Feasibility of Synthetic Computed Tomography Images Generated from Magnetic Resonance Imaging Scans Using Various Deep Learning Methods in the Planning of Radiation Therapy for Prostate Cancer

Abstract

We aimed to evaluate and compare the qualities of synthetic computed tomography (sCT) generated by various deep-learning methods in volumetric modulated arc therapy (VMAT) planning for prostate cancer. Simulation computed tomography (CT) and T2-weighted simulation magnetic resonance image from 113 patients were used in the sCT generation by three deep-learning approaches: generative adversarial network (GAN), cycle-consistent GAN (CycGAN), and reference-guided CycGAN (RgGAN), a new model which performed further adjustment of sCTs generated by CycGAN with available paired images. VMAT plans on the original simulation CT images were recalculated on the sCTs and the dosimetric differences were evaluated. For soft tissue, a significant difference in the mean Hounsfield unites (HUs) was observed between the original CT images and only sCTs from GAN (p = 0.03). The mean relative dose differences for planning target volumes or organs at risk were within 2% among the sCTs from the three deep-learning approaches. The differences in dosimetric parameters for D98% and D95% from original CT were lowest in sCT from RgGAN. In conclusion, HU conservation for soft tissue was poorest for GAN. There was the trend that sCT generated from the RgGAN showed best performance in dosimetric conservation D98% and D95% than sCTs from other methodologies.

Synthetic 18F-FDG PET Image Generation Using a Combination of Biomathematical Modeling and Machine Learning

“…Peng et al [ 14 ] trained a cGAN and a cycle-consistency GAN (cycleGAN) to generate synthetic CT images from MR images of nasopharyngeal carcinoma. Yoo et al [ 15 ] examined the quality of three different deep learning networks named GAN, CycGAN, and reference-guided GAN (RgGAN) for generating synthetic CT images of prostate cancer from T2-weighted MR images.…”

Channel-wise attention enhanced and structural similarity constrained cycleGAN for effective synthetic CT generation from head and neck MRI images

“…To address the aforementioned limitations, estimating Hounsfield Unit (HU) and generating synthetic-CT (sCT) from MR images using artificial intelligence (AI) algorithms may be a potential and effective solution in clinical setting, which have gained significant attention for image-to-image translation [ 17 – 23 ]. In recent years, data-driven AI has made tremendous developments in image processing, computer vision and pattern recognition.…”

Synthetic computed tomography generation for abdominal adaptive radiotherapy using low-field magnetic resonance imaging

“…DL techniques for the generation of sCT images from MRI have shown promising results for pelvis and brain imaging [26] , [11] , [12] , [13] , [14] , [15] , [16] , [17] . However, the use of these methods for the abdomen has been scarcely studied [25] , [18] , [19] , [20] , precisely in a region for which ART can be critical.…”