Deep learning‐based convolutional neural network for intramodality brain MRI synthesis

Abstract

Purpose The existence of multicontrast magnetic resonance (MR) images increases the level of clinical information available for the diagnosis and treatment of brain cancer patients. However, acquiring the complete set of multicontrast MR images is not always practically feasible. In this study, we developed a state‐of‐the‐art deep learning convolutional neural network (CNN) for image‐to‐image translation across three standards MRI contrasts for the brain. Methods BRATS’2018 MRI dataset of 477 patients clinically diagnosed with glioma brain cancer was used in this study, with each patient having T1‐weighted (T1), T2‐weighted (T2), and FLAIR contrasts. It was randomly split into 64%, 16%, and 20% as training, validation, and test set, respectively. We developed a U‐Net model to learn the nonlinear mapping of a source image contrast to a target image contrast across three MRI contrasts. The model was trained and validated with 2D paired MR images using a mean‐squared error (MSE) cost function, Adam optimizer with 0.001 learning rate, and 120 epochs with a batch size of 32. The generated synthetic‐MR images were evaluated against the ground‐truth images by computing the MSE, mean absolute error (MAE), peak signal‐to‐noise ratio (PSNR), and structural similarity index (SSIM). Results The generated synthetic‐MR images with our model were nearly indistinguishable from the real images on the testing dataset for all translations, except synthetic FLAIR images had slightly lower quality and exhibited loss of details. The range of average PSNR, MSE, MAE, and SSIM values over the six translations were 29.44–33.25 dB, 0.0005–0.0012, 0.0086–0.0149, and 0.932–0.946, respectively. Our results were as good as the best‐reported results by other deep learning models on BRATS datasets. Conclusions Our U‐Net model exhibited that it can accurately perform image‐to‐image translation across brain MRI contrasts. It could hold great promise for clinical use for improved clinical decision‐making and better diagnosis of brain cancer patients due to the availability of multicontrast MRIs. This approach may be clinically relevant and setting a significant step to efficiently fill a gap of absent MR sequences without additional scanning.

Deep-learning-based generation of synthetic 6-minute MRI from 2-minute MRI for use in head and neck cancer radiotherapy

“…In their study, the authors sought to generate synthetic post-contrast T1-weighted (T1w) scans from pre-contrast T1w and T2w scans, which yielded average whole-image SSIM values of 0.88 in their test set for their best-performing model. Moreover, several studies synthesizing T1w or T2w scans also reported similar SSIM values, often in the range of 0.85-0.95 ( 22 , 25 , 29 , 30 ). Therefore, it is encouraging that our whole-image SSIM values of 0.93 are comparable or even superior to those currently reported.…”

“…Additionally, it warrants mentioning that the raw outputs of the DL model were often blurrier than their ground-truth counterparts. This effect has been widely documented in synthetic image studies ( 15 , 20 , 22 , 24 , 25 , 30 ), often driven by a lower spatial resolution input image up-sampled to match a higher spatial resolution output image. While this slight blurring effect is unlikely to affect underlying image quality (as evidenced by metric performance), in supplementary analyses we demonstrated that this difference was perceived by the clinicians and added bias to the analysis.…”

Contrast‐enhanced MRI synthesis using dense‐dilated residual convolutions based 3D network toward elimination of gadolinium in neuro‐oncology

“…MRI synthesis approaches based on deep learning currently serve as an emerging field of research in neuro-oncology. 8,9 In particular, various deep learning-based approaches have been investigated for contrast-enhanced MRI synthesis toward reduction 7,[10][11][12][13] or even elimination 8,[14][15][16][17][18][19][20][21][22] of gadolinium contrast agents in glioma patients. The former involves methods that propose the synthesis of full-dose contrast-enhanced images from their low-dose counterparts (e.g., 10% low-dose).…”

Deep-Learning-Based Generation of Synthetic High-Resolution MRI from Low-Resolution MRI for Use in Head and Neck Cancer Adaptive Radiotherapy

“…One less routinely studied domain is synthetic image generation, i.e., mapping an input image to an output image. Recent work has highlighted the utility of DL for synthetically generating CT images from MRI sequences (14)(15)(16)(17)(18)(19)(20)(21), MRI sequences from CT images (22)(23)(24)(25)(26), and MRI sequences from other MRI sequences (27)(28)(29)(30)(31). However, to date, no studies have investigated the feasibility of using DL to generate high-resolution synthetic MRI sequences from low-resolution MRI sequences to decrease the required scan time for HNC-related imaging.…”