Deep learning models for bone suppression in chest radiographs

Author First name, Last name, Institution

Maxim Gusarev, Innopolis University
Ramil Kuleev, Innopolis University
Adil Khan, Innopolis University
Adin Ramirez Rivera, Universidade Estadual de Campinas
Asad Masood Khattak, Zayed University

Document Type

Conference Proceeding

Source of Publication

2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2017

Publication Date

10-4-2017

Abstract

© 2017 IEEE. Bone suppression in lung radiographs is an important task, as it improves the results on other related tasks, such as nodule detection or pathologies classification. In this paper, we propose two architectures that suppress bones in radiographs by treating them as noise. In the proposed methods, we create end-to-end learning frameworks that minimize noise in the images while maintaining sharpness and detail in them. Our results show that our proposed noise-cancellation scheme is robust and does not introduce artifacts into the images.

DOI Link

10.1109/cibcb.2017.8058543

ISBN

9781467389884

Publisher

Institute of Electrical and Electronics Engineers Inc.

Last Page

7

Disciplines

Computer Sciences

Keywords

autoencoder, bone suppression, convolution neural network, deep learning, lung cancer

Scopus ID

85034630633

Recommended Citation

Gusarev, Maxim; Kuleev, Ramil; Khan, Adil; Rivera, Adin Ramirez; and Khattak, Asad Masood, "Deep learning models for bone suppression in chest radiographs" (2017). All Works. 1175.
https://zuscholars.zu.ac.ae/works/1175

Indexed in Scopus

yes

Open Access

no