English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Topological texture features were compared in their ability to classifymorphological patterns known as 'honeycombing' that are considered indicativefor the presence of fibrotic interstitial lung diseases in high-resolutioncomputed tomography (HRCT) images. For 14 patients with known occurrence ofhoney-combing, a stack of 70 axial, lung kernel reconstructed images wereacquired from HRCT chest exams. A set of 241 regions of interest of bothhealthy and pathological (89) lung tissue were identified by an experiencedradiologist. Texture features were extracted using six properties calculatedfrom gray-level co-occurrence matrices (GLCM), Minkowski Dimensions (MDs), andthree Minkowski Functionals (MFs, e.g. MF.euler). A k-nearest-neighbor (k-NN)classifier and a Multilayer Radial Basis Functions Network (RBFN) wereoptimized in a 10-fold cross-validation for each texture vector, and theclassification accuracy was calculated on independent test sets as aquantitative measure of automated tissue characterization. A Wilcoxonsigned-rank test was used to compare two accuracy distributions and thesignificance thresholds were adjusted for multiple comparisons by theBonferroni correction. The best classification results were obtained by the MFfeatures, which performed significantly better than all the standard GLCM andMD features (p < 0.005) for both classifiers. The highest accuracy was foundfor MF.euler (97.5%, 96.6%; for the k-NN and RBFN classifier, respectively).The best standard texture features were the GLCM features 'homogeneity' (91.8%,87.2%) and 'absolute value' (90.2%, 88.5%). The results indicate that advancedtopological texture features can provide superior classification performance incomputer-assisted diagnosis of interstitial lung diseases when compared tostandard texture analysis methods.

Classification of interstitial lung disease patterns with topological texture features