文献类型：期刊文献

英文题名：Deformable registration of lung 3DCT images using an unsupervised heterogeneous multi-resolution neural network

作者：Chang, Qing[1];Zhang, Jieming[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai, Peoples R China

年份：2023

卷号：61

期号：9

起止页码：2353

外文期刊名：MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING

收录：;EI(收录号：20231713949733);WOS:【SCI-EXPANDED(收录号:WOS:000974266900001)】；

基金：This work was supported by the National Natural Science Foundation of China under award number 61976091.

语种：英文

外文关键词：Deep learning; Image registration; Deformable registration; Lung registration

摘要：Lung image registration is more challenging than other organs. This is because the breath of the human body causes large deformations in the lung parenchyma and small deformations in tissues such as the pulmonary vascular. Many studies have recently used multi-resolution networks to solve the lung registration problem. However, they use the same structure of registration modules on each level, which makes it difficult to handle complex and small deformations. We propose an unsupervised heterogeneous multi-resolution network (UHMR-Net) to overcome the above problem. The image detail registration module (IDRM) is designed on the highest resolution level. Within this module, the cascaded network is used on the same resolution image to continuously learn the "remaining" detail deformation fields. The shallow shrinkage loss (SS-Loss) is designed to supervise the cascaded network, thus further improving the ability of the network to handle small deformations. Moreover, with the lightweight feature local correlation layer we proposed, the image boundary registration module (IBRM), on multiple low-resolution levels, can better solve the large deformation registration problem. The target registration error on the public DIR-Lab 4DCT dataset was 1.56 +/- 1.39 mm, which was significantly better than the classic conventional methods and advanced deep-based methods.