Microscopic image analysis in breast cancer detection using ensemble deep learning architectures integrated with web of things. (January 2023)

• Record Type: Journal Article
• Authors: Sheeba, Adlin; Santhosh Kumar, P.; Ramamoorthy, M.; Sasikala, S.
• Is Part Of: Biomedical signal processing and control. Volume 79(2023)Part 2
• Publication Date: 2023-01
• Subjects: Breast cancer -- Deep learning -- Microscopic images -- Web of things -- Classification; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104048
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Overall proposed architecture. Highlights: Breast cancer is a leading cause of death among women. Death rate from breast cancer is reduced when it is detected early. In recent years, cancer-related mortality has risen dramatically. The goal of machine learning is to make it easier for computers to learn independently. Abstract: Breast cancer is a leading cause of death among women. Death rate from breast cancer is reduced when it is detected early. Deep learning (DL) methods have become a viable alternative for diagnosis, overcoming the limitations of traditional classification methods. Because biosensors and deep learning are required to identify tumors based on microscopic pictures, automation is needed. The goal of machine learning is to make it easier for computers to learn independently. This research proposed novel technique in breast cancer detection utilizing ensemble DL techniques in classification with features extraction. Input image has been collected based on web of things (WoT) in which the pre-historic data and collected microscopic images have been taken as input dataset. The input image has been processed for noise removal using Gaussian filtering and segmented using active contour convolutional neural networks. Then the classification was carried out using convoluted transfer learning integrated with regional attention mechanism. Compared to existing methods in the domain, the simulation results show that the suggested localization-based cancer classification method is superior. It has reported average classification accuracy of 96%, detection accuracy of 92%, Mean Average Precision (mAP) of 82%, sensitivity of 92%, specificity of 91%, root mean square error (RMSE) of 70% on various breast cancer microscopic image datasets.