Literature DB >> 28623478

Feature fusion for lung nodule classification.

Amal A Farag1, Asem Ali2, Salwa Elshazly3, Aly A Farag2.   

Abstract

PURPOSE: This article examines feature-based nodule description for the purpose of nodule classification in chest computed tomography scanning.
METHODS: Three features based on (i) Gabor filter, (ii) multi-resolution local binary pattern (LBP) texture features and (iii) signed distance fused with LBP which generates a combinational shape and texture feature are utilized to provide feature descriptors of malignant and benign nodules and non-nodule regions of interest. Support vector machines (SVMs) and k-nearest neighbor (kNN) classifiers in serial and two-tier cascade frameworks are optimized and analyzed for optimal classification results of nodules.
RESULTS: A total of 1191 nodule and non-nodule samples from the Lung Image Data Consortium database is used for analysis. Classification using SVM and kNN classifiers is examined. The classification results from the two-tier cascade SVM using Gabor features showed overall better results for identifying non-nodules, malignant and benign nodules with average area under the receiver operating characteristics (AUC-ROC) curves of 0.99 and average f1-score of 0.975 over the two tiers.
CONCLUSION: In the results, higher overall AUCs and f1-scores were obtained for the non-nodules cases using any of the three features, showing the greatest distinguishability over nodules (benign/malignant). SVM and kNN classifiers were used for benign, malignant and non-nodule classification, where Gabor proved to be the most effective of the features for classification. The cascaded framework showed the greatest distinguishability between benign and malignant nodules.

Entities:  

Keywords:  Classification; Computed tomography; Features extraction; Gabor; LBP; Lung nodules

Mesh:

Year:  2017        PMID: 28623478     DOI: 10.1007/s11548-017-1626-1

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  15 in total

1.  Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique.

Authors:  Y Lee; T Hara; H Fujita; S Itoh; T Ishigaki
Journal:  IEEE Trans Med Imaging       Date:  2001-07       Impact factor: 10.048

2.  Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical CT images.

Authors:  William J Kostis; Anthony P Reeves; David F Yankelevitz; Claudia I Henschke
Journal:  IEEE Trans Med Imaging       Date:  2003-10       Impact factor: 10.048

3.  Lung image database consortium: developing a resource for the medical imaging research community.

Authors:  Samuel G Armato; Geoffrey McLennan; Michael F McNitt-Gray; Charles R Meyer; David Yankelevitz; Denise R Aberle; Claudia I Henschke; Eric A Hoffman; Ella A Kazerooni; Heber MacMahon; Anthony P Reeves; Barbara Y Croft; Laurence P Clarke
Journal:  Radiology       Date:  2004-09       Impact factor: 11.105

4.  Gabor-based kernel PCA with fractional power polynomial models for face recognition.

Authors:  Chengjun Liu
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2004-05       Impact factor: 6.226

5.  Toward precise pulmonary nodule descriptors for nodule type classification.

Authors:  Amal Farag; Shireen Elhabian; James Graham; Aly Farag; Robert Falk
Journal:  Med Image Comput Comput Assist Interv       Date:  2010

6.  Improved pulmonary nodule classification utilizing quantitative lung parenchyma features.

Authors:  Samantha K N Dilger; Johanna Uthoff; Alexandra Judisch; Emily Hammond; Sarah L Mott; Brian J Smith; John D Newell; Eric A Hoffman; Jessica C Sieren
Journal:  J Med Imaging (Bellingham)       Date:  2015-09-01

7.  Automated pulmonary nodule CT image characterization in lung cancer screening.

Authors:  Anthony P Reeves; Yiting Xie; Artit Jirapatnakul
Journal:  Int J Comput Assist Radiol Surg       Date:  2015-06-30       Impact factor: 2.924

8.  Automatic detection of abnormalities in chest radiographs using local texture analysis.

Authors:  Bram van Ginneken; Shigehiko Katsuragawa; Bart M ter Haar Romeny; Kunio Doi; Max A Viergever
Journal:  IEEE Trans Med Imaging       Date:  2002-02       Impact factor: 10.048

9.  Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine.

Authors:  Hiram Madero Orozco; Osslan Osiris Vergara Villegas; Vianey Guadalupe Cruz Sánchez; Humberto de Jesús Ochoa Domínguez; Manuel de Jesús Nandayapa Alfaro
Journal:  Biomed Eng Online       Date:  2015-02-12       Impact factor: 2.819

10.  Computer-aided classification of lung nodules on computed tomography images via deep learning technique.

Authors:  Kai-Lung Hua; Che-Hao Hsu; Shintami Chusnul Hidayati; Wen-Huang Cheng; Yu-Jen Chen
Journal:  Onco Targets Ther       Date:  2015-08-04       Impact factor: 4.147

View more
  2 in total

1.  A Comparative Classification Analysis of Abdominal Aortic Aneurysms by Machine Learning Algorithms.

Authors:  Balaji Rengarajan; Wei Wu; Crystal Wiedner; Daijin Ko; Satish C Muluk; Mark K Eskandari; Prahlad G Menon; Ender A Finol
Journal:  Ann Biomed Eng       Date:  2020-01-24       Impact factor: 3.934

2.  Combining multi-scale feature fusion with multi-attribute grading, a CNN model for benign and malignant classification of pulmonary nodules.

Authors:  Jumin Zhao; Chen Zhang; Dengao Li; Jing Niu
Journal:  J Digit Imaging       Date:  2020-08       Impact factor: 4.056

  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.