Near-Affine-Invariant Texture Learning for Lung Tissue Analysis Using Isotropic Wavelet Frames

Depeursinge, AdrienVan de Ville, DimitriPlaton, AlexandraGeissbuhler, AntoinePoletti, Pierre-AlexandreMueller, Henning2012-07-272012-07-272012-07-27201210.1109/TITB.2012.2198829https://infoscience.epfl.ch/handle/20.500.14299/84249WOS:000305979500016We propose near-affine-invariant texture descriptors derived from isotropic wavelet frames for the characterization of lung tissue patterns in high-resolution computed tomography (HRCT) imaging. Affine invariance is desirable to enable learning of nondeterministic textures without a priori localizations, orientations, or sizes. When combined with complementary gray-level histograms, the proposed method allows a global classification accuracy of 76.9% with balanced precision among five classes of lung tissue using a leave-one-patient-out cross validation, in accordance with clinical practice.High-resolution computed tomography (HRCT)interstitial lung diseases (ILDs)isotropic wavelet frameslung tissue analysistexture analysisHigh-Resolution CtComputed-Tomography FindingsQuantitative-AnalysisMedical ImagesClassificationDiseasesSegmentationRetrievalSystemHrctNear-Affine-Invariant Texture Learning for Lung Tissue Analysis Using Isotropic Wavelet Framestext::journal::journal article::research article