Breast Cancer Classification Using Feature Selection via Improved Simulated Annealing and SVM Classifier

Sep 22, 2026

Breast cancer ranks among the most common cancers in women, making early detection essential for better therapy outcomes and lower mortality. This study proposes an automated computer-aided diagnostic (CAD) system for mammograms, built on four stages: preprocessing, feature extraction, feature selection, and SVM classification. Improved simulated annealing adaptively selects informative features while reducing dimensionality. Experiments on CBIS-DDSM and MIAS report 99.67% and 98% accuracy, with strong sensitivity and F1-score results.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages16

Reading Time40 min

AccessFree to download

Abstract

Keywords

1. Introduction

Background and motivation

CAD systems and mammography challenges

Proposed four-stage pipeline

Materials and methods (implied)

Article Breast Cancer Classification Using Feature Selection via Improved Simulated Annealing and SVM Classifier Maedeh Kiani Sarkaleh 1, Hossein Azgomi 1, * and Azadeh Kiani-Sarkaleh 2 Academic Editor: Takouhie Catherine Maldjian Received: 23 July 2025 Revised: 21 August 2025 Accepted: 22 August 2025 Published: 23 February 2026 Copyright: © 2026 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. 1 Department of Computer Engineering, Ra.C., Islamic Azad University, Rasht 4147654949, Iran; [m.kiani8312@iau.ac.ir](m.kiani8312@iau.ac.ir) 2 Department of Electrical Engineering, Ra.C., Islamic Azad University, Rasht 4147654949, Iran; [azadeh.kiani@iau.ac.ir](azadeh.kiani@iau.ac.ir) * [Correspondence: hossein.azgomi@iau.ac.ir](Correspondence: hossein.azgomi@iau.ac.ir) Abstract Background: Breast cancer is among the most common cancers in women, and early diagnosis is critical for better treatment outcomes and reduced mortality. Efficient computer-aided diagnostic (CAD) systems play a crucial role in enhancing diagnostic accuracy and facilitating timely clinical decisions. Methods: This study proposes an automated CAD system for detecting cancerous tumors in mammograms, consisting of four stages: preprocessing, feature extraction, feature selection, and classification. In preprocessing, the region of interest (ROI) is extracted, followed by noise suppression and contrast enhancement to improve image quality. Shape, histogram, and tissue-related features are then computed from each ROI. An Improved Simulated Annealing (ISA) algorithm is employed to adaptively select the most informative features through a flexible process and composite fitness function, effectively reducing dimensionality while preserving high classification accuracy. Finally, classification is performed using a Support Vector Machine (SVM) to distinguish between malignant and benign masses. Results: Evaluation on the CBIS-DDSM and MIAS datasets showed the system achieved accuracies of 99.67% and 98%, sensitivities of 99.33% and 98%, and F1-scores of 99.66% and 97.9%, respectively. These results indicate notable improvements over traditional SA and full-feature approaches. Conclusions: The findings confirm the effectiveness of the ISA algorithm in selecting relevant features, thereby enhancing the performance of breast cancer detection. Keywords: breast cancer; image processing; improved simulated annealing; featureselection; SVM classifier 1. Introduction Despite significant advancements in early diagnosis and medical treatments, breast cancer remains the second leading cause of death among women worldwide and the primary cause among Black and Hispanic women. Data indicate that the breast cancer mortality rate declined by approximately 44% from 1989 to 2022, largely due to improved medical practices, more precise screening, and early detection [1] . Breast cancer is characterized by the uncontrolled proliferation of abnormal cells in breast tissue, leading to tumor formation. If left undiagnosed and untreated, these tumors can metastasize to other parts of the body, posing a serious threat to the patient’s health. The prevalence of breast cancer continues to rise globally, with the highest incidence observed in industrialized countries. This trend is influenced by various factors, including lifestyle, age, hormones, genetics, and dietary habits [2] . Early diagnosis of breast cancer enables the timely initiation of treatment, significantly increasing the chances of success. Even in regions with limited access to specialists, machine learning can support early detection [3] . Mammography remains a fundamental tool for breast cancer screening; however, interpreting masses in mammographic images presentsa significant challenge. To address this, Computer-Aided Diagnosis (CAD) systems have been developed t

FAQs

What problem does the proposed system address?

It targets the difficulty of detecting and classifying malignant versus benign breast masses in mammographic images, supporting timely and accurate diagnosis.

How does the method select features?

It uses an Improved Simulated Annealing (ISA) algorithm with a composite fitness function to adaptively choose the most informative features while reducing dimensionality.

What classifier is used for the final decision?

A Support Vector Machine (SVM) classifier distinguishes between malignant and benign masses after feature selection.

Sep 22, 2026

Upload by Olivia Brown