Breast cancer detection based on simplified deep learning technique with histopathological image using BreaKHis database

Toma, Tania Afroz, Biswas, Shivazi, Miah, Md Sipon, Alibakhshikenari, Mohammad, Virdee, Bal Singh, Fernando, Sandra, Rahman, Md Habibur, Ali, Syed Mansoor, Arpanaei, Farhad, Hossain, Mohammad Amzad, Rahman, Md Mahbubur, Niu, Ming-bo, Parchin, Naser Ojaroudi and Livreri, Patrizia (2023) Breast cancer detection based on simplified deep learning technique with histopathological image using BreaKHis database. Radio Science, 58 (11). pp. 1-18. ISSN 1944-799X

[img]
Preview
Text
Radio Science - 2023 - Toma - Breast Cancer Detection Based on Simplified Deep Learning Technique With Histopathological.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (1MB) | Preview
Official URL: https://agupubs.onlinelibrary.wiley.com/doi/full/1...

Abstract / Description

Presented here are the results of an investigation conducted to determine the effectiveness of deep learning (DL)-based systems utilizing the power of transfer learning for detecting breast cancer in histopathological images. It is shown that DL models that are not specifically developed for breast cancer detection can be trained using transfer learning to effectively detect breast cancer in histopathological images. The outcome of the analysis enables the selection of the best DL architecture for detecting cancer with high accuracy. This should facilitate pathologists to achieve early diagnoses of breast cancer and administer appropriate treatment to the patient. The experimental work here used the BreaKHis database consisting of 7909 histopathological pictures from 82 clinical breast cancer patients. The strategy presented for DL training uses various image processing techniques for extracting various feature patterns. This is followed by applying transfer learning techniques in the deep convolutional networks like ResNet, ResNeXt, SENet, Dual Path Net, DenseNet, NASNet, and Wide ResNet. Comparison with recent literature shows that ResNext-50, ResNext-101, DPN131, DenseNet-169 and NASNet-A provide an accuracy of 99.8%, 99.5%, 99.675%, 99.725%, and 99.4%, respectively, and outperform previous studies.

Item Type: Article
Uncontrolled Keywords: deep learning (DL) models; histopathological images; breast cancer detection; BreaKHis database
Subjects: 000 Computer science, information & general works
600 Technology
600 Technology > 620 Engineering & allied operations
Department: School of Computing and Digital Media
Depositing User: Bal Virdee
Date Deposited: 23 Nov 2023 11:04
Last Modified: 20 Dec 2023 14:26
URI: https://repository.londonmet.ac.uk/id/eprint/8912

Downloads

Downloads per month over past year



Downloads each year

Actions (login required)

View Item View Item