Amazing technological breakthrough possible @S-Logix

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • +91- 81240 01111

Social List

Multi-modal classification for human breast cancer prognosis prediction: Proposal of deep-learning based stacked ensemble model - 2021

Multi-Modal Classification For Human Breast Cancer Prognosis Prediction: Proposal Of Deep-Learning Based Stacked Ensemble Model

Research Area:  Machine Learning


Breast cancer is the most frequently occurring cancer and has compelling contributions to increasing mortality rates among women. The manual prognosis and diagnosis of this disease take long hours, even for a medical professional. A model with better predictive power can benefit cancer patients from going through the toxic side effects and extra medical expenses related to unnecessary treatment. Medical professionals can be benefited from early-stage detection and selection of the appropriate cancer treatment plan. The availability of multi-modal cancer data, i.e., genomic details, histopathology images, and clinical details, supports the researchers in proceeding with the development of multi-modal based advanced deep-learning models. This research proposes gated attentive deep learning models stacked with random forest classifiers, which use multi-modal data and produce informative features to enhance the breast cancer prognosis prediction. It is designed as a bi-phase model; phase one uses a sigmoid gated attention convolutional neural network to generate the stacked features, while phase two passes the stacked features to the random forest classifier. The comparative study of the proposed and other existing methods over METABRIC (1980 patients) and TCGA-BRCA (1080 patients) datasets illustrate significant enhancements, 5.1% in sensitivity values, in the survival estimation of breast cancer patients.


Author(s) Name:  Nikhilanand Arya, Sriparna Saha

Journal name:  Knowledge-Based Systems

Conferrence name:  

Publisher name:  Elsevier

DOI:  10.1016/j.knosys.2021.106965

Volume Information:  Volume 221, 7 June 2021, 106965