Synthesis of magnetic resonance images from computed tomography data using convolutional neural network with contextual loss function

Abstract

Background: Magnetic resonance imaging (MRI) images synthesized from computed tomography (CT) data can provide more detailed information on pathological structures than that of CT data alone; thus, the synthesis of MRI has received increased attention especially in medical scenarios where only CT images are available. A novel convolutional neural network (CNN) combined with a contextual loss function was proposed for synthesis of T1-and T2-weighted images (T1WI and T2WI) from CT data.Methods: A total of 5,053 and 5,081 slices of T1WI and T2WI, respectively were selected for the dataset of CT and MRI image pairs. Affine registration, image denoising, and contrast enhancement were done on the aforementioned multi-modality medical image dataset comprising T1WI, T2WI, and CT images of the brain. A deep CNN was then proposed by modifying the ResNet structure to constitute the encoder and decoder of U-Net, called double ResNet-U-Net (DRUNet). Three different loss functions were utilized to optimize the parameters of the proposed models: mean squared error (MSE) loss, binary crossentropy (BCE) loss, and contextual loss. Statistical analysis of the independent-sample t-test was conducted by comparing DRUNets with different loss functions and different network layers. Results: DRUNet-101 with contextual loss yielded higher values of peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and Tenengrad function (i.e., 34.25±2.06, 0.97±0.03, and 17.03±2.75 for T1WI and 33.50±1.08, 0.98±0.05, and 19.76±3.54 for T2WI respectively). The results were statistically significant at P<0.001 with a narrow confidence interval of difference, indicating the superiority of DRUNet-101 with contextual loss. In addition, both image zooming and difference maps presented for the final synthetic MR images visually reflected the robustness of DRUNet-101 with contextual loss. The visualization of convolution filters and feature maps showed that the proposed model can generate synthetic MR images with high-frequency information. Conclusions: The results demonstrated that DRUNet-101 with contextual loss function provided better high-frequency information in synthetic MR images compared with the other two functions. The proposed DRUNet model has a distinct advantage over previous models in terms of PSNR, SSIM, and Tenengrad score.Overall, DRUNet-101 with contextual loss is recommended for synthesizing MR images from CT scans.

Neurosonographic Classification in Premature Infants Receiving Omega-3 Supplementation Using Convolutional Neural Networks

“…The architecture of our network is based on a simpler model compared with the networks presented in previous studies [29,30]. Although it consists of fewer layers, we achieved stable accuracy and loss curves during the training process after a certain number of iterations, indicating a satisfactory level of learning and generalization of the model [36]. Such a simpler architecture contributes to faster execution, requires fewer resources, reduces the tendency for overfitting, facilitates interpretation, and lowers the risk of overfitting, especially in clinical settings where rapid diagnosis is crucial.…”

Improved edge gradient image clarity evaluation algorithm

“…The clarity ratio is defined as the ratio of the maximum value of the focus evaluation function to the minimum value, and the expression is shown in equation (9).…”

Improving Solar Radiation Forecasting Utilizing Data Augmentation Model Generative Adversarial Networks with Convolutional Support Vector Machine (GAN-CSVR)

“…It reduces the sum of the squares of the variations between the genuine and synthetic specimens in meteorological data. The MSE loss function is defined in Equation ( 4) [40]:…”