Title: Development of language education optimisation algorithm and adaptive shuffle attention Net-V2 for classification of breast cancer

Authors: V. Anitha; Murugavalli Subramaniam; A. Ameelia Roseline

Addresses: Department of Computer Science and Engineering, Panimalar Engineering College, Chennai, India; Department of Information and Communication Engineering, Anna University, Chennai, India ' Department of Computer Science and Engineering, Panimalar Engineering College, Chennai City Campus, Chennai, India ' Department of Electronics and Communication Engineering, Panimalar Engineering College, Chennai, India

Abstract: The digital breast tomosynthesis (DBT) model is proposed as an innovative tomographic model for reducing the challenges in existing mammography models. However, the manual processing of the enormous volume of breast cancer photos makes the early identification of breast cancer from tomosynthesis images still difficult due to the possibility of humans. As a result, an automated and effective breast cancer classification method is created employing deep learning techniques. The tomosynthesis images are collected from various benchmark datasets. The gathered images from the tomosynthesis are given to the hybrid convolution (3D/2D)-based dilated transformer-based residual UNet (HCDTRU) model for segmentation. The segmented breast cancer images are now fed to the adaptive shuffle AttentionNetV2 (ASANV2) for classification. The effective breast cancer classification is done with the optimisation of the parameters in the developed ASANV2 framework. The parameters in the ASANV2 framework are tuned utilising the adaptive updated language education process optimisation (AU-LEO) algorithm.

Keywords: breast cancer classification; hybrid convolution (3D/2D)-based dilated TransResUNet; adaptive shuffle AttentionNetV2; ASANV2; adaptive updated language education process optimisation; AU-LEO.

DOI: 10.1504/IJAHUC.2025.146144

International Journal of Ad Hoc and Ubiquitous Computing, 2025 Vol.49 No.1, pp.21 - 42

Received: 15 Nov 2023
Accepted: 18 Sep 2024
Published online: 07 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article