MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classification

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated notable advantages in breast cancer im...

Full description

Saved in:
Bibliographic Details
Main Authors: Haonan Li, Vijay Govindarajan, Tan Fong Ang, Zaffar Ahmed Shaikh, Amel Ksibi, Yen-Lin Chen, Chin Soon Ku, Ming Chern Leong, Fatiha Hana Shabaruddin, Wan Zamaniah Wan Ishak, Lip Yee Por
Format: Article
Language:English
Published: SAGE Publishing 2025-07-01
Series:Digital Health
Online Access:https://doi.org/10.1177/20552076251361603
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849717767175929856
author Haonan Li
Vijay Govindarajan
Tan Fong Ang
Zaffar Ahmed Shaikh
Amel Ksibi
Yen-Lin Chen
Chin Soon Ku
Ming Chern Leong
Fatiha Hana Shabaruddin
Wan Zamaniah Wan Ishak
Lip Yee Por
author_facet Haonan Li
Vijay Govindarajan
Tan Fong Ang
Zaffar Ahmed Shaikh
Amel Ksibi
Yen-Lin Chen
Chin Soon Ku
Ming Chern Leong
Fatiha Hana Shabaruddin
Wan Zamaniah Wan Ishak
Lip Yee Por
author_sort Haonan Li
collection DOAJ
description As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated notable advantages in breast cancer image classification. However, their performance heavily relies on the proper configuration of hyperparameters. To overcome the inefficiencies and weaknesses of conventional hyperparameter optimization methods, like limited effectiveness and vulnerability to premature convergence, this research proposes a Multi-Strategy Parrot Optimizer (MSPO) and applies it to breast cancer image classification tasks. Based on the original Parrot Optimizer, MSPO integrates several strategies, including Sobol sequence initialization, nonlinear decreasing inertia weight, and a chaotic parameter to enhance global exploration ability and convergence steadiness. Tests using the CEC 2022 benchmark functions reveal that MSPO surpasses leading algorithms regarding optimization precision and convergence rate. An ablation study was conducted on three variants of MSPO through CEC 2022 to further validate the effectiveness of each key strategy. Furthermore, MSPO is combined with the ResNet18 model and applied to the BreaKHis breast cancer image dataset. Results indicate that the model optimized by MSPO notably surpasses both the non-optimized version and other alternative optimization algorithms using four assessment indicators: accuracy, precision, recall, and F1-score. This validates the promising application potential and practical significance of MSPO in medical image classification tasks.
format Article
id doaj-art-3ca80ed62c6c4d36a787e626059ad3fb
institution DOAJ
issn 2055-2076
language English
publishDate 2025-07-01
publisher SAGE Publishing
record_format Article
series Digital Health
spelling doaj-art-3ca80ed62c6c4d36a787e626059ad3fb2025-08-20T03:12:34ZengSAGE PublishingDigital Health2055-20762025-07-011110.1177/20552076251361603MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classificationHaonan Li0Vijay Govindarajan1Tan Fong Ang2Zaffar Ahmed Shaikh3Amel Ksibi4Yen-Lin Chen5Chin Soon Ku6Ming Chern Leong7Fatiha Hana Shabaruddin8Wan Zamaniah Wan Ishak9Lip Yee Por10 Center of Research for Cyber Security and Network (CSNET), Faculty of Computer Science and Information Technology, , Kuala Lumpur, Wilayar Persekutuan, Malaysia Distribution and Supply Technology, Expedia Group, Seattle, WA, USA Center of Research for Cyber Security and Network (CSNET), Faculty of Computer Science and Information Technology, , Kuala Lumpur, Wilayar Persekutuan, Malaysia School of Engineering, , Lausanne, Switzerland Department of Information Systems, College of Computer and Information Sciences, , Riyadh, Saudi Arabia Department of Computer Science and Information Engineering, National Taipei University of Technology, Taipei, Taiwan Department of Computer Science, , Perak, Malaysia Pediatric and Congenital Heart Center, National Heart Institute, Kuala Lumpur, Malaysia Faculty of Pharmacy, University Malaya, Kuala Lumpur, Malaysia Clinical Oncology Unit, Faculty of Medicine, , Kuala Lumpur, Malaysia Center of Research for Cyber Security and Network (CSNET), Faculty of Computer Science and Information Technology, , Kuala Lumpur, Wilayar Persekutuan, MalaysiaAs one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated notable advantages in breast cancer image classification. However, their performance heavily relies on the proper configuration of hyperparameters. To overcome the inefficiencies and weaknesses of conventional hyperparameter optimization methods, like limited effectiveness and vulnerability to premature convergence, this research proposes a Multi-Strategy Parrot Optimizer (MSPO) and applies it to breast cancer image classification tasks. Based on the original Parrot Optimizer, MSPO integrates several strategies, including Sobol sequence initialization, nonlinear decreasing inertia weight, and a chaotic parameter to enhance global exploration ability and convergence steadiness. Tests using the CEC 2022 benchmark functions reveal that MSPO surpasses leading algorithms regarding optimization precision and convergence rate. An ablation study was conducted on three variants of MSPO through CEC 2022 to further validate the effectiveness of each key strategy. Furthermore, MSPO is combined with the ResNet18 model and applied to the BreaKHis breast cancer image dataset. Results indicate that the model optimized by MSPO notably surpasses both the non-optimized version and other alternative optimization algorithms using four assessment indicators: accuracy, precision, recall, and F1-score. This validates the promising application potential and practical significance of MSPO in medical image classification tasks.https://doi.org/10.1177/20552076251361603
spellingShingle Haonan Li
Vijay Govindarajan
Tan Fong Ang
Zaffar Ahmed Shaikh
Amel Ksibi
Yen-Lin Chen
Chin Soon Ku
Ming Chern Leong
Fatiha Hana Shabaruddin
Wan Zamaniah Wan Ishak
Lip Yee Por
MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classification
Digital Health
title MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classification
title_full MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classification
title_fullStr MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classification
title_full_unstemmed MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classification
title_short MSPO: A machine learning hyperparameter optimization method for enhanced breast cancer image classification
title_sort mspo a machine learning hyperparameter optimization method for enhanced breast cancer image classification
url https://doi.org/10.1177/20552076251361603
work_keys_str_mv AT haonanli mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT vijaygovindarajan mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT tanfongang mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT zaffarahmedshaikh mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT amelksibi mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT yenlinchen mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT chinsoonku mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT mingchernleong mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT fatihahanashabaruddin mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT wanzamaniahwanishak mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification
AT lipyeepor mspoamachinelearninghyperparameteroptimizationmethodforenhancedbreastcancerimageclassification