Development of Artificial Intelligence-Based Dual-Energy Subtraction for Chest Radiography

Abstract

Recently, some facilities have utilized the dual-energy subtraction (DES) technique for chest radiography to increase pulmonary lesion detectability. However, the availability of the technique is limited to certain facilities, in addition to other limitations, such as increased noise in high-energy images and motion artifacts with the one-shot and two-shot methods, respectively. The aim of this study was to develop artificial intelligence-based DES (AI–DES) technology for chest radiography to overcome these limitations. Using a trained pix2pix model on clinically acquired chest radiograph pairs, we successfully converted 130 kV images into virtual 60 kV images that closely resemble the real images. The averaged peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) between virtual and real 60 kV images were 33.8 dB and 0.984, respectively. We also achieved the production of soft-tissue- and bone-enhanced images using a weighted image subtraction process with the virtual 60 kV images. The soft-tissue-enhanced images exhibited sufficient bone suppression, particularly within lung fields. Although the bone-enhanced images contained artifacts on and around the lower thoracic and lumbar spines, superior sharpness and noise characteristics were presented. The main contribution of our development is its ability to provide selectively enhanced images for specific tissues using only high-energy images obtained via routine chest radiography. This suggests the potential to improve the detectability of pulmonary lesions while addressing challenges associated with the existing DES technique. However, further improvements are necessary to improve the image quality.