UNIGE document Scientific Article - Review
previous document  unige:20892  next document
add to browser collection

Comparative performance analysis of state-of-the-art classification algorithms applied to lung tissue categorization

Hidki, Asmaa
Published in Journal of digital imaging. 2010, vol. 23, no. 1, p. 18-30
Collection Open Access - Licence nationale Springer
Abstract In this paper, we compare five common classifier families in their ability to categorize six lung tissue patterns in high-resolution computed tomography (HRCT) images of patients affected with interstitial lung diseases (ILD) and with healthy tissue. The evaluated classifiers are naive Bayes, k-nearest neighbor, J48 decision trees, multilayer perceptron, and support vector machines (SVM). The dataset used contains 843 regions of interest (ROI) of healthy and five pathologic lung tissue patterns identified by two radiologists at the University Hospitals of Geneva. Correlation of the feature space composed of 39 texture attributes is studied. A grid search for optimal parameters is carried out for each classifier family. Two complementary metrics are used to characterize the performances of classification. These are based on McNemar's statistical tests and global accuracy. SVM reached best values for each metric and allowed a mean correct prediction rate of 88.3% with high class-specific precision on testing sets of 423 ROIs.
Keywords *AlgorithmsBayes TheoremDecision TreesHumansLung Diseases, Interstitial/*radiographyNeural Networks (Computer)Radiographic Image Interpretation, Computer-Assisted/*methodsTomography, X-Ray Computed/*statistics & numerical data
PMID: 18982390
Full text
Research groups Groupe Geissbuhler Antoine (informatique médicale) (222)
Radiologie des urgences (800)
(ISO format)
DEPEURSINGE, Adrien et al. Comparative performance analysis of state-of-the-art classification algorithms applied to lung tissue categorization. In: Journal of digital imaging, 2010, vol. 23, n° 1, p. 18-30. doi: 10.1007/s10278-008-9158-4 https://archive-ouverte.unige.ch/unige:20892

539 hits



Deposited on : 2012-05-23

Export document
Format :
Citation style :