MR Image Synthesis Research Articles

Research on multi-sequence MR image synthesis CT algorithm based on unsupervised method

BackgroundUsing multi-sequence MRI to synthesize CT, combining different MRI sequences, and processing synthetic CT (sCT) based on unsupervised algorithms, to conduct more in-depth and comprehensive research on MR-based radiotherapy planning. MethodsFirst, we compare and analyze the effects of single-sequence MRI synthesis to CT to determine the quality of the synthesis and find a set of optimal sequence combinations. In addition, the study introduces a Staged Multi-Sequence Fusion Network (SMSF-Net) that employs an unsupervised approach to effectively fuse information from multiple MRI sequences. The staged sequence fusion module can efficiently extract information from different sequences and combine complementary information from different sequences. Finally, image encoding is processed using a multi-layer convolutional network to generate synthetic CT images. ResultsIn this study, the mean absolute error (MAE), root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) of the SMSF-Net are 18.85, 84.62, 34.31, and 0.962, which are superior to other single-sequence models and multi-sequence models. Experiments show that the improvement of SMSF-Net is statistically significant. In the qualitative comparison experiment, sCT synthesized by SMSF-Net is superior to other models in detail in the synthesis of complex areas of bones and nasal cavities. ConclusionThis study proposes a Staged SMSF-Net. As a multi-sequence MRI synthesis sCT algorithm based on unsupervised learning, SMSF-Net can use the complementary information between multiple sequences to improve the quality of synthetic sCT. This study has reference value for MRI-only radiotherapy planning.

A multi-task generative model for simultaneous post-contrast MR image synthesis and brainstem glioma segmentation

ObjectivesThis study aims to generate post-contrast MR images reducing the exposure of gadolinium-based contrast agents (GBCAs) for brainstem glioma (BSG) detection, simultaneously delineating the BSG lesion, and providing high-resolution contrast information. MethodsA retrospective cohort of 30 patients diagnosed with brainstem glioma was included. Multi-contrast images, including pre-contrast T1 weighted (pre-T1w), T2 weighted (T2w), arterial spin labeling (ASL) and post-contrast T1w images, were collected. A multi-task generative model was developed to synthesize post-contrast T1w images and simultaneously segment BSG masks from the multi-contrast inputs. Performance evaluation was conducted using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean absolute error (MAE) metrics. A perceptual study was also undertaken to assess diagnostic quality. ResultsThe proposed model achieved SSIM of 0.86 ± 0.04, PSNR of 26.33 ± 0.05 and MAE of 57.20 ± 20.50 for post-contrast T1w image synthesis. Automated delineation of the BSG lesions achieved Dice similarity coefficient (DSC) score of 0.88 ± 0.27. ConclusionsThe proposed model can synthesize high-quality post-contrast T1w images and accurately segment the BSG region, yielding satisfactory DSC scores. Clinical relevance statementThe synthesized post-contrast MR image presented in this study has the potential to reduce the usage of gadolinium-based contrast agents, which may pose risks to patients. Moreover, the automated segmentation method proposed in this paper aids radiologists in accurately identifying the brainstem glioma lesion, facilitating the diagnostic process.

Generative adversarial network-based synthesis of contrast-enhanced MR images from precontrast images for predicting histological characteristics in breast cancer

Objective. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a sensitive tool for assessing breast cancer by analyzing tumor blood flow, but it requires gadolinium-based contrast agents, which carry risks such as brain retention and astrocyte migration. Contrast-free MRI is thus preferable for patients with renal impairment or who are pregnant. This study aimed to investigate the feasibility of generating contrast-enhanced MR images from precontrast images and to evaluate the potential use of synthetic images in diagnosing breast cancer. Approach. This retrospective study included 322 women with invasive breast cancer who underwent preoperative DCE-MRI. A generative adversarial network (GAN) based postcontrast image synthesis (GANPIS) model with perceptual loss was proposed to generate contrast-enhanced MR images from precontrast images. The quality of the synthesized images was evaluated using the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The diagnostic performance of the generated images was assessed using a convolutional neural network to predict Ki-67, luminal A and histological grade with the area under the receiver operating characteristic curve (AUC). The patients were divided into training (n = 200), validation (n = 60), and testing sets (n = 62). Main results. Quantitative analysis revealed strong agreement between the generated and real postcontrast images in the test set, with PSNR and SSIM values of 36.210 ± 2.670 and 0.988 ± 0.006, respectively. The generated postcontrast images achieved AUCs of 0.918 ± 0.018, 0.842 ± 0.028 and 0.815 ± 0.019 for predicting the Ki-67 expression level, histological grade, and luminal A subtype, respectively. These results showed a significant improvement compared to the use of precontrast images alone, which achieved AUCs of 0.764 ± 0.031, 0.741 ± 0.035, and 0.797 ± 0.021, respectively. Significance. This study proposed a GAN-based MR image synthesis method for breast cancer that aims to generate postcontrast images from precontrast images, allowing the use of contrast-free images to simulate kinetic features for improved diagnosis.

Learning Unified Hyper-Network for Multi-Modal MR Image Synthesis and Tumor Segmentation With Missing Modalities.

Accurate segmentation of brain tumors is of critical importance in clinical assessment and treatment planning, which requires multiple MR modalities providing complementary information. However, due to practical limits, one or more modalities may be missing in real scenarios. To tackle this problem, existing methods need to train multiple networks or a unified but fixed network for various possible missing modality cases, which leads to high computational burdens or sub-optimal performance. In this paper, we propose a unified and adaptive multi-modal MR image synthesis method, and further apply it to tumor segmentation with missing modalities. Based on the decomposition of multi-modal MR images into common and modality-specific features, we design a shared hyper-encoder for embedding each available modality into the feature space, a graph-attention-based fusion block to aggregate the features of available modalities to the fused features, and a shared hyper-decoder for image reconstruction. We also propose an adversarial common feature constraint to enforce the fused features to be in a common space. As for missing modality segmentation, we first conduct the feature-level and image-level completion using our synthesis method and then segment the tumors based on the completed MR images together with the extracted common features. Moreover, we design a hypernet-based modulation module to adaptively utilize the real and synthetic modalities. Experimental results suggest that our method can not only synthesize reasonable multi-modal MR images, but also achieve state-of-the-art performance on brain tumor segmentation with missing modalities.

Hybrid generative adversarial network based on a mixed attention fusion module for multi-modal MR image synthesis algorithm

Hybrid generative adversarial network based on a mixed attention fusion module for multi-modal MR image synthesis algorithm

Contouring Analysis on Synthetic Contrast-Enhanced MR from GRMM-GAN and Implications on MR-Guide Radiation Therapy

MR-guided linear accelerators have been commercialized making MR-only planning and adaptation an appealing alternative circumventing MR-CT registration. However, obtaining daily contrast-enhanced MR images can be prohibitive due to the increased risk of side effects from repeated contrast injections. In this work, we evaluate the quality of contrast-enhanced multi-modal MR image synthesis network GRMM-GAN (gradient regularized multi-modal multi-discrimination sparse-attention fusion generative adversarial network) for MR-guided radiation therapy. With IRB approval, we trained the GRMM-GAN based on 165 abdominal MR studies from 65 patients. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast enhanced (T1ce) images. The two pre-contrast MR modalities, T2 and T1pre images were adopted as inputs for GRMM-GAN, and the T1ce image at the portal venous phase was used as an output. Ten MR scans containing 21 liver tumors were selected for contouring analysis. A Turing test was first given to six radiation oncologists, in which 100 real T1ce and synthetic T1ce image slices are randomly given to the radiation oncologists to determine the authenticity of the synthesis. We then invited two radiation oncologists (RadOnc 1 and RadOnc2) to manually contour the 21 liver tumors independently on the real T1ce images. RadOnc2 then performed contouring on the respective synthetic T1ce MRs. DICE coefficient (defined as the intersection over the average of two volumes) and Hausdorff distance (HD, measuring how far two volumes are from each other) were used as analysis metrics. The DICE coefficients were calculated from the two radiation oncologists' contours on the real T1ce MR for each tumor. The DICE coefficients were also calculated from RadOnc 2's contours on real and synthetic MRs. Besides, tumor center shifts were extracted. The tumor center of mass coordinates was extracted from real and synthetic volumes. The difference in the coordinates indicated the shifts in the superior-inferior (SI), right-left (RL), and anterior-posterior (AP) directions between real and synthetic tumor volumes. An average of 52.3% test score was achieved from the six radiation oncologists, which is close to random guessing. RadOnc 1 and RadOnc 2, who had participated in the contouring analysis, achieved an average DICE of 0.91±0.02 from tumor volumes drawn on the real T1ce MRs. This result sets the inter-operator uncertainty baseline in the real clinical setting. RadOnc 2 achieved an average DICE (real vs. synth) of 0.90±0.04 and HD of 4.76±1.82 mm. Only sub-millimeter (SI: 0.67 mm, RL: 0.41 mm, AP: 0.39 mm) tumor center shifts were observed in all three directions. The GRMM-GAN method has the potential for MR-guided liver radiation when contrast agents cannot be administered daily and provide synthetic contrast-enhanced MR for better tumor targeting. The network can produce synthetic MR images with satisfactory contour agreement and geometric integrity.

A paired dataset of T1- and T2-weighted MRI at 3 Tesla and 7 Tesla

Brain magnetic resonance imaging (MRI) provides detailed soft tissue contrasts that are critical for disease diagnosis and neuroscience research. Higher MRI resolution typically comes at the cost of signal-to-noise ratio (SNR) and tissue contrast, particularly for more common 3 Tesla (3T) MRI scanners. At ultra-high magnetic field strength, 7 Tesla (7T) MRI allows for higher resolution with greater tissue contrast and SNR. However, the prohibitively high costs of 7T MRI scanners deter their widespread adoption in clinical and research centers. To obtain higher-quality images without 7T MRI scanners, algorithms that can synthesize 7T MR images from 3T MR images are under active development. Here, we make available a dataset of paired T1-weighted and T2-weighted MR images at 3T and 7T of 10 healthy subjects to facilitate the development and evaluation of 3T-to-7T MR image synthesis models. The quality of the dataset is assessed using image quality metrics implemented in MRIQC.

Contrast-Enhanced Liver Magnetic Resonance Image Synthesis Using Gradient Regularized Multi-Modal Multi-Discrimination Sparse Attention Fusion GAN.

To provide abdominal contrast-enhanced MR image synthesis, we developed an gradient regularized multi-modal multi-discrimination sparse attention fusion generative adversarial network (GRMM-GAN) to avoid repeated contrast injections to patients and facilitate adaptive monitoring. With IRB approval, 165 abdominal MR studies from 61 liver cancer patients were retrospectively solicited from our institutional database. Each study included T2, T1 pre-contrast (T1pre), and T1 contrast-enhanced (T1ce) images. The GRMM-GAN synthesis pipeline consists of a sparse attention fusion network, an image gradient regularizer (GR), and a generative adversarial network with multi-discrimination. The studies were randomly divided into 115 for training, 20 for validation, and 30 for testing. The two pre-contrast MR modalities, T2 and T1pre images, were adopted as inputs in the training phase. The T1ce image at the portal venous phase was used as an output. The synthesized T1ce images were compared with the ground truth T1ce images. The evaluation metrics include peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). A Turing test and experts' contours evaluated the image synthesis quality. The proposed GRMM-GAN model achieved a PSNR of 28.56, an SSIM of 0.869, and an MSE of 83.27. The proposed model showed statistically significant improvements in all metrics tested with p-values < 0.05 over the state-of-the-art model comparisons. The average Turing test score was 52.33%, which is close to random guessing, supporting the model's effectiveness for clinical application. In the tumor-specific region analysis, the average tumor contrast-to-noise ratio (CNR) of the synthesized MR images was not statistically significant from the real MR images. The average DICE from real vs. synthetic images was 0.90 compared to the inter-operator DICE of 0.91. We demonstrated the function of a novel multi-modal MR image synthesis neural network GRMM-GAN for T1ce MR synthesis based on pre-contrast T1 and T2 MR images. GRMM-GAN shows promise for avoiding repeated contrast injections during radiation therapy treatment.

Bidirectional feature matching based on deep pairwise contrastive learning for multiparametric MRI image synthesis

Objective. Multi-parametric MR image synthesis is an effective approach for several clinical applications where specific modalities may be unavailable to reach a diagnosis. While technical and practical conditions limit the acquisition of new modalities for a patient, multimodal image synthesis combines multiple modalities to synthesize the desired modality. Approach. In this paper, we propose a new multi-parametric magnetic resonance imaging (MRI) synthesis model, which generates the target MRI modality from two other available modalities, in pathological MR images. We first adopt a contrastive learning approach that trains an encoder network to extract a suitable feature representation of the target space. Secondly, we build a synthesis network that generates the target image from a common feature space that approximately matches the contrastive learned space of the target modality. We incorporate a bidirectional feature learning strategy that learns a multimodal feature matching function, in two opposite directions, to transform the augmented multichannel input in the learned target space. Overall, our training synthesis loss is expressed as the combination of the reconstruction loss and a bidirectional triplet loss, using a pair of features. Main results. Compared to other state-of-the-art methods, the proposed model achieved an average improvement rate of 3.9% and 3.6% on the IXI and BraTS’18 datasets respectively. On the tumor BraTS’18 dataset, our model records the highest Dice score of 0.793(0.04) for preserving the synthesized tumor regions in the segmented images. Significance. Validation of the proposed model on two public datasets confirms the efficiency of the model to generate different MR contrasts, and preserve tumor areas in the synthesized images. In addition, the model is flexible to generate head and neck CT image from MR acquisitions. In future work, we plan to validate the model using interventional iMRI contrasts for MR-guided neurosurgery applications, and also for radiotherapy applications. Clinical measurements will be collected during surgery to evaluate the model’s performance.

A least square generative network based on invariant contrastive feature pair learning for multimodal MR image synthesis.

During MR-guided neurosurgical procedures, several factors may limit the acquisition of additional MR sequences, which are needed by neurosurgeons to adjust surgical plans or ensure complete tumor resection. Automatically synthesized MR contrasts generated from other available heterogeneous MR sequences could alleviate timing constraints. We propose a new multimodal MR synthesis approach leveraging a combination of MR modalities presenting glioblastomas to generate an additional modality. The proposed learning approach relies on a least square GAN (LSGAN) using an unsupervised contrastive learning strategy. We incorporate a contrastive encoder, which extracts an invariant contrastive representation from augmented pairs of the generated and real target MR contrasts. This contrastive representation describes a pair of features for each input channel, allowing to regularize the generator to be invariant to the high-frequency orientations. Moreover, when training the generator, we impose on the LSGAN loss another term reformulated as the combination of a reconstruction and a novel perception loss based on a pair of features. When compared to other multimodal MR synthesis approaches evaluated on the BraTS'18 brain dataset, the model yields the highest Dice score with [Formula: see text] and achieves the lowest variability information of [Formula: see text], with a probability rand index score of [Formula: see text] and a global consistency error of [Formula: see text]. The proposed model allows to generate reliable MR contrasts with enhanced tumors on the synthesized image using a brain tumor dataset (BraTS'18). In future work, we will perform a clinical evaluation of residual tumor segmentations during MR-guided neurosurgeries, where limited MR contrasts will be acquired during the procedure.

Label-informed cardiac magnetic resonance image synthesis through conditional generative adversarial networks.

Synthesis of a large set of high-quality medical images with variability in anatomical representation and image appearance has the potential to provide solutions for tackling the scarcity of properly annotated data in medical image analysis research. In this paper, we propose a novel framework consisting of image segmentation and synthesis based on mask-conditional GANs for generating high-fidelity and diverse Cardiac Magnetic Resonance (CMR) images. The framework consists of two modules: i) a segmentation module trained using a physics-based simulated database of CMR images to provide multi-tissue labels on real CMR images, and ii) a synthesis module trained using pairs of real CMR images and corresponding multi-tissue labels, to translate input segmentation masks to realistic-looking cardiac images. The anatomy of synthesized images is based on labels, whereas the appearance is learned from the training images. We investigate the effects of the number of tissue labels, quantity of training data, and multi-vendor data on the quality of the synthesized images. Furthermore, we evaluate the effectiveness and usability of the synthetic data for a downstream task of training a deep-learning model for cardiac cavity segmentation in the scenarios of data replacement and augmentation. The results of the replacement study indicate that segmentation models trained with only synthetic data can achieve comparable performance to the baseline model trained with real data, indicating that the synthetic data captures the essential characteristics of its real counterpart. Furthermore, we demonstrate that augmenting real with synthetic data during training can significantly improve both the Dice score (maximum increase of 4%) and Hausdorff Distance (maximum reduction of 40%) for cavity segmentation, suggesting a good potential to aid in tackling medical data scarcity.

LEGAN: A Light and Effective Generative Adversarial Network for medical image synthesis

Medical image synthesis plays an important role in clinical diagnosis by providing auxiliary pathological information. However, previous methods usually utilize the one-step strategy designed for wild image synthesis, which are not sensitive to local details of tissues within medical images. In addition, these methods consume a great number of computing resources in generating medical images, which seriously limits their applicability in clinical diagnosis. To address the above issues, a Light and Effective Generative Adversarial Network (LEGAN) is proposed to generate high-fidelity medical images in a lightweight manner. In particular, a coarse-to-fine paradigm is designed to imitate the painting process of humans for medical image synthesis within a two-stage generative adversarial network, which guarantees the sensitivity to local information of medical images. Furthermore, a low-rank convolutional layer is introduced to construct LEGAN for lightweight medical image synthesis, which utilizes principal components of full-rank convolutional kernels to reduce model redundancy. Additionally, a multi-stage mutual information distillation is devised to maximize dependencies of distributions between generated and real medical images in model training. Finally, extensive experiments are conducted in two typical tasks, i.e., retinal fundus image synthesis and proton density weighted MR image synthesis. The results demonstrate that LEGAN outperforms the comparison methods by a significant margin in terms of Fréchet inception distance (FID) and Number of parameters (NoP).

Deformable MR-CT image registration using an unsupervised, dual-channel network for neurosurgical guidance.

The accuracy of minimally invasive, intracranial neurosurgery can be challenged by deformation of brain tissue - e.g., up to 10mm due to egress of cerebrospinal fluid during neuroendoscopic approach. We report an unsupervised, deep learning-based registration framework to resolve such deformations between preoperative MR and intraoperative CT with fast runtime for neurosurgical guidance. The framework incorporates subnetworks for MR and CT image synthesis with a dual-channel registration subnetwork (with synthesis uncertainty providing spatially varying weights on the dual-channel loss) to estimate a diffeomorphic deformation field from both the MR and CT channels. An end-to-end training is proposed that jointly optimizes both the synthesis and registration subnetworks. The proposed framework was investigated using three datasets: (1) paired MR/CT with simulated deformations; (2) paired MR/CT with real deformations; and (3) a neurosurgery dataset with real deformation. Two state-of-the-art methods (Symmetric Normalization and VoxelMorph) were implemented as a basis of comparison, and variations in the proposed dual-channel network were investigated, including single-channel registration, fusion without uncertainty weighting, and conventional sequential training of the synthesis and registration subnetworks. The proposed method achieved: (1) Dice coefficient=0.82±0.07 and TRE=1.2±0.6mm on paired MR/CT with simulated deformations; (2) Dice coefficient=0.83±0.07 and TRE=1.4±0.7mm on paired MR/CT with real deformations; and (3) Dice=0.79±0.13 and TRE=1.6±1.0mm on the neurosurgery dataset with real deformations. The dual-channel registration with uncertainty weighting demonstrated superior performance (e.g., TRE=1.2±0.6mm) compared to single-channel registration (TRE=1.6±1.0mm, p<0.05 for CT channel and TRE=1.3±0.7mm for MR channel) and dual-channel registration without uncertainty weighting (TRE=1.4±0.8mm, p<0.05). End-to-end training of the synthesis and registration subnetworks also improved performance compared to the conventional sequential training strategy (TRE=1.3±0.6mm). Registration runtime with the proposed network was ∼3s. The deformable registration framework based on dual-channel MR/CT registration with spatially varying weights and end-to-end training achieved geometric accuracy and runtime that was superior to state-of-the-art baseline methods and various ablations of the proposed network. The accuracy and runtime of the method may be compatible with the requirements of high-precision neurosurgery.

CT-Based Pelvic T1-Weighted MR Image Synthesis Using UNet, UNet++ and Cycle-Consistent Generative Adversarial Network (Cycle-GAN).

BackgroundComputed tomography (CT) and magnetic resonance imaging (MRI) are the mainstay imaging modalities in radiotherapy planning. In MR-Linac treatment, manual annotation of organs-at-risk (OARs) and clinical volumes requires a significant clinician interaction and is a major challenge. Currently, there is a lack of available pre-annotated MRI data for training supervised segmentation algorithms. This study aimed to develop a deep learning (DL)-based framework to synthesize pelvic T1-weighted MRI from a pre-existing repository of clinical planning CTs.MethodsMRI synthesis was performed using UNet++ and cycle-consistent generative adversarial network (Cycle-GAN), and the predictions were compared qualitatively and quantitatively against a baseline UNet model using pixel-wise and perceptual loss functions. Additionally, the Cycle-GAN predictions were evaluated through qualitative expert testing (4 radiologists), and a pelvic bone segmentation routine based on a UNet architecture was trained on synthetic MRI using CT-propagated contours and subsequently tested on real pelvic T1 weighted MRI scans.ResultsIn our experiments, Cycle-GAN generated sharp images for all pelvic slices whilst UNet and UNet++ predictions suffered from poorer spatial resolution within deformable soft-tissues (e.g. bladder, bowel). Qualitative radiologist assessment showed inter-expert variabilities in the test scores; each of the four radiologists correctly identified images as acquired/synthetic with 67%, 100%, 86% and 94% accuracy. Unsupervised segmentation of pelvic bone on T1-weighted images was successful in a number of test casesConclusionPelvic MRI synthesis is a challenging task due to the absence of soft-tissue contrast on CT. Our study showed the potential of deep learning models for synthesizing realistic MR images from CT, and transferring cross-domain knowledge which may help to expand training datasets for 21 development of MR-only segmentation models.

Multi-Modality MR Image Synthesis via Confidence-Guided Aggregation and Cross-Modality Refinement.

Magnetic resonance imaging (MRI) can provide multi-modality MR images by setting task-specific scan parameters, and has been widely used in various disease diagnosis and planned treatments. However, in practical clinical applications, it is often difficult to obtain multi-modality MR images simultaneously due to patient discomfort, and scanning costs, etc. Therefore, how to effectively utilize the existing modality images to synthesize missing modality image has become a hot research topic. In this paper, we propose a novel confidence-guided aggregation and cross-modality refinement network (CACR-Net) for multi-modality MR image synthesis, which effectively utilizes complementary and correlative information of multiple modalities to synthesize high-quality target-modality images. Specifically, to effectively utilize the complementary modality-specific characteristics, a confidence-guided aggregation module is proposed to adaptively aggregate the multiple target-modality images generated from multiple source-modality images by using the corresponding confidence maps. Based on the aggregated target-modality image, a cross-modality refinement module is presented to further refine the target-modality image by mining correlative information among the multiple source-modality images and aggregated target-modality image. By training the proposed CACR-Net in an end-to-end manner, high-quality and sharp target-modality MR images are effectively synthesized. Experimental results on the widely used benchmark demonstrate that the proposed method outperforms state-of-the-art methods.

DUAL-CYCLE CONSTRAINED BIJECTIVE VAE-GAN FOR TAGGED-TO-CINE MAGNETIC RESONANCE IMAGE SYNTHESIS.

Tagged magnetic resonance imaging (MRI) is a widely used imaging technique for measuring tissue deformation in moving organs. Due to tagged MRI's intrinsic low anatomical resolution, another matching set of cine MRI with higher resolution is sometimes acquired in the same scanning session to facilitate tissue segmentation, thus adding extra time and cost. To mitigate this, in this work, we propose a novel dual-cycle constrained bijective VAE-GAN approach to carry out tagged-to-cine MR image synthesis. Our method is based on a variational autoencoder backbone with cycle reconstruction constrained adversarial training to yield accurate and realistic cine MR images given tagged MR images. Our framework has been trained, validated, and tested using 1,768, 416, and 1,560 subject-independent paired slices of tagged and cine MRI from twenty healthy subjects, respectively, demonstrating superior performance over the comparison methods. Our method can potentially be used to reduce the extra acquisition time and cost, while maintaining the same workflow for further motion analyses.

MustGAN: multi-stream Generative Adversarial Networks for MR Image Synthesis.

Multi-contrast MRI protocols increase the level of morphological information available for diagnosis. Yet, the number and quality of contrasts are limited in practice by various factors including scan time and patient motion. Synthesis of missing or corrupted contrasts from other high-quality ones can alleviate this limitation. When a single target contrast is of interest, common approaches for multi-contrast MRI involve either one-to-one or many-to-one synthesis methods depending on their input. One-to-one methods take as input a single source contrast, and they learn a latent representation sensitive to unique features of the source. Meanwhile, many-to-one methods receive multiple distinct sources, and they learn a shared latent representation more sensitive to common features across sources. For enhanced image synthesis, we propose a multi-stream approach that aggregates information across multiple source images via a mixture of multiple one-to-one streams and a joint many-to-one stream. The complementary feature maps generated in the one-to-one streams and the shared feature maps generated in the many-to-one stream are combined with a fusion block. The location of the fusion block is adaptively modified to maximize task-specific performance. Quantitative and radiological assessments on T1,- T2-, PD-weighted, and FLAIR images clearly demonstrate the superior performance of the proposed method compared to previous state-of-the-art one-to-one and many-to-one methods.

Anatomic and Molecular MR Image Synthesis Using Confidence Guided CNNs.

Data-driven automatic approaches have demonstrated their great potential in resolving various clinical diagnostic dilemmas in neuro-oncology, especially with the help of standard anatomic and advanced molecular MR images. However, data quantity and quality remain a key determinant, and a significant limit of the potential applications. In our previous work, we explored the synthesis of anatomic and molecular MR image networks (SAMR) in patients with post-treatment malignant gliomas. In this work, we extend this through a confidence-guided SAMR (CG-SAMR) that synthesizes data from lesion contour information to multi-modal MR images, including T1-weighted ( [Formula: see text]), gadolinium enhanced [Formula: see text] (Gd- [Formula: see text]), T2-weighted ( [Formula: see text]), and fluid-attenuated inversion recovery ( FLAIR ), as well as the molecular amide proton transfer-weighted ( [Formula: see text]) sequence. We introduce a module that guides the synthesis based on a confidence measure of the intermediate results. Furthermore, we extend the proposed architecture to allow training using unpaired data. Extensive experiments on real clinical data demonstrate that the proposed model can perform better than current the state-of-the-art synthesis methods. Our code is available at https://github.com/guopengf/CG-SAMR.

Multimodal MRI synthesis using unified generative adversarial networks.

Complementary information obtained from multiple contrasts of tissue facilitates physicians assessing, diagnosing and planning treatment of a variety of diseases. However, acquiring multiple contrasts magnetic resonance images (MRI) for every patient using multiple pulse sequences is time-consuming and expensive, where, medical image synthesis has been demonstrated as an effective alternative. The purpose of this study is to develop a unified framework for multimodal MR image synthesis. A unified generative adversarial network consisting of only a single generator and a single discriminator was developed to learn the mappings among images of four different modalities. The generator took an image and its modality label as inputs and learned to synthesize the image in the target modality, while the discriminator was trained to distinguish between real and synthesized images and classify them to their corresponding modalities. The network was trained and tested using multimodal brain MRI consisting of four different contrasts which are T1-weighted (T1), T1-weighted and contrast-enhanced (T1c), T2-weighted (T2), and fluid-attenuated inversion recovery (Flair). Quantitative assessments of our proposed method were made through computing normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), structural similarity index measurement (SSIM), visual information fidelity (VIF), and naturalness image quality evaluator (NIQE). The proposed model was trained and tested on a cohort of 274 glioma patients with well-aligned multi-types of MRI scans. After the model was trained, tests were conducted by using each of T1, T1c, T2, Flair as a single input modality to generate its respective rest modalities. Our proposed method shows high accuracy and robustness for image synthesis with arbitrary MRI modality that is available in the database as input. For example, with T1 as input modality, the NMAEs for the generated T1c, T2, Flair respectively are 0.034±0.005, 0.041±0.006, and 0.041±0.006, the PSNRs respectively are 32.353±2.525dB, 30.016±2.577dB, and 29.091±2.795dB, the SSIMs are 0.974±0.059, 0.969±0.059, and 0.959±0.059, the VIF are 0.750±0.087, 0.706±0.097, and 0.654±0.062, and NIQE are 1.396±0.401, 1.511±0.460, and 1.259±0.358, respectively. We proposed a novel multimodal MR image synthesis method based on a unified generative adversarial network. The network takes an image and its modality label as inputs and synthesizes multimodal images in a single forward pass. The results demonstrate that the proposed method is able to accurately synthesize multimodal MR images from a single MR image.

Multimodal MR Image Synthesis Using Gradient Prior and Adversarial Learning

In magnetic resonance imaging (MRI), several images can be obtained using different imaging settings (e.g. T1, T2, DWI, and Flair). These images have similar anatomical structures but are with different contrasts, which provide a wealth of information for diagnosis. However, the images under specific imaging settings may not be available due to the limitation of scanning time or corruption caused by noises. It is attractive to derive missing images with some settings from the available MR images. In this paper, we propose a novel end-to-end multisetting MR image synthesis method. The proposed method is based on generative adversarial networks (GANs) - a deep learning model. In the proposed method, different MR images obtained by different settings are used as the inputs of a GANs and each image is encoded by an encoder. Each encoder includes a refinement structure which is used to extract a multiscale feature map from an input image. The multiscale feature maps from different input images are then fused to generate several desired target images under specific settings. Because the resultant images obtained with GANs have blurred edges, we fuse gradient prior information in the model to protect high frequency information such as important tissue textures of medical images. In the proposed model, the multiscale information is also adopted in the adversarial learning (not just in the generator or discriminator) so that we can produce high quality synthesized images. We evaluated the proposed method on two public datasets: BRATS and ISLES. Experimental results demonstrate that the proposed approach is superior to current state-of-the-art methods.