Comparison of different deep learning architectures for synthetic CT generation from MR images

TL;DR

This study compares various deep learning architectures for generating synthetic CT images from MRI scans, finding that eCNN and ResNet perform best in accuracy and image quality, offering promising tools for MRI-guided radiation planning.

Contribution

The paper provides a comparative analysis of multiple deep learning models for sCT generation, highlighting the superior performance of eCNN and ResNet architectures over traditional and other deep learning methods.

Findings

eCNN achieved the lowest MAE and ME in pelvis region

ResNet had the highest PSNR among tested models

eCNN showed superior tissue segmentation accuracy

Abstract

MRI-guided radiation treatment planning is widely applied because of its superior soft-tissue contrast and no ionization radiation compared to CT-based planning. In this regard, synthetic CT (sCT) images should be generated from the patients MRI scans if radiation treatment planning is sought. Among the different available methods for this purpose, the deep learning algorithms have and do outperform their conventional counterparts. In this study, we investigated the performance of some most popular deep learning architectures including eCNN, U-Net, GAN, V-Net, and Res-Net for the task of sCT generation. As a baseline, an atlas-based method is implemented to which the results of the deep learning-based model are compared. A dataset consisting of 20 co-registered MR-CT pairs of the male pelvis is applied to assess the different sCT production methods' performance. The mean error (ME), mean absolute error (MAE), Pearson correlation coefficient (PCC), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR) metrics were computed between the estimated sCT and the ground truth (reference) CT images. The visual inspection revealed that the sCTs produced by eCNN, V-Net, and ResNet, unlike the other methods, were less noisy and greatly resemble the ground truth CT image. In the whole pelvis region, the eCNN yielded the lowest MAE (26.03-8.85 HU) and ME (0.82-7.06 HU), and the highest PCC metrics were yielded by the eCNN (0.93-0.05) and ResNet (0.91-0.02) methods. The ResNet model had the highest PSNR of 29.38-1.75 among all models. In terms of the Dice similarity coefficient, the eCNN method revealed superior performance in major tissue identification (air, bone, and soft tissue). All in all, the eCNN and ResNet deep learning methods revealed acceptable performance with clinically tolerable quantification errors.