Simulation of biomedical signals and images using Monte Carlo methods for training of deep learning networks

Document Type

Book Chapter

Publication Title

Deep Learning Techniques for Biomedical and Health Informatics

First Page

213

Last Page

236

Publisher

Elsevier

School

Electron Science Research Institute

RAS ID

35302

Comments

Mavaddat, N., Ahderom, S., Tiporlini, V., & Alameh, K. (2020). Simulation of biomedical signals and images using Monte Carlo methods for training of deep learning networks. In B. Agarwal, V. E. Balas, L. C. Jain, R. C. Poonia & Manisha (Eds.), Deep Learning Techniques for Biomedical and Health Informatics (pp. 213-236). Elsevier. https://doi.org/10.1016/B978-0-12-819061-6.00009-4

Abstract

© 2020 Elsevier Inc. All rights reserved. High accuracy supervised deep learning methods require massive data with accurate ground truth. However, in biomedical applications, exact measurement of the ground truth is often impractical or even impossible. An important avenue to generate data with ground truth is simulation of the biomedical or imaging process. In this chapter, Monte Carlo methods are proposed as a useful set of tools to generate physics-based simulated signals and images.

DOI

10.1016/B978-0-12-819061-6.00009-4

Access Rights

subscription content

Link to Full Text

Share

 
COinS