Synthesis of gadolinium-enhanced glioma images on multisequence magnetic resonance images using contrastive learning.

Abstract

Gadolinium-based contrast agents are commonly used in brain magnetic resonance imaging (MRI), however, they cannot be used by patients with allergic reactions or poor renal function. For long-term follow-up patients, gadolinium deposition in the body can cause nephrogenic systemic fibrosis and other potentialrisks. Developing a new method of enhanced image synthesis based on the advantages of multisequence MRI has important clinical value for these patients. In this paper, an end-to-end synthesis model structure similarity index measure (SSIM)-based Dual Constrastive Learning with Attention (SDACL) based on contrastive learning is proposed to synthesize contrast-enhanced T1 (T1ce) using three unenhanced MRI images of T1, T2, and Flair in patients withglioma. The model uses the attention-dilation generator to enlarge the receptive field by expanding the residual blocks and to strengthen the feature representation and context learning of multisequence MRI. To enhance the detail and texture performance of the imaged tumor area, a comprehensive loss function combining patch-level contrast loss and structural similarity loss is created, which can effectively suppress noise and ensure the consistency of synthesized images and real images. The normalized root-mean-square error (NRMSE), peak signal-to-noise ratio (PSNR), and SSIM of the model on the independent test set are 0.307 0.12, 23.337 3.21, and 0.881 0.05,respectively. Results show this method can be used for the multisequence synthesis of T1ce images, which can provide valuable information for clinical diagnosis.