rates. In light of the limitation on the conventional interpretation of images, this study presents a novel hybrid model that integrates DenseNet201-based transfer learning with a Bayesian-Optimized Fast Learning Network (FLN) for breast cancer classification from ultrasound images. DenseNet201 was employed to obtain robust, high-quality features from pre-trained weights. FLN is finely tuned with Bayesian optimization to select optimal hyperparameters such as learning rate, hidden neurons, and dropout rate. The proposed model achieved an accuracy of 96.79%, an F1 score of 94.71%, a precision of 96.81%, and a recall of 93.48% with AUC scores of 0.96, 0.95, and 0.98 for benign, malignant, and normal classes. These results underscore the model’s balanced performance and its ability to minimize misclassifications, particularly false positives. The end-to-end hybrid approach not only outperforms several state-of-the-art models but also demonstrates improved generalization and stability, offering a promising, clinically viable tool for enhancing breast cancer diagnosis.
format Article
id doaj-art-bac4edc84e5d408aa34fc944508781b4
institution OA Journals
issn 2731-0809
language English
publishDate 2025-05-01
publisher Springer
record_format Article
series Discover Artificial Intelligence
spelling doaj-art-bac4edc84e5d408aa34fc944508781b42025-08-20T02:03:36ZengSpringerDiscover Artificial Intelligence2731-08092025-05-015111710.1007/s44163-025-00335-4Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning networkEmmanuel Ahishakiye0Fredrick Kanobe1Department of Networks, Data Science and Artificial Intelligence, Kyambogo UniversityDepartment of Information Technology, Uganda Management InstituteAbstract Breast cancer is the most prevalent cancer among women globally, with over 2.3 million new cases reported annually, hence, early and accurate diagnosis is crucial in minimizing mortality rates. In light of the limitation on the conventional interpretation of images, this study presents a novel hybrid model that integrates DenseNet201-based transfer learning with a Bayesian-Optimized Fast Learning Network (FLN) for breast cancer classification from ultrasound images. DenseNet201 was employed to obtain robust, high-quality features from pre-trained weights. FLN is finely tuned with Bayesian optimization to select optimal hyperparameters such as learning rate, hidden neurons, and dropout rate. The proposed model achieved an accuracy of 96.79%, an F1 score of 94.71%, a precision of 96.81%, and a recall of 93.48% with AUC scores of 0.96, 0.95, and 0.98 for benign, malignant, and normal classes. These results underscore the model’s balanced performance and its ability to minimize misclassifications, particularly false positives. The end-to-end hybrid approach not only outperforms several state-of-the-art models but also demonstrates improved generalization and stability, offering a promising, clinically viable tool for enhancing breast cancer diagnosis.https://doi.org/10.1007/s44163-025-00335-4Breast cancerTransfer learningBayesian optimizationFast learning networkMedical image classification
spellingShingle Emmanuel Ahishakiye
Fredrick Kanobe
Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network
Discover Artificial Intelligence
Breast cancer
Transfer learning
Bayesian optimization
Fast learning network
Medical image classification
title Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network
title_full Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network
title_fullStr Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network
title_full_unstemmed Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network
title_short Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network
title_sort breast cancer classification using breast ultrasound images with a hybrid of transfer learning and bayesian optimized fast learning network
topic Breast cancer
Transfer learning
Bayesian optimization
Fast learning network
Medical image classification
url https://doi.org/10.1007/s44163-025-00335-4
work_keys_str_mv AT emmanuelahishakiye breastcancerclassificationusingbreastultrasoundimageswithahybridoftransferlearningandbayesianoptimizedfastlearningnetwork
AT fredrickkanobe breastcancerclassificationusingbreastultrasoundimageswithahybridoftransferlearningandbayesianoptimizedfastlearningnetwork