Distinctive local binary pattern for non‐rigid registration of lung computed tomography images. Issue 22 (12th October 2015)

• Record Type: Journal Article
• Authors: Cao, Zhulou; Dong, Enqing
• Is Part Of: Electronics letters. Volume 51:Issue 22(2015)
• Page Start: 1742
• Page End: 1744
• Publication Date: 2015-10-12
• Subjects: computerised tomography -- image registration -- lung -- medical image processing -- pattern recognition; distinctive local binary pattern -- nonrigid lung computed tomography image registration -- census transform -- lung motion discontinuity -- local intensity variation -- differential‐based registration methods -- high contrast images -- inverse‐consistent symmetrical method -- Lucas‐Kanade method -- 4D CT lung dataset -- bilateral filter‐based Demons; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2015.0598
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : Non‐rigid registration of lung computed tomography (CT) images is a valuable tool for various clinical applications. Many methods such as bilateral filters and census transform have been used to deal with discontinuity of lung motion and local intensity variation. However, census transform cannot distinguish between low and high contrast regions, which may lead to negative influence to differential‐based registration methods. A novel distinctive local binary pattern that can generate distinctive representations of high contrast images is proposed. Combing the novel local binary pattern, bilateral filters, the inverse‐consistent symmetrical method and the Lucas–Kanade method, a novel accurate image registration method is developed. The experiments are performed on the publicly available 4D CT lung dataset from DIR‐Lab. Compared with the census transform, the proposed distinctive local binary pattern can achieve relatively better results. The proposed image registration method greatly improves the accuracy of the classical Lucas–Kanade method and the bilateral filters‐based Demons. In addition, the proposed registration method is most accurate among all unmasked methods tested on this dataset.