Classification of benign and malignant bone lesions on CT images using random forest

M. V. Suhas, Anindita Mishra

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Bones form the supporting framework of the body. It has a hard outer layer made of compact (cortical) bone that covers a lighter spongy (trabecular) bone inside. Osteoblast (cell that lays down new bone) and osteoclast (cell that dissolves old bone) are the two types of cells present in the bone. Throughout our lifetime, new bone keeps replacing the dissolving old bone. An uncontrollable division of these cells along with fat cells and blood forming cells in the bone marrow could destroy surrounding body tissue causing bone cancer. This work presents a Computer Aided Diagnosis (CAD) system that helps radiologists in differentiating malignant and benign bone lesions in the spine on CT images. Firstly, the lesions are segmented using active contour models and then texture is analyzed through second order statistical measurements based on the Gray Level Co-occurrence Matrix (GLCM). We use features like autocorrelation, contrast, cluster shade, cluster prominence, energy, maximum probability, variance and difference variance to train and test the Random Forest. The aim of this paper is to discuss a technique that improves the sensitivity, specificity and accuracy of detecting the bone lesions.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1807-1810
Number of pages4
ISBN (Electronic)9781509007745
DOIs
Publication statusPublished - 05-01-2017
Externally publishedYes
Event1st IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Bangalore, India
Duration: 20-05-201621-05-2016

Conference

Conference1st IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016
CountryIndia
CityBangalore
Period20-05-1621-05-16

Fingerprint

Bone
Computer aided diagnosis
Osteoblasts
Oils and fats
Autocorrelation
Blood
Textures
Tissue

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems
  • Electrical and Electronic Engineering

Cite this

Suhas, M. V., & Mishra, A. (2017). Classification of benign and malignant bone lesions on CT images using random forest. In 2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings (pp. 1807-1810). [7808146] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RTEICT.2016.7808146
Suhas, M. V. ; Mishra, Anindita. / Classification of benign and malignant bone lesions on CT images using random forest. 2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1807-1810
@inproceedings{0d9d6f943d7e495680fc5de96593bcb0,
title = "Classification of benign and malignant bone lesions on CT images using random forest",
abstract = "Bones form the supporting framework of the body. It has a hard outer layer made of compact (cortical) bone that covers a lighter spongy (trabecular) bone inside. Osteoblast (cell that lays down new bone) and osteoclast (cell that dissolves old bone) are the two types of cells present in the bone. Throughout our lifetime, new bone keeps replacing the dissolving old bone. An uncontrollable division of these cells along with fat cells and blood forming cells in the bone marrow could destroy surrounding body tissue causing bone cancer. This work presents a Computer Aided Diagnosis (CAD) system that helps radiologists in differentiating malignant and benign bone lesions in the spine on CT images. Firstly, the lesions are segmented using active contour models and then texture is analyzed through second order statistical measurements based on the Gray Level Co-occurrence Matrix (GLCM). We use features like autocorrelation, contrast, cluster shade, cluster prominence, energy, maximum probability, variance and difference variance to train and test the Random Forest. The aim of this paper is to discuss a technique that improves the sensitivity, specificity and accuracy of detecting the bone lesions.",
author = "Suhas, {M. V.} and Anindita Mishra",
year = "2017",
month = "1",
day = "5",
doi = "10.1109/RTEICT.2016.7808146",
language = "English",
pages = "1807--1810",
booktitle = "2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Suhas, MV & Mishra, A 2017, Classification of benign and malignant bone lesions on CT images using random forest. in 2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings., 7808146, Institute of Electrical and Electronics Engineers Inc., pp. 1807-1810, 1st IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016, Bangalore, India, 20-05-16. https://doi.org/10.1109/RTEICT.2016.7808146

Classification of benign and malignant bone lesions on CT images using random forest. / Suhas, M. V.; Mishra, Anindita.

2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1807-1810 7808146.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Classification of benign and malignant bone lesions on CT images using random forest

AU - Suhas, M. V.

AU - Mishra, Anindita

PY - 2017/1/5

Y1 - 2017/1/5

N2 - Bones form the supporting framework of the body. It has a hard outer layer made of compact (cortical) bone that covers a lighter spongy (trabecular) bone inside. Osteoblast (cell that lays down new bone) and osteoclast (cell that dissolves old bone) are the two types of cells present in the bone. Throughout our lifetime, new bone keeps replacing the dissolving old bone. An uncontrollable division of these cells along with fat cells and blood forming cells in the bone marrow could destroy surrounding body tissue causing bone cancer. This work presents a Computer Aided Diagnosis (CAD) system that helps radiologists in differentiating malignant and benign bone lesions in the spine on CT images. Firstly, the lesions are segmented using active contour models and then texture is analyzed through second order statistical measurements based on the Gray Level Co-occurrence Matrix (GLCM). We use features like autocorrelation, contrast, cluster shade, cluster prominence, energy, maximum probability, variance and difference variance to train and test the Random Forest. The aim of this paper is to discuss a technique that improves the sensitivity, specificity and accuracy of detecting the bone lesions.

AB - Bones form the supporting framework of the body. It has a hard outer layer made of compact (cortical) bone that covers a lighter spongy (trabecular) bone inside. Osteoblast (cell that lays down new bone) and osteoclast (cell that dissolves old bone) are the two types of cells present in the bone. Throughout our lifetime, new bone keeps replacing the dissolving old bone. An uncontrollable division of these cells along with fat cells and blood forming cells in the bone marrow could destroy surrounding body tissue causing bone cancer. This work presents a Computer Aided Diagnosis (CAD) system that helps radiologists in differentiating malignant and benign bone lesions in the spine on CT images. Firstly, the lesions are segmented using active contour models and then texture is analyzed through second order statistical measurements based on the Gray Level Co-occurrence Matrix (GLCM). We use features like autocorrelation, contrast, cluster shade, cluster prominence, energy, maximum probability, variance and difference variance to train and test the Random Forest. The aim of this paper is to discuss a technique that improves the sensitivity, specificity and accuracy of detecting the bone lesions.

UR - http://www.scopus.com/inward/record.url?scp=85015086289&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015086289&partnerID=8YFLogxK

U2 - 10.1109/RTEICT.2016.7808146

DO - 10.1109/RTEICT.2016.7808146

M3 - Conference contribution

SP - 1807

EP - 1810

BT - 2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Suhas MV, Mishra A. Classification of benign and malignant bone lesions on CT images using random forest. In 2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1807-1810. 7808146 https://doi.org/10.1109/RTEICT.2016.7808146