Automatic detection of tree-in-bud patterns for computer assisted diagnosis of respiratory tract infections
33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2011), 5096–5099
Abstract
Abnormal nodular branching opacities at the lung periphery in Chest Computed Tomography (CT) are termed by radiology literature as tree-in-bud (TIB) opacities. These subtle opacity differences represent pulmonary disease in the small airways such as infectious or inflammatory bronchiolitis. Precisely quantifying the detection and measurement of TIB abnormality using computer assisted detection (CAD) would assist clinical and research investigation of this pathology commonly seen in pulmonary infections. This paper presents a novel method for automatically detecting TIB patterns based on fast localization of candidates using local scale information of the images. The proposed method combines shape index, local gradient statistics, and steerable wavelet features to automatically identify TIB patterns. Experimental results using 39 viral bronchiolitis human para-influenza (HPIV) CTs and 21 normal lung CTs achieved an overall accuracy of 89.95%.
Abstract sourceThis 2011 EMBC paper presents a method for identifying tree-in-bud patterns in chest CT images. The authors evaluated it on CT scans from 39 patients with viral bronchiolitis and 21 normal lung CT scans.
Summary
The paper describes a computer-assisted method to detect tree-in-bud (TIB) patterns—small branching opacities associated with small-airway disease—in chest computed tomography (CT). The method first uses locally adaptive scale filtering to identify candidate regions, then combines shape index, local gradient statistics and steerable wavelet features, with a support vector machine classifier, to distinguish TIB patterns from normal regions. The authors report an overall accuracy of 89.95% on CT scans from 39 patients with viral bronchiolitis and 21 normal lung CT scans. The evaluation used two-fold cross-validation; the paper notes that the data had 5 mm slice spacing and that quantitative evaluation of disease severity was not addressed. Read the paper.
Cite this work
Ulaş Bağci; Jianhua Yao; Jesus Caban; Tara N Palmore; Anthony F Suffredini; Daniel J Mollura (2011). Automatic detection of tree-in-bud patterns for computer assisted diagnosis of respiratory tract infections. 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2011), 5096–5099 https://doi.org/10.1109/IEMBS.2011.6091262
BibTeX