Methods Inf Med 2018; 57(05/06): 272-279
DOI: 10.1055/s-0039-1681086
Focus Theme “Computational intelligence” – Original Article
Georg Thieme Verlag KG Stuttgart · New York

Analysis of Machine Learning Algorithms for Diagnosis of Diffuse Lung Diseases

Isadora Cardoso
1  Instituto de Computação, Universidade Federal de Alagoas, Maceió, Brazil
,
Eliana Almeida
1  Instituto de Computação, Universidade Federal de Alagoas, Maceió, Brazil
,
Hector Allende-Cid
2  Escuela de Ingeniería Informatica, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile
,
Alejandro C. Frery
1  Instituto de Computação, Universidade Federal de Alagoas, Maceió, Brazil
,
Rangaraj M. Rangayyan
3  Department of Electrical and Computer Engineering, Schulich School of Engineering, University of Calgary, Calgary, Alberta, Canada
,
Paulo M. Azevedo-Marques
4  Department of Internal Medicine, Ribeirão Preto Medical School, University of São Paulo, Ribeirão Preto, Brazil
,
Heitor S. Ramos
1  Instituto de Computação, Universidade Federal de Alagoas, Maceió, Brazil
› Author Affiliations
Funding This work was partially funded by Fapeal, CNPq, and SEFAZ-AL. The work of Héctor Allende-Cid was supported by the project FONDECYT Initiation into Research 11150248.
Further Information

Publication History

05 December 2017

26 May 2018

Publication Date:
15 March 2019 (online)

Computational Intelligence Re-meets Medical Image Processing

A Comparison of Some Nature-Inspired Optimization Metaheuristics Applied in Biomedical Image Registration

Summary

Background Diffuse lung diseases (DLDs) are a diverse group of pulmonary disorders, characterized by inflammation of lung tissue, which may lead to permanent loss of the ability to breathe and death. Distinguishing among these diseases is challenging to physicians due their wide variety and unknown causes. Computer-aided diagnosis (CAD) is a useful approach to improve diagnostic accuracy, by combining information provided by experts with Machine Learning (ML) methods.

Objectives Exploring the potential of dimensionality reduction combined with ML methods for diagnosis of DLDs; improving the classification accuracy over state-of-the-art methods.

Methods A data set composed of 3252 regions of interest (ROIs) was used, from which 28 features were extracted per ROI. We used Principal Component Analysis, Linear Discriminant Analysis, and Stepwise Selection – Forward, Backward, and Forward-Backward to reduce feature dimensionality. The feature subsets obtained were used as input to the following ML methods: Support Vector Machine, Gaussian Mixture Model, k-Nearest Neighbor, and Deep Feedforward Neural Network. We also applied a Deep Convolutional Neural Network directly to the ROIs.

Results We achieved the maximum reduction from 28 to 5 dimensions using LDA. The best classification results were obtained by DFNN, with 99.60% of overall accuracy.

Conclusions This work contributes to the analysis and selection of features that can efficiently characterize the DLDs studied.