Ensemble Deep Learning-Based Image Classification for Breast Cancer Subtype and Invasiveness Diagnosis from Whole Slide Image Histopathology

Authors

Aadhi Aadhavan Balasubramanian, Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, USA.
Salah Mohammed Al-Heejawi, College of Engineering, Northeastern University, Boston, MA 02115, USA.
Akarsh Singh, College of Engineering, Northeastern University, Boston, MA 02115, USA.
Anne Breggia, Center for Applied Science and Technology, Maine Health Institute for Research, Scarborough, ME, United States.Follow
Bilal Ahmad, Maine Medical Center, Portland, ME 04102, USA.Follow
Robert Christman, Maine Medical Center, Portland, ME 04102, USA.Follow
Stephen Ryan, Maine Medical CenterFollow
Saeed Amal, The Roux Institute, Department of Bioengineering, College of Engineering, Northeastern University, Boston, MA 02115, USA.

Document Type

Article

Publication Date

6-14-2024

Institution/Department

Urology; Center for Interdisciplinary Population & Health Research

Journal Title

Cancers

Abstract

Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens.

ISSN

2072-6694

Recommended Citation

Balasubramanian, Aadhi Aadhavan; Al-Heejawi, Salah Mohammed; Singh, Akarsh; Breggia, Anne; Ahmad, Bilal; Christman, Robert; Ryan, Stephen; and Amal, Saeed, "Ensemble Deep Learning-Based Image Classification for Breast Cancer Subtype and Invasiveness Diagnosis from Whole Slide Image Histopathology" (2024). MaineHealth Maine Medical Center. 3724.
https://knowledgeconnection.mainehealth.org/mmc/3724