Rotation-covariant tissue analysis for interstitial lung diseases using learned steerable filters: Performance evaluation and relevance for diagnostic aid

• Published in: Computerized medical imaging and graphics Vol. 64; pp. 1 - 11
• Main Authors: Joyseeree, Ranveer, Müller, Henning, Depeursinge, Adrien
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2018; Elsevier Science Ltd
• Subjects: Basis functions; Classification; Decision analysis; Diagnostic systems; Diagnostics; Diseases; Filters; Ground truth; ILD; Lung diseases; Medical diagnosis; Medical imaging; One-versus-one; Performance evaluation; Radial basis function; Signatures; Studies; Support vector machines; Texture signatures; Tissue analysis; ILD; One-versus-one; Texture signatures; Classification
• ISSN: 0895-6111; 1879-0771
• DOI: 10.1016/j.compmedimag.2018.01.005

•A novel method to detect and classify several classes of lung tissue is presented.•The method leverages recent advances in visual pattern recognition.•Grayscale and frequency domain data help generate optimal texture signatures.•A multiclass tissue classification accuracy of 80.31% is observed.•The accuracy of the ground truth for the ILD dataset is justifiably questioned. A novel method to detect and classify several classes of diseased and healthy lung tissue of interstitial lung diseases is presented, as these diseases are hard to diagnose and differentiate. Local organizations of image directions at several scales drive the process of creating discriminative lung tissue texture signatures using spatial and Fourier domain information extracted from the images. The signatures are generated for four diseased tissue classes and healthy tissue, all of which appear in the Interstitial Lung Disease (ILD) database, using a novel one-versus-one approach for learning discriminative filter signatures. A multiclass tissue classification accuracy of 80.31% is observed using Radial Basis Function (RBF) Support Vector Machines (SVMs). The presented method compares well against a variety of state-of-the-art approaches. Another strong feature of our approach is the ability to access the individual class probabilities before a final classification decision is made. This enables an analysis of the causes of misclassification in this paper. We also make the case against total reliance on the accuracy of the ground truth given that the ILD database only contains a single label for a specific region and sometimes more than one pattern can be present, particularly for regions classified as healthy tissue. Measures to address misclassifications in this context are also proposed.