Three-stage Registration Pipeline for Dynamic Lung Field of Chest X-ray Images Based on Convolutional Neural Networks

Yingjian Yang ¹ Jie Zheng ¹ Peng Guo ¹ Qi Gao ² Yingwei Guo ^3* Ziran Chen ^1,4 Chengcheng Liu ⁵ Tianqi Wu ¹ Zhanglei Ouyang ¹ Huai Chen ^6* Yan Kang ^7*

• ¹ Department of Radiological Research and Development, Shenzhen Lanmage Medical Technology Co., Ltd, Shenzhen, China
• ² Neusoft Medical Systems Co., Ltd., Shenyang, Liaoning Province, China
• ³ Schol of Electrical and Information Engineering, Northeast Petroleum University, Daqing, China
• ⁴ College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning Province, China
• ⁵ School of Life and Health Management, Shenyang City University, Shenyang, Liaoning Province, China
• ⁶ Department of Radiology, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, Guangdong Province, China
• ⁷ College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen, Guangdong, China

The anatomically constrained registration network (AC-RegNet), which yields anatomically plausible results, has emerged as the state-of-the-art registration architecture for chest X-ray (CXR) images. Nevertheless, accurate lung field registration results may be more favored and exciting than the registration results of the entire CXR images and hold promise for dynamic lung field analysis in clinical practice.Objective: Based on the above, a registration model of the dynamic lung field of CXR images based on AC-RegNet and static CXR images is urgently developed to register these dynamic lung fields for clinical quantitative analysis.Methods: This paper proposes a fully automatic three-stage registration pipeline for the dynamic lung field of CXR images. First, the dynamic lung field mask images are generated from a pre-trained standard lung field segmentation model with the dynamic CXR images. Then, a lung field abstraction model is designed to generate the dynamic lung field images based on the dynamic lung field mask images and their corresponding CXR images. Finally, we propose a three-step registration training method to train the AC-RegNet, obtaining the registration network of the dynamic lung field images (AC-RegNet_V3). The proposed AC-RegNet_V3 with the four basic segmentation networks achieve the mean dice similarity coefficient (DSC) of 0.991, 0.993, 0.993, and 0.993, mean Hausdorff distance (HD) of 12.512, 12.813, 12.449, and 13.661, mean average symmetric surface distance (ASSD) of 0.654, 0.550, 0.572, and 0.564, and mean squared distance (MSD) of 559.098, 577.797, 548.189, and 559.652, respectively. Besides, compared to the dynamic CXR images, the mean DSC of these four basic segmentation networks with AC-RegNet has been significantly improved by 7.2%, 7.4%, 7.4%, and 7.4% (p-value＜0.0001). Meanwhile, the mean HD has been significantly improved by 8. 994, 8.693, 9.057, and 7.845 (p-value＜0.0001). Similarly, the mean ASSD has significantly improved by 4.576, 4.680, 4.658, and 4.658 (p-value＜0.0001). Last, the mean MSD has significantly improved by 508.936, 519.776, 517.904, and 520.626 (p-value ＜0.0001).Our proposed three-stage registration pipeline has demonstrated its effectiveness in dynamic lung field registration. Therefore, it could become a powerful tool for dynamic lung field analysis in clinical practice, such as pulmonary airflow detection and air trapping location.