A feature-based affine registration method for capturing background lung tissue deformation for ground glass nodule tracking. Issue 5 (3rd September 2022)

• Record Type: Journal Article
• Authors: Ben-Zikri, Yehuda K.; Helguera, María; Fetzer, David; Shrier, David A.; Aylward, Stephen. R.; Chittajallu, Deepak; Niethammer, Marc; Cahill, Nathan D.; Linte, Cristian A.
• Is Part Of: Computer methods in biomechanics and biomedical engineering. Volume 10:Issue 5(2022)
• Page Start: 521
• Page End: 539
• Publication Date: 2022-09-03
• Subjects: Lung ct imaging -- pulmonary nodule tracking -- background lung tissue deformation -- intensity- and feature-based affine registration -- non-rigid registration -- target registration error; Imaging systems in biology -- Periodicals; Imaging systems in medicine -- Periodicals; Biomechanics -- Data processing -- Periodicals; Biomedical engineering -- Periodicals; 616.0757
• DOI: 10.1080/21681163.2021.1994471
• Languages: English
• ISSNs: 2168-1163

Abstract

ABSTRACT: Apparent changes in lung nodule size assessed via simple image-based measurements from computed tomography (CT) images may be compromised by the effect of the background lung tissue deformation on the nodule, leading to erroneous nodule tracking. We propose a feature-based affine registration method and study its performance vis-a-vis several other registration methods. We implement and test each registration method using a lung- and a lesion-centred region of interest on 10 patient CT datasets featuring 12 nodules. We evaluate each registration method according to the target registration error (TRE) computed across 30–50 homologous fiducial landmarks selected by expert radiologists. Our results show that the proposed feature-based affine lesion-centred registration yielded a 1.11.2 mm TRE, while a Symmetric Normalisation deformable registration yielded a 1.21.2 mm TRE, with a baseline least-square fit of the validation fiducial landmarks of 1.51.2 mm TRE. The proposed feature-based affine registration is computationally efficient, eliminates the need for nodule segmentation, and reduces the susceptibility of artificial deformations. We also conducted a pilot pre-clinical study that showed the proposed feature-based lesion-centred affine registration effectively compensates for the background lung tissue deformation and serves as a reliable baseline registration method prior to assessing lung nodule changes due to disease.