Bone suppression of lateral chest x-rays with imperfect and limited dual-energy subtraction images

Yunbi Liu; Fengxia Zeng; Mengwei Ma; Bowen Zheng; Zhaoqiang Yun; Genggeng Qin; Wei Yang; Qianjin Feng

doi:10.1016/j.compmedimag.2023.102186

Bone suppression of lateral chest x-rays with imperfect and limited dual-energy subtraction images

Comput Med Imaging Graph. 2023 Apr:105:102186. doi: 10.1016/j.compmedimag.2023.102186. Epub 2023 Jan 21.

Authors

Yunbi Liu¹, Fengxia Zeng², Mengwei Ma², Bowen Zheng², Zhaoqiang Yun³, Genggeng Qin⁴, Wei Yang⁵, Qianjin Feng³

Affiliations

¹ School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, Guangdong 518172, China; Shenzhen Research Institute of Big Data, Shenzhen, China; University of Science and Technology of China, Hefei, China.
² Radiology Department, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China.
³ School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China.
⁴ Radiology Department, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China. Electronic address: zealotq@smu.edu.cn.
⁵ School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China. Electronic address: weiyanggm@gmail.com.

PMID: 36731328
DOI: 10.1016/j.compmedimag.2023.102186

Abstract

Bone suppression is to suppress the superimposed bone components over the soft tissues within the lung area of Chest X-ray (CXR), which is potentially useful for the subsequent lung disease diagnosis for radiologists, as well as computer-aided systems. Despite bone suppression methods for frontal CXRs being well studied, it remains challenging for lateral CXRs due to the limited and imperfect DES dataset containing paired lateral CXR and soft-tissue/bone images and more complex anatomical structures in the lateral view. In this work, we propose a bone suppression method for lateral CXRs by leveraging a two-stage distillation learning strategy and a specific data correction method. Specifically, a primary model is first trained on a real DES dataset with limited samples. The bone-suppressed results on a relatively large lateral CXR dataset produced by the primary model are improved by a designed gradient correction method. Secondly, the corrected results serve as training samples to train the distillated model. By automatically learning knowledge from both the primary model and the extra correction procedure, our distillated model is expected to promote the performance of the primary model while omitting the tedious correction procedure. We adopt an ensemble model named MsDd-MAP for the primary and distillated models, which learns the complementary information of Multi-scale and Dual-domain (i.e., intensity and gradient) and fuses them in a maximum-a-posteriori (MAP) framework. Our method is evaluated on a two-exposure lateral DES dataset consisting of 46 subjects and a lateral CXR dataset consisting of 240 subjects. The experimental results suggest that our method is superior to other competing methods regarding the quantitative evaluation metrics. Furthermore, the subjective evaluation by three experienced radiologists also indicates that the distillated model can produce more visually appealing soft-tissue images than the primary model, even comparable to real DES imaging for lateral CXRs.

Keywords: Bone suppression; Deep learning; Lateral chest X-ray.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Bone and Bones
Humans
Radiography
Radiography, Thoracic* / methods
Thorax*
X-Rays