Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190055,
        author = {nirbhay kumar kashyap and Anil Kumar Sagar},
        title = {Multiresolution Texture Driven Breast Cancer Detection Using a Modified Particle Swarm Optimization Method},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {2814-2823},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190055},
        abstract = {The diagnosis of breast cancer heavily depends on feature selection methods to extract important traits from tissue samples or medical imaging. This paper presents a feature selection method uses Modified Particle Swarm Optimization (MPSO). Based on the best features, breast tissue is classified as benign or malignant using SVM, MLP, and RF after three feature extraction techniques—HLG, GLRLM, and WPT1F—are applied. In terms of accuracy, sensitivity, and specificity, MPSO outperformed conventional techniques in training and evaluation using craniocaudal (CC) view images from the DDSM dataset. Because of its compactness and informativeness, the MPSO feature subset is known to improve early breast cancer detection. The model's generalization across a variety of imaging modalities was supported by validation of its performance on additional datasets from different mammographic views. Greater correlation between the expected and actual results, as well as reduced type-I and type-II errors to produce more accurate predictions, are indicated by a higher kappa value},
        keywords = {Particle swarm optimization, Mammographic images, Computer aided detection, Wavelet packet transform, LBP, GLCM, GLRLM},
        month = {January},
        }