Diffeomorphic Lung Registration Using Deep CNNs and Reinforced Learning
Overview
Affiliations
Image registration is a well-known problem in the field of medical imaging. In this paper, we focus on the registration of chest inspiratory and expiratory computed tomography (CT) scans from the same patient. Our method recovers the diffeomorphic elastic displacement vector field (DVF) by jointly regressing the direct and the inverse transformation. Our architecture is based on the RegNet network but we implement a reinforced learning strategy that can accommodate a large training dataset. Our results show that our method performs with a lower estimation error for the same number of epochs than the RegNet approach.
Artificial general intelligence for radiation oncology.
Liu C, Liu Z, Holmes J, Zhang L, Zhang L, Ding Y Meta Radiol. 2024; 1(3).
PMID: 38344271 PMC: 10857824. DOI: 10.1016/j.metrad.2023.100045.
A review of deep learning-based deformable medical image registration.
Zou J, Gao B, Song Y, Qin J Front Oncol. 2022; 12:1047215.
PMID: 36568171 PMC: 9768226. DOI: 10.3389/fonc.2022.1047215.
Artificial Intelligence in Radiation Therapy.
Fu Y, Zhang H, Morris E, Glide-Hurst C, Pai S, Traverso A IEEE Trans Radiat Plasma Med Sci. 2022; 6(2):158-181.
PMID: 35992632 PMC: 9385128. DOI: 10.1109/TRPMS.2021.3107454.
Hasenstab K, Tabalon J, Yuan N, Retson T, Hsiao A Radiol Artif Intell. 2022; 4(1):e210211.
PMID: 35146437 PMC: 8823452. DOI: 10.1148/ryai.2021210211.
Artificial intelligence in functional imaging of the lung.
San Jose Estepar R Br J Radiol. 2021; 95(1132):20210527.
PMID: 34890215 PMC: 9153712. DOI: 10.1259/bjr.20210527.