Abstract
AbstractBreast Cancer (BC) has been increasing in incidence among women for a variety of reasons, and prompt detection and management are essential to reducing mortality rates. In the context of clinical-level breast cancer screening, the needle biopsy sample is used to generate Breast Histology Images (BHIs), which will then be used to confirm the results. Using a novel Deep-Learning Plan (DLP), the proposed work identifies BHI accurately and confirms the severity of BC by confirming its severity. As part of the proposed DLP implementation, four phases are involved: (i) the collection and enhancement of images, (ii) the extraction of features, (iii) the reduction of features and their integration, and (iv) binary classification and validation. The purpose of this study is to optimize deep features and machine features using particle swarm algorithms. To evaluate the performance of the proposed scheme, we compare the results obtained using individual deep features, dual deep features, and hybrid features. Using the hybrid image features in the classifier, this study has determined that ResNet18 with k-nearest neighbor provides superior classification accuracy (> 94%).
Publisher
Springer Science and Business Media LLC
Subject
Computational Mathematics,General Computer Science
Reference44 articles.
1. Wu, S., Bafna, V., Chang, H.Y., Mischel, P.S.: Extrachromosomal DNA: an emerging hallmark in human cancer. Annu. Rev. Pathol. 17, 367–386 (2022)
2. Tumolo, M.R., Panico, A., De Donno, A., Mincarone, P., Leo, C.G., Guarino, R., Sabina, S.: The expression of microRNAs and exposure to environmental contaminants related to human health: a review. Int. J. Environ. Health Res. 32(2), 332–354 (2022)
3. Khan, S., Awan, K.A., Iqbal, M.J.: Sulforaphane as a potential remedy against cancer: comprehensive mechanistic review. J. Food Biochem. 46(3), e13886 (2022)
4. https://www.who.int/news-room/fact-sheets/detail/cancer
5. https://www.who.int/news-room/fact-sheets/detail/breast-cancer