An automatic deformity path tracing and estimation technique for thoracic CT image sequences

Abstract

Clinical studies based on respiratory systems often suffer road blocks or might yield inconsistent results due to several artifacts creeping into data from a variety of subjects involved and their erratic, different-from-each other breathing patterns. This ultimately results in loss of valuable resources and time and finally ends up with potentially wrong and inconclusive results. The proposed technique can be seen as an automatic framework to establish deformity patterns in the thoracic region for an individual as well as for a set of diverse subjects using temporally sequenced thoracic (Computed Tomography) CT images for a full inhale-exhale breathing phase. Common feature points among the temporally sequential frames are traced for spatial movements, thus providing with the inter-frame duration displacements and ultimately total average displacement for all the points. The proposed work presents a unique and innovative arrangement of methods to compute the average deformation of the thoracic region from all anatomical positions. The credibility and performance of the above proposed method is demonstrated by its exemplary experimental results. © 2015 IEEE.