Bone suppression of lateral chest x-rays with imperfect and limited dual-energy subtraction images. (April 2023)

• Record Type: Journal Article
• Authors: Liu, Yunbi; Zeng, Fengxia; Ma, Mengwei; Zheng, Bowen; Yun, Zhaoqiang; Qin, Genggeng; Yang, Wei; Feng, Qianjin
• Is Part Of: Computerized medical imaging and graphics. Volume 105(2023)
• Publication Date: 2023-04
• Subjects: Bone suppression -- Lateral chest X-ray -- Deep learning; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2023.102186
• Languages: English
• ISSNs: 0895-6111

Abstract

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. Highlights: Unlike most studies that have studied bone suppression from frontal CXRs, we present for the first time a framework for bone suppression from lateral CXRs. We propose to leverage an ensemble framework named as MsDd-MAP to predict bone images of lateral CXRs at multiple scales in both intensity and gradient domains and fuse the final prediction in a maximum-a-posteriori (MAP) framework. A correction procedure is proposed to improve the quality of initially estimated soft-tissue and bone images from the primary model. Furthermore, we construct a relatively large-scale corrected dataset that contains knowledge from both the primary model and the correction procedure to train a distillated model.