Detection of morphological structures for vessel wall segmentation in IVUS using Random Forests

L. LO VERCIO; M. DEL FRESNO; I. LARRABIDE

Tandil

Simposio; SIPAIM; 2016

Background: Intravascular ultrasound (IVUS) provides axial gray-scale images, allowing the assessment of ves-sel morphology and tissues. Automated segmentation of lumen-intima and media-adventitia interfaces is valuableto identify artery occlusion.Purpose: Bifurcations, shadows and echogenic plaques usually affect proper segmentation of the vessel wall.Thus, identification of these morphological structures is an advisable step when developing segmentation tech-niques, which have been dealing with this issue by using different features and methods in the past. The aim ofthis work is to develop a simultaneous classification method for IVUS image sectors into bifurcations, shadows,echogenic plaques and normal, as an intermediate step for the arterial wall segmentation.Methods: A 22-dimensional feature vector, mainly composed by current existing methods, is computed for eachcolumn in the polar image. To deal with this multiclass classification problem, Random Forest (RF) is used asclassifier. Due to the high skeweness of the problem, RFs are successively trained by resampling the trainingdata, specifically the majority class.Results: Fscore reaches 0.62, when the RF is trained with 15% of the normal samples of the training set.Thresholds found in the RF are close to the previously reported values for the features in the literature.Conclusion: Random Forest demonstrates good performance to classify morphological structures in IVUS.Random undersampling for training was useful to deal with the imbalanced data, and to manage the trade-offbetween precision and recall of minority classes. However, better features must be developed to improve theclassification of the structures, specially in the case of the echogenic plaque.