EpiBrCan-Lite: A lightweight deep learning model for breast cancer subtype classification using epigenomic data.

Journal: Computer methods and programs in biomedicine
Published Date:

Abstract

BACKGROUND AND OBJECTIVES: Early breast cancer subtypes classification improves the survival rate as it facilitates prognosis of the patient. In literature this problem was prominently solved by various Machine Learning and Deep Learning techniques. However, these studies have three major shortcomings: huge Trainable Weight Parameters (TWP), suffer from low performance and class imbalance problem.

Authors

  • Punam Bedi
    Department of Computer Science, University of Delhi, New Delhi, India.
  • Surbhi Rani
    Department of Computer Science, University of Delhi, Delhi, India. Electronic address: srani@cs.du.ac.in.
  • Bhavna Gupta
    Keshav Mahavidyalaya, University of Delhi, New Delhi, India. Electronic address: bgupta@keshav.du.ac.in.
  • Veenu Bhasin
    PGDAV College, University of Delhi, New Delhi, India. Electronic address: veenu.bhasin@pgdav.du.ac.in.
  • Pushkar Gole
    Department of Computer Science, University of Delhi, New Delhi, India.