Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks

Semi-Supervised Learning of MRI Synthesis Without Fully-Sampled Ground Truths

Learning-based translation between MRI contrasts involves supervised deep models trained using high-quality source- and target-contrast images derived from fully-sampled acquisitions, which might be difficult to collect under limitations on scan costs or time. To facilitate curation of training sets, here we introduce the first semi-supervised model for MRI contrast translation (ssGAN) that can be trained directly using undersampled k-space data. To enable semi-supervised learning on undersampled data, ssGAN introduces novel multi-coil losses in image, k-space, and adversarial domains. The multi-coil losses are selectively enforced on acquired k-space samples unlike traditional losses in single-coil synthesis models. Comprehensive experiments on retrospectively undersampled multi-contrast brain MRI datasets are provided. Our results demonstrate that ssGAN yields on par performance to a supervised model, while outperforming single-coil models trained on coil-combined magnitude images. It also outperforms cascaded reconstruction-synthesis models where a supervised synthesis model is trained following self-supervised reconstruction of undersampled data. Thus, ssGAN holds great promise to improve the feasibility of learning-based multi-contrast MRI synthesis.

Shifting machine learning for healthcare from development to deployment and from models to data

In the past decade, the application of machine learning (ML) to healthcare has helped drive the automation of physician tasks as well as enhancements in clinical capabilities and access to care. This progress has emphasized that, from model development to model deployment, data play central roles. In this Review, we provide a data-centric view of the innovations and challenges that are defining ML for healthcare. We discuss deep generative models and federated learning as strategies to augment datasets for improved model performance, as well as the use of the more recent transformer models for handling larger datasets and enhancing the modelling of clinical text. We also discuss data-focused problems in the deployment of ML, emphasizing the need to efficiently deliver data to ML models for timely clinical predictions and to account for natural data shifts that can deteriorate model performance.

Adversarial counterfactual augmentation: application in Alzheimer's disease classification

Due to the limited availability of medical data, deep learning approaches for medical image analysis tend to generalise poorly to unseen data. Augmenting data during training with random transformations has been shown to help and became a ubiquitous technique for training neural networks. Here, we propose a novel adversarial counterfactual augmentation scheme that aims at finding the most effective synthesised images to improve downstream tasks, given a pre-trained generative model. Specifically, we construct an adversarial game where we update the input conditional factor of the generator and the downstream classifier with gradient backpropagation alternatively and iteratively. This can be viewed as finding the 'weakness' of the classifier and purposely forcing it to overcome its weakness via the generative model. To demonstrate the effectiveness of the proposed approach, we validate the method with the classification of Alzheimer's Disease (AD) as a downstream task. The pre-trained generative model synthesises brain images using age as conditional factor. Extensive experiments and ablation studies have been performed to show that the proposed approach improves classification performance and has potential to alleviate spurious correlations and catastrophic forgetting. Code: https://github.com/xiat0616/adversarial_counterfactual_augmentation.

A Systematic Literature Review on Applications of GAN-Synthesized Images for Brain MRI

With the advances in brain imaging, magnetic resonance imaging (MRI) is evolving as a popular radiological tool in clinical diagnosis. Deep learning (DL) methods can detect abnormalities in brain images without an extensive manual feature extraction process. Generative adversarial network (GAN)-synthesized images have many applications in this field besides augmentation, such as image translation, registration, super-resolution, denoising, motion correction, segmentation, reconstruction, and contrast enhancement. The existing literature was reviewed systematically to understand the role of GAN-synthesized dummy images in brain disease diagnosis. Web of Science and Scopus databases were extensively searched to find relevant studies from the last 6 years to write this systematic literature review (SLR). Predefined inclusion and exclusion criteria helped in filtering the search results. Data extraction is based on related research questions (RQ). This SLR identifies various loss functions used in the above applications and software to process brain MRIs. A comparative study of existing evaluation metrics for GAN-synthesized images helps choose the proper metric for an application. GAN-synthesized images will have a crucial role in the clinical sector in the coming years, and this paper gives a baseline for other researchers in the field.

TCGAN: a transformer-enhanced GAN for PET synthetic CT

Multimodal medical images can be used in a multifaceted approach to resolve a wide range of medical diagnostic problems. However, these images are generally difficult to obtain due to various limitations, such as cost of capture and patient safety. Medical image synthesis is used in various tasks to obtain better results. Recently, various studies have attempted to use generative adversarial networks for missing modality image synthesis, making good progress. In this study, we propose a generator based on a combination of transformer network and a convolutional neural network (CNN). The proposed method can combine the advantages of transformers and CNNs to promote a better detail effect. The network is designed for positron emission tomography (PET) to computer tomography synthesis, which can be used for PET attenuation correction. We also experimented on two datasets for magnetic resonance T1- to T2-weighted image synthesis. Based on qualitative and quantitative analyses, our proposed method outperforms the existing methods.

Synthetic Time of Flight Magnetic Resonance Angiography Generation Model Based on Cycle-Consistent Generative Adversarial Network Using PETRA-MRA in the Patients With Treated Intracranial Aneurysm

BACKGROUND

Pointwise encoding time reduction with radial acquisition (PETRA) magnetic resonance angiography (MRA) is useful for evaluating intracranial aneurysm recurrence, but the problem of severe background noise and low peripheral signal-to-noise ratio (SNR) remain. Deep learning could reduce noise using high- and low-quality images.

PURPOSE

To develop a cycle-consistent generative adversarial network (cycleGAN)-based deep learning model to generate synthetic TOF (synTOF) using PETRA.

STUDY TYPE

Retrospective.

POPULATION

A total of 377 patients (mean age: 60 ± 11; 293 females) with treated intracranial aneurysms who underwent both PETRA and TOF from October 2017 to January 2021. Data were randomly divided into training (49.9%, 188/377) and validation (50.1%, 189/377) groups.

FIELD STRENGTH/SEQUENCE

Ultra-short echo time and TOF-MRA on a 3-T MR system.

ASSESSMENT

For the cycleGAN model, the peak SNR (PSNR) and structural similarity (SSIM) were evaluated. Image quality was compared qualitatively (5-point Likert scale) and quantitatively (SNR). A multireader diagnostic optimality evaluation was performed with 17 radiologists (experience of 1-18 years).

STATISTICAL TESTS

Generalized estimating equation analysis, Friedman's test, McNemar test, and Spearman's rank correlation. P < 0.05 indicated statistical significance.

RESULTS

The PSNR and SSIM between synTOF and TOF were 17.51 [16.76; 18.31] dB and 0.71 ± 0.02. The median values of overall image quality, noise, sharpness, and vascular conspicuity were significantly higher for synTOF than for PETRA (4.00 [4.00; 5.00] vs. 4.00 [3.00; 4.00]; 5.00 [4.00; 5.00] vs. 3.00 [2.00; 4.00]; 4.00 [4.00; 4.00] vs. 4.00 [3.00; 4.00]; 3.00 [3.00; 4.00] vs. 3.00 [2.00; 3.00]). The SNRs of the middle cerebral arteries were the highest for synTOF (synTOF vs. TOF vs. PETRA; 63.67 [43.25; 105.00] vs. 52.42 [32.88; 74.67] vs. 21.05 [12.34; 37.88]). In the multireader evaluation, there was no significant difference in diagnostic optimality or preference between synTOF and TOF (19.00 [18.00; 19.00] vs. 20.00 [18.00; 20.00], P = 0.510; 8.00 [6.00; 11.00] vs. 11.00 [9.00, 14.00], P = 1.000).

DATA CONCLUSION

The cycleGAN-based deep learning model provided synTOF free from background artifact. The synTOF could be a versatile alternative to TOF in patients who have undergone PETRA for evaluating treated aneurysms.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 1.

Medical image translation using an edge-guided generative adversarial network with global-to-local feature fusion

In this paper, we propose a framework based deep learning for medical image translation using paired and unpaired training data. Initially, a deep neural network with an encoder-decoder structure is proposed for image-to-image translation using paired training data. A multi-scale context aggregation approach is then used to extract various features from different levels of encoding, which are used during the corresponding network decoding stage. At this point, we further propose an edge-guided generative adversarial network for image-to-image translation based on unpaired training data. An edge constraint loss function is used to improve network performance in tissue boundaries. To analyze framework performance, we conducted five different medical image translation tasks. The assessment demonstrates that the proposed deep learning framework brings significant improvement beyond state-of-the-arts.

ResViT: Residual Vision Transformers for Multimodal Medical Image Synthesis

Generative adversarial models with convolutional neural network (CNN) backbones have recently been established as state-of-the-art in numerous medical image synthesis tasks. However, CNNs are designed to perform local processing with compact filters, and this inductive bias compromises learning of contextual features. Here, we propose a novel generative adversarial approach for medical image synthesis, ResViT, that leverages the contextual sensitivity of vision transformers along with the precision of convolution operators and realism of adversarial learning. ResViT's generator employs a central bottleneck comprising novel aggregated residual transformer (ART) blocks that synergistically combine residual convolutional and transformer modules. Residual connections in ART blocks promote diversity in captured representations, while a channel compression module distills task-relevant information. A weight sharing strategy is introduced among ART blocks to mitigate computational burden. A unified implementation is introduced to avoid the need to rebuild separate synthesis models for varying source-target modality configurations. Comprehensive demonstrations are performed for synthesizing missing sequences in multi-contrast MRI, and CT images from MRI. Our results indicate superiority of ResViT against competing CNN- and transformer-based methods in terms of qualitative observations and quantitative metrics.

PTNet3D: A 3D High-Resolution Longitudinal Infant Brain MRI Synthesizer Based on Transformers

An increased interest in longitudinal neurodevelopment during the first few years after birth has emerged in recent years. Noninvasive magnetic resonance imaging (MRI) can provide crucial information about the development of brain structures in the early months of life. Despite the success of MRI collections and analysis for adults, it remains a challenge for researchers to collect high-quality multimodal MRIs from developing infant brains because of their irregular sleep pattern, limited attention, inability to follow instructions to stay still during scanning. In addition, there are limited analytic approaches available. These challenges often lead to a significant reduction of usable MRI scans and pose a problem for modeling neurodevelopmental trajectories. Researchers have explored solving this problem by synthesizing realistic MRIs to replace corrupted ones. Among synthesis methods, the convolutional neural network-based (CNN-based) generative adversarial networks (GANs) have demonstrated promising performance. In this study, we introduced a novel 3D MRI synthesis framework- pyramid transformer network (PTNet3D)- which relies on attention mechanisms through transformer and performer layers. We conducted extensive experiments on high-resolution Developing Human Connectome Project (dHCP) and longitudinal Baby Connectome Project (BCP) datasets. Compared with CNN-based GANs, PTNet3D consistently shows superior synthesis accuracy and superior generalization on two independent, large-scale infant brain MRI datasets. Notably, we demonstrate that PTNet3D synthesized more realistic scans than CNN-based models when the input is from multi-age subjects. Potential applications of PTNet3D include synthesizing corrupted or missing images. By replacing corrupted scans with synthesized ones, we observed significant improvement in infant whole brain segmentation.

Manifold-aware synthesis of high-resolution diffusion from structural imaging

The physical and clinical constraints surrounding diffusion-weighted imaging (DWI) often limit the spatial resolution of the produced images to voxels up to eight times larger than those of T1w images. The detailed information contained in accessible high-resolution T1w images could help in the synthesis of diffusion images with a greater level of detail. However, the non-Euclidean nature of diffusion imaging hinders current deep generative models from synthesizing physically plausible images. In this work, we propose the first Riemannian network architecture for the direct generation of diffusion tensors (DT) and diffusion orientation distribution functions (dODFs) from high-resolution T1w images. Our integration of the log-Euclidean Metric into a learning objective guarantees, unlike standard Euclidean networks, the mathematically-valid synthesis of diffusion. Furthermore, our approach improves the fractional anisotropy mean squared error (FA MSE) between the synthesized diffusion and the ground-truth by more than 23% and the cosine similarity between principal directions by almost 5% when compared to our baselines. We validate our generated diffusion by comparing the resulting tractograms to our expected real data. We observe similar fiber bundles with streamlines having <3% difference in length, <1% difference in volume, and a visually close shape. While our method is able to generate diffusion images from structural inputs in a high-resolution space within 15 s, we acknowledge and discuss the limits of diffusion inference solely relying on T1w images. Our results nonetheless suggest a relationship between the high-level geometry of the brain and its overall white matter architecture that remains to be explored.

Virtual contrast enhancement for CT scans of abdomen and pelvis

Contrast agents are commonly used to highlight blood vessels, organs, and other structures in magnetic resonance imaging (MRI) and computed tomography (CT) scans. However, these agents may cause allergic reactions or nephrotoxicity, limiting their use in patients with kidney dysfunctions. In this paper, we propose a generative adversarial network (GAN) based framework to automatically synthesize contrast-enhanced CTs directly from the non-contrast CTs in the abdomen and pelvis region. The respiratory and peristaltic motion can affect the pixel-level mapping of contrast-enhanced learning, which makes this task more challenging than other body parts. A perceptual loss is introduced to compare high-level semantic differences of the enhancement areas between the virtual contrast-enhanced and actual contrast-enhanced CT images. Furthermore, to accurately synthesize the intensity details as well as remain texture structures of CT images, a dual-path training schema is proposed to learn the texture and structure features simultaneously. Experiment results on three contrast phases (i.e. arterial, portal, and delayed phase) show the potential to synthesize virtual contrast-enhanced CTs directly from non-contrast CTs of the abdomen and pelvis for clinical evaluation.

A bidirectional multilayer contrastive adaptation network with anatomical structure preservation for unpaired cross-modality medical image segmentation

Multi-modal medical image segmentation has achieved great success through supervised deep learning networks. However, because of domain shift and limited annotation information, unpaired cross-modality segmentation tasks are still challenging. The unsupervised domain adaptation (UDA) methods can alleviate the segmentation degradation of cross-modality segmentation by knowledge transfer between different domains, but current methods still suffer from the problems of model collapse, adversarial training instability, and mismatch of anatomical structures. To tackle these issues, we propose a bidirectional multilayer contrastive adaptation network (BMCAN) for unpaired cross-modality segmentation. The shared encoder is first adopted for learning modality-invariant encoding representations in image synthesis and segmentation simultaneously. Secondly, to retain the anatomical structure consistency in cross-modality image synthesis, we present a structure-constrained cross-modality image translation approach for image alignment. Thirdly, we construct a bidirectional multilayer contrastive learning approach to preserve the anatomical structures and enhance encoding representations, which utilizes two groups of domain-specific multilayer perceptron (MLP) networks to learn modality-specific features. Finally, a semantic information adversarial learning approach is designed to learn structural similarities of semantic outputs for output space alignment. Our proposed method was tested on three different cross-modality segmentation tasks: brain tissue, brain tumor, and cardiac substructure segmentation. Compared with other UDA methods, experimental results show that our proposed BMCAN achieves state-of-the-art segmentation performance on the above three tasks, and it has fewer training components and better feature representations for overcoming overfitting and domain shift problems. Our proposed method can efficiently reduce the annotation burden of radiologists in cross-modality image analysis.

Swin transformer-based GAN for multi-modal medical image translation

Medical image-to-image translation is considered a new direction with many potential applications in the medical field. The medical image-to-image translation is dominated by two models, including supervised Pix2Pix and unsupervised cyclic-consistency generative adversarial network (GAN). However, existing methods still have two shortcomings: 1) the Pix2Pix requires paired and pixel-aligned images, which are difficult to acquire. Nevertheless, the optimum output of the cycle-consistency model may not be unique. 2) They are still deficient in capturing the global features and modeling long-distance interactions, which are critical for regions with complex anatomical structures. We propose a Swin Transformer-based GAN for Multi-Modal Medical Image Translation, named MMTrans. Specifically, MMTrans consists of a generator, a registration network, and a discriminator. The Swin Transformer-based generator enables to generate images with the same content as source modality images and similar style information of target modality images. The encoder part of the registration network, based on Swin Transformer, is utilized to predict deformable vector fields. The convolution-based discriminator determines whether the target modality images are similar to the generator or from the real images. Extensive experiments conducted using the public dataset and clinical datasets showed that our network outperformed other advanced medical image translation methods in both aligned and unpaired datasets and has great potential to be applied in clinical applications.

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).

Convolutional Neural Network Based Frameworks for Fast Automatic Segmentation of Thalamic Nuclei from Native and Synthesized Contrast Structural MRI

Thalamic nuclei have been implicated in several neurological diseases. Thalamic nuclei parcellation from structural MRI is challenging due to poor intra-thalamic nuclear contrast while methods based on diffusion and functional MRI are affected by limited spatial resolution and image distortion. Existing multi-atlas based techniques are often computationally intensive and time-consuming. In this work, we propose a 3D convolutional neural network (CNN) based framework for thalamic nuclei parcellation using T1-weighted Magnetization Prepared Rapid Gradient Echo (MPRAGE) images. Transformation of images to an efficient representation has been proposed to improve the performance of subsequent classification tasks especially when working with limited labeled data. We investigate this by transforming the MPRAGE images to White-Matter-nulled MPRAGE (WMn-MPRAGE) contrast, previously shown to exhibit good intra-thalamic nuclear contrast, prior to the segmentation step. We trained two 3D segmentation frameworks using MPRAGE images (n = 35 subjects): (a) a native contrast segmentation (NCS) on MPRAGE images and (b) a synthesized contrast segmentation (SCS) where synthesized WMn-MPRAGE representation generated by a contrast synthesis CNN were used. Thalamic nuclei labels were generated using THOMAS, a multi-atlas segmentation technique proposed for WMn-MPRAGE images. The segmentation accuracy and clinical utility were evaluated on a healthy cohort (n = 12) and a cohort (n = 45) comprising of healthy subjects and patients with alcohol use disorder (AUD), respectively. Both the segmentation CNNs yielded comparable performances on most thalamic nuclei with Dice scores greater than 0.84 for larger nuclei and at least 0.7 for smaller nuclei. However, for some nuclei, the SCS CNN yielded significant improvements in Dice scores (medial geniculate nucleus, P = 0.003, centromedian nucleus, P = 0.01) and percent volume difference (ventral anterior, P = 0.001, ventral posterior lateral, P = 0.01) over NCS. In the AUD cohort, the SCS CNN demonstrated a significant atrophy in ventral lateral posterior nucleus in AUD patients compared to healthy age-matched controls (P = 0.01), agreeing with previous studies on thalamic atrophy in alcoholism, whereas the NCS CNN showed spurious atrophy of the ventral posterior lateral nucleus. CNN-based segmentation of thalamic nuclei provides a fast and automated technique for thalamic nuclei prediction in MPRAGE images. The transformation of images to an efficient representation, such as WMn-MPRAGE, can provide further improvements in segmentation performance.

Data-driven myelin water imaging based on T1 and T2 relaxometry

Long acquisition times preclude the application of multiecho spin echo (MESE) sequences for myelin water fraction (MWF) mapping in daily clinical practice. In search of alternative methods, previous studies of interest explored the biophysical modeling of MWF from measurements of different tissue properties that can be obtained in scan times shorter than those required for the MESE. In this work, a novel data-driven estimation of MWF maps from fast relaxometry measurements is proposed and investigated. T₁ and T₂ relaxometry maps were acquired in a cohort of 20 healthy subjects along with a conventional MESE sequence. Whole-brain quantitative mapping was achieved with a fast protocol in 6 min 24 s. Reference MWF maps were derived from the MESE sequence (TA = 11 min 17 s) and their data-driven estimation from relaxometry measurements was investigated using three different modeling strategies: two general linear models (GLMs) with linear and quadratic regressors, respectively; a random forest regression model; and two deep neural network architectures, a U-Net and a conditional generative adversarial network (cGAN). Models were validated using a 10-fold crossvalidation. The resulting maps were visually and quantitatively compared by computing the root mean squared error (RMSE) between the estimated and reference MWF maps, the intraclass correlation coefficients (ICCs) between corresponding MWF values in different brain regions, and by performing Bland-Altman analysis. Qualitatively, the estimated maps appear to generally provide a similar, yet more blurred MWF contrast in comparison with the reference, with the cGAN model best capturing MWF variabilities in small structures. By estimating the average adjusted coefficient of determination of the GLM with quadratic regressors, we showed that 87% of the variability in the MWF values can be explained by relaxation times alone. Further quantitative analysis showed an average RMSE smaller than 0.1% for all methods. The ICC was greater than 0.81 for all methods, and the bias smaller than 2.19%. It was concluded that this work confirms the notion that relaxometry parameters contain a large part of the information on myelin water and that MWF maps can be generated from T₁ /T₂ data with minimal error. Among the investigated modeling approaches, the cGAN provided maps with the best trade-off between accuracy and blurriness. Fast relaxometry, like the 6 min 24 s whole-brain protocol used in this work in conjunction with machine learning, may thus have the potential to replace time-consuming MESE acquisitions.

Transformer-Based T2-weighted MRI Synthesis from T1-weighted Images

Multi-modality magnetic resonance (MR) images provide complementary information for disease diagnoses. However, modality missing is quite usual in real-life clinical practice. Current methods usually employ convolution-based generative adversarial network (GAN) or its variants to synthesize the missing modality. With the development of vision transformer, we explore its application in the MRI modality synthesis task in this work. We propose a novel supervised deep learning method for synthesizing a missing modality, making use of a transformer-based encoder. Specifically, a model is trained for translating 2D MR images from T1-weighted to T2-weighted based on conditional GAN (cGAN). We replace the encoder with transformer and input adjacent slices to enrich spatial prior knowledge. Experimental results on a private dataset and a public dataset demonstrate that our proposed model outperforms state-of-the-art supervised methods for MR image synthesis, both quantitatively and qualitatively. Clinical relevance- This work proposes a method to synthesize T2-weighted images from T1-weighted ones to address the modality missing issue in MRI.

FDG-PET to T1 Weighted MRI Translation with 3D Elicit Generative Adversarial Network (E-GAN)

Objective: With the strengths of deep learning, computer-aided diagnosis (CAD) is a hot topic for researchers in medical image analysis. One of the main requirements for training a deep learning model is providing enough data for the network. However, in medical images, due to the difficulties of data collection and data privacy, finding an appropriate dataset (balanced, enough samples, etc.) is quite a challenge. Although image synthesis could be beneficial to overcome this issue, synthesizing 3D images is a hard task. The main objective of this paper is to generate 3D T1 weighted MRI corresponding to FDG-PET. In this study, we propose a separable convolution-based Elicit generative adversarial network (E-GAN). The proposed architecture can reconstruct 3D T1 weighted MRI from 2D high-level features and geometrical information retrieved from a Sobel filter. Experimental results on the ADNI datasets for healthy subjects show that the proposed model improves the quality of images compared with the state of the art. In addition, the evaluation of E-GAN and the state of art methods gives a better result on the structural information (13.73% improvement for PSNR and 22.95% for SSIM compared to Pix2Pix GAN) and textural information (6.9% improvements for homogeneity error in Haralick features compared to Pix2Pix GAN).

Synthesizing pseudo-T2w images to recapture missing data in neonatal neuroimaging with applications in rs-fMRI

T1- and T2-weighted (T1w and T2w) images are essential for tissue classification and anatomical localization in Magnetic Resonance Imaging (MRI) analyses. However, these anatomical data can be challenging to acquire in non-sedated neonatal cohorts, which are prone to high amplitude movement and display lower tissue contrast than adults. As a result, one of these modalities may be missing or of such poor quality that they cannot be used for accurate image processing, resulting in subject loss. While recent literature attempts to overcome these issues in adult populations using synthetic imaging approaches, evaluation of the efficacy of these methods in pediatric populations and the impact of these techniques in conventional MR analyses has not been performed. In this work, we present two novel methods to generate pseudo-T2w images: the first is based in deep learning and expands upon previous models to 3D imaging without the requirement of paired data, the second is based in nonlinear multi-atlas registration providing a computationally lightweight alternative. We demonstrate the anatomical accuracy of pseudo-T2w images and their efficacy in existing MR processing pipelines in two independent neonatal cohorts. Critically, we show that implementing these pseudo-T2w methods in resting-state functional MRI analyses produces virtually identical functional connectivity results when compared to those resulting from T2w images, confirming their utility in infant MRI studies for salvaging otherwise lost subject data.

GAN for synthesizing CT from T2-weighted MRI data towards MR-guided radiation treatment

OBJECTIVE

In medical domain, cross-modality image synthesis suffers from multiple issues , such as context-misalignment, image distortion, image blurriness, and loss of details. The fundamental objective behind this study is to address these issues in estimating synthetic Computed tomography (sCT) scans from T2-weighted Magnetic Resonance Imaging (MRI) scans to achieve MRI-guided Radiation Treatment (RT).

MATERIALS AND METHODS

We proposed a conditional generative adversarial network (cGAN) with multiple residual blocks to estimate sCT from T2-weighted MRI scans using 367 paired brain MR-CT images dataset. Few state-of-the-art deep learning models were implemented to generate sCT including Pix2Pix model, U-Net model, autoencoder model and their results were compared, respectively.

RESULTS

Results with paired MR-CT image dataset demonstrate that the proposed model with nine residual blocks in generator architecture results in the smallest mean absolute error (MAE) value of [Formula: see text], and mean squared error (MSE) value of [Formula: see text], and produces the largest Pearson correlation coefficient (PCC) value of [Formula: see text], SSIM value of [Formula: see text] and peak signal-to-noise ratio (PSNR) value of [Formula: see text], respectively. We qualitatively evaluated our result by visual comparisons of generated sCT to original CT of respective MRI input.

DISCUSSION

The quantitative and qualitative comparison of this work demonstrates that deep learning-based cGAN model can be used to estimate sCT scan from a reference T2 weighted MRI scan. The overall accuracy of our proposed model outperforms different state-of-the-art deep learning-based models.

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

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.

Brain tumor image generation using an aggregation of GAN models with style transfer

In the recent past, deep learning-based models have achieved tremendous success in computer vision-related tasks with the help of large-scale annotated datasets. An interesting application of deep learning is synthetic data generation, especially in the domain of medical image analysis. The need for such a task arises due to the scarcity of original data. Class imbalance is another reason for applying data augmentation techniques. Generative Adversarial Networks (GANs) are beneficial for synthetic image generation in various fields. However, stand-alone GANs may only fetch the localized features in the latent representation of an image, whereas combining different GANs might understand the distributed features. To this end, we have proposed AGGrGAN, an aggregation of three base GAN models-two variants of Deep Convolutional Generative Adversarial Network (DCGAN) and a Wasserstein GAN (WGAN) to generate synthetic MRI scans of brain tumors. Further, we have applied the style transfer technique to enhance the image resemblance. Our proposed model efficiently overcomes the limitation of data unavailability and can understand the information variance in multiple representations of the raw images. We have conducted all the experiments on the two publicly available datasets - the brain tumor dataset and the Multimodal Brain Tumor Segmentation Challenge (BraTS) 2020 dataset. Results show that the proposed model can generate fine-quality images with maximum Structural Similarity Index Measure (SSIM) scores of 0.57 and 0.83 on the said two datasets.

Research on new treatment mode of radiotherapy based on pseudo-medical images

BACKGROUND AND OBJECTIVE

Multi-modal medical images with multiple feature information are beneficial for radiotherapy. A new radiotherapy treatment mode based on triangle generative adversarial network (TGAN) model was proposed to synthesize pseudo-medical images between multi-modal datasets.

METHODS

CBCT, MRI and CT images of 80 patients with nasopharyngeal carcinoma were selected. The TGAN model based on multi-scale discriminant network was used for data training between different image domains. The generator of the TGAN model refers to cGAN and CycleGAN, and only one generation network can establish the non-linear mapping relationship between multiple image domains. The discriminator used multi-scale discrimination network to guide the generator to synthesize pseudo-medical images that are similar to real images from both shallow and deep aspects. The accuracy of pseudo-medical images was verified in anatomy and dosimetry.

RESULTS

In the three synthetic directions, namely, CBCT → CT, CBCT → MRI, and MRI → CT, significant differences (p < 0.05) in the three-fold-cross validation results on PSNR and SSIM metrics between the pseudo-medical images obtained based on TGAN and the real images. In the testing stage, for TGAN, the MAE metric results in the three synthesis directions (CBCT → CT, CBCT → MRI, and MRI → CT) were presented as mean (standard deviation), which were 68.67 (5.83), 83.14 (8.48), and 79.96 (7.59), and the NMI metric results were 0.8643 (0.0253), 0.8051 (0.0268), and 0.8146 (0.0267) respectively. In terms of dose verification, the differences in dose distribution between the pseudo-CT obtained by TGAN and the real CT were minimal. The H values of the measurement results of dose uncertainty in PGTV, PGTVnd, PTV1, and PTV2 were 42.510, 43.121, 17.054, and 7.795, respectively (P < 0.05). The differences were statistically significant. The gamma pass rate (2%/2 mm) of pseudo-CT obtained by the new model was 94.94% (0.73%), and the numerical results were better than those of the three other comparison models.

CONCLUSIONS

The pseudo-medical images acquired based on TGAN were close to the real images in anatomy and dosimetry. The pseudo-medical images synthesized by the TGAN model have good application prospects in clinical adaptive radiotherapy.

Quality assessment of anatomical MRI images from generative adversarial networks: Human assessment and image quality metrics

BACKGROUND

Generative Adversarial Networks (GANs) can synthesize brain images from image or noise input. So far, the gold standard for assessing the quality of the generated images has been human expert ratings. However, due to limitations of human assessment in terms of cost, scalability, and the limited sensitivity of the human eye to more subtle statistical relationships, a more automated approach towards evaluating GANs is required.

NEW METHOD

We investigated to what extent visual quality can be assessed using image quality metrics and we used group analysis and spatial independent components analysis to verify that the GAN reproduces multivariate statistical relationships found in real data. Reference human data was obtained by recruiting neuroimaging experts to assess real Magnetic Resonance (MR) images and images generated by a GAN. Image quality was manipulated by exporting images at different stages of GAN training.

RESULTS

Experts were sensitive to changes in image quality as evidenced by ratings and reaction times, and the generated images reproduced group effects (age, gender) and spatial correlations moderately well. We also surveyed a number of image quality metrics. Overall, Fréchet Inception Distance (FID), Maximum Mean Discrepancy (MMD) and Naturalness Image Quality Evaluator (NIQE) showed sensitivity to image quality and good correspondence with the human data, especially for lower-quality images (i.e., images from early stages of GAN training). However, only a Deep Quality Assessment (QA) model trained on human ratings was able to reproduce the subtle differences between higher-quality images.

CONCLUSIONS

We recommend a combination of group analyses, spatial correlation analyses, and both distortion metrics (FID, MMD, NIQE) and perceptual models (Deep QA) for a comprehensive evaluation and comparison of brain images produced by GANs.

Artificial Intelligence in Neuro-Oncologic Imaging: A Brief Review for Clinical Use Cases and Future Perspectives

The artificial intelligence (AI) techniques, both deep learning end-to-end approaches and radiomics with machine learning, have been developed for various imaging-based tasks in neuro-oncology. In this brief review, use cases of AI in neuro-oncologic imaging are summarized: image quality improvement, metastasis detection, radiogenomics, and treatment response monitoring. We then give a brief overview of generative adversarial network and potential utility of synthetic images for various deep learning algorithms of imaging-based tasks and image translation tasks as becoming new data input. Lastly, we highlight the importance of cohorts and clinical trial as a true validation for clinical utility of AI in neuro-oncologic imaging.

Synthetic MR: Physical principles, clinical implementation, and new developments

Current clinical MR imaging practices rely on the qualitative assessment of images for diagnosis and treatment planning. While contrast in MR images is dependent on the spin parameters of the imaged tissue, pixel values on MR images are relative and are not scaled to represent any tissue properties. Synthetic MR is a fully featured imaging workflow consisting of efficient multiparameter mapping acquisition, synthetic image generation, and volume quantitation of brain tissues. As the application becomes more widely available on multiple vendors and scanner platforms, it has also gained widespread adoption as clinicians begin to recognize the benefits of rapid quantitation. This review will provide details about the sequence with a focus on the physical principles behind its relaxometry mechanisms. It will present an overview of the products in their current form and some potential issues when implementing it in the clinic. It will conclude by highlighting some recent advances of the technique, including a 3D mapping method and its associated applications. This article is protected by copyright. All rights reserved.

The stability of oncologic MRI radiomic features and the potential role of deep learning: a review

The use of MRI radiomic models for the diagnosis, prognosis and treatment response prediction of tumors has been increasingly reported in literature. However, its widespread adoption in clinics is hampered by issues related to features stability. In the MRI radiomic workflow, the main factors that affect radiomic features computation can be found in the image acquisition and reconstruction phase, in the image pre-processing steps, and in the segmentation of the region of interest on which radiomic indices are extracted. Deep Neural Networks (DNNs), having shown their potentiality in the medical image processing and analysis field, can be seen as an attractive strategy to partially overcome the issues related to radiomic stability and mitigate their impact. In fact, DNN approaches can be prospectively integrated in the MRI radiomic workflow to improve image quality, obtain accurate and reproducible segmentations and generate standardized images. In this review, DNN methods that can be included in the image processing steps of the radiomic workflow are described and discussed, in the light of a detailed analysis of the literature in the context of MRI radiomic reliability.

A Dual Discriminator Adversarial Learning Approach for Dental Occlusal Surface Reconstruction

Objective. Restoring the correct masticatory function of partially edentulous patient is a challenging task primarily due to the complex tooth morphology between individuals. Although some deep learning-based approaches have been proposed for dental restorations, most of them do not consider the influence of dental biological characteristics for the occlusal surface reconstruction. Description. In this article, we propose a novel dual discriminator adversarial learning network to address these challenges. In particular, this network architecture integrates two models: a dilated convolutional-based generative model and a dual global-local discriminative model. While the generative model adopts dilated convolution layers to generate a feature representation that preserves clear tissue structure, the dual discriminative model makes use of two discriminators to jointly distinguish whether the input is real or fake. While the global discriminator focuses on the missing teeth and adjacent teeth to assess whether it is coherent as a whole, the local discriminator aims only at the defective teeth to ensure the local consistency of the generated dental crown. Results. Experiments on 1000 real-world patient dental samples demonstrate the effectiveness of our method. For quantitative comparison, the image quality metrics are used to measure the similarity of the generated occlusal surface, and the root mean square between the generated result and the target crown calculated by our method is 0.114 mm. In qualitative analysis, the proposed approach can generate more reasonable dental biological morphology. Conclusion. The results demonstrate that our method significantly outperforms the state-of-the-art methods in occlusal surface reconstruction. Importantly, the designed occlusal surface has enough anatomical morphology of natural teeth and superior clinical application value.

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

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.

Multi-Contrast MRI Image Synthesis Using Switchable Cycle-Consistent Generative Adversarial Networks

Multi-contrast MRI images use different echo and repetition times to highlight different tissues. However, not all desired image contrasts may be available due to scan-time limitations, suboptimal signal-to-noise ratio, and/or image artifacts. Deep learning approaches have brought revolutionary advances in medical image synthesis, enabling the generation of unacquired image contrasts (e.g., T1-weighted MRI images) from available image contrasts (e.g., T2-weighted images). Particularly, CycleGAN is an advanced technique for image synthesis using unpaired images. However, it requires two separate image generators, demanding more training resources and computations. Recently, a switchable CycleGAN has been proposed to address this limitation and successfully implemented using CT images. However, it remains unclear if switchable CycleGAN can be applied to cross-contrast MRI synthesis. In addition, whether switchable CycleGAN is able to outperform original CycleGAN on cross-contrast MRI image synthesis is still an open question. In this paper, we developed a switchable CycleGAN model for image synthesis between multi-contrast brain MRI images using a large set of publicly accessible pediatric structural brain MRI images. We conducted extensive experiments to compare switchable CycleGAN with original CycleGAN both quantitatively and qualitatively. Experimental results demonstrate that switchable CycleGAN is able to outperform CycleGAN model on pediatric MRI brain image synthesis.

DualMMP-GAN: Dual-scale multi-modality perceptual generative adversarial network for medical image segmentation

Multi-modality magnetic resonance imaging (MRI) can reveal distinct patterns of tissue in the human body and is crucial to clinical diagnosis. But it still remains a challenge to obtain diverse and plausible multi-modality MR images due to expense, noise, and artifacts. For the same lesion, different modalities of MRI have big differences in context information, coarse location, and fine structure. In order to achieve better generation and segmentation performance, a dual-scale multi-modality perceptual generative adversarial network (DualMMP-GAN) is proposed based on cycle-consistent generative adversarial networks (CycleGAN). Dilated residual blocks are introduced to increase the receptive field, preserving structure and context information of images. A dual-scale discriminator is constructed. The generator is optimized by discriminating patches to represent lesions with different sizes. The perceptual consistency loss is introduced to learn the mapping between the generated and target modality at different semantic levels. Moreover, generative multi-modality segmentation (GMMS) combining given modalities with generated modalities is proposed for brain tumor segmentation. Experimental results show that the DualMMP-GAN outperforms the CycleGAN and some state-of-the-art methods in terms of PSNR, SSMI, and RMSE in most tasks. In addition, dice, sensitivity, specificity, and Hausdorff95 obtained from segmentation by GMMS are all higher than those from a single modality. The objective index obtained by the proposed methods are close to upper bounds obtained from real multiple modalities, indicating that GMMS can achieve similar effects as multi-modality. Overall, the proposed methods can serve as an effective method in clinical brain tumor diagnosis with promising application potential.

AI musculoskeletal clinical applications: how can AI increase my day-to-day efficiency?

Artificial intelligence (AI) is expected to bring greater efficiency in radiology by performing tasks that would otherwise require human intelligence, also at a much faster rate than human performance. In recent years, milestone deep learning models with unprecedented low error rates and high computational efficiency have shown remarkable performance for lesion detection, classification, and segmentation tasks. However, the growing field of AI has significant implications for radiology that are not limited to visual tasks. These are essential applications for optimizing imaging workflows and improving noninterpretive tasks. This article offers an overview of the recent literature on AI, focusing on the musculoskeletal imaging chain, including initial patient scheduling, optimized protocoling, magnetic resonance imaging reconstruction, image enhancement, medical image-to-image translation, and AI-aided image interpretation. The substantial developments of advanced algorithms, the emergence of massive quantities of medical data, and the interest of researchers and clinicians reveal the potential for the growing applications of AI to augment the day-to-day efficiency of musculoskeletal radiologists.

Undersampled Multi-contrast MRI Reconstruction Based on Double-domain Generative Adversarial Network

Multi-contrast magnetic resonance imaging can provide comprehensive information for clinical diagnosis. However, multi-contrast imaging suffers from long acquisition time, which makes it inhibitive for daily clinical practice. Subsampling k-space is one of the main methods to speed up scan time. Missing k-space samples will lead to inevitable serious artifacts and noise. Considering the assumption that different contrast modalities share some mutual information, it may be possible to exploit this redundancy to accelerate multi-contrast imaging acquisition. Recently, generative adversarial network shows superior performance in image reconstruction and synthesis. Some studies based on k-space reconstruction also exhibit superior performance over conventional state-of-art method. In this study, we propose a cross-domain two-stage generative adversarial network for multi-contrast images reconstruction based on prior full-sampled contrast and undersampled information. The new approach integrates reconstruction and synthesis, which estimates and completes the missing k-space and then refines in image space. It takes one fully-sampled contrast modality data and highly undersampled data from several other modalities as input, and outputs high quality images for each contrast simultaneously. The network is trained and tested on a public brain dataset from healthy subjects. Quantitative comparisons against baseline clearly indicate that the proposed method can effectively reconstruct undersampled images. Even under high acceleration, the network still can recover texture details and reduce artifacts.

Review of Machine Learning Applications Using Retinal Fundus Images

Automating screening and diagnosis in the medical field saves time and reduces the chances of misdiagnosis while saving on labor and cost for physicians. With the feasibility and development of deep learning methods, machines are now able to interpret complex features in medical data, which leads to rapid advancements in automation. Such efforts have been made in ophthalmology to analyze retinal images and build frameworks based on analysis for the identification of retinopathy and the assessment of its severity. This paper reviews recent state-of-the-art works utilizing the color fundus image taken from one of the imaging modalities used in ophthalmology. Specifically, the deep learning methods of automated screening and diagnosis for diabetic retinopathy (DR), age-related macular degeneration (AMD), and glaucoma are investigated. In addition, the machine learning techniques applied to the retinal vasculature extraction from the fundus image are covered. The challenges in developing these systems are also discussed.

Detecting brain lesions in suspected acute ischemic stroke with CT-based synthetic MRI using generative adversarial networks

Background

Difficulties in detecting brain lesions in acute ischemic stroke (AIS) have convinced researchers to use computed tomography (CT) to scan for and magnetic resonance imaging (MRI) to search for these lesions. This work aimed to develop a generative adversarial network (GAN) model for CT-to-MR image synthesis and evaluate reader performance with synthetic MRI (syn-MRI) in detecting brain lesions in suspected patients.

Methods

Patients with primarily suspected AIS were randomly assigned to the training (n=140) or testing (n=53) set. Emergency CT and follow-up MR images in the training set were used to develop a GAN model to generate syn-MR images from the CT data in the testing set. The standard reference was the manual segmentations of follow-up MR images. Image similarity was evaluated between syn-MRI and the ground truth using a 4-grade visual rating scale, the peak signal-to-noise ratio (PSNR), and the structural similarity index measure (SSIM). Reader performance with syn-MRI and CT was evaluated and compared on a per-patient (patient detection) and per-lesion (lesion detection) basis. Paired t-tests or Wilcoxon signed-rank tests were used to compare reader performance in lesion detection between the syn-MRI and CT data.

Results

Grade 2–4 brain lesions were observed on syn-MRI in 92.5% (49/53) of the patients, while the remaining syn-MRI data showed no lesions compared to the ground truth. The GAN model exhibited a weak PSNR of 24.30 dB but a favorable SSIM of 0.857. Compared with CT, syn-MRI led to an increase in the overall sensitivity from 38% (57/150) to 82% (123/150) in patient detection and from 4% (68/1,620) to 16% (262/1,620) in lesion detection (R=0.32, corrected P<0.001), but the specificity in patient detection decreased from 67% (6/9) to 33% (3/9). An additional 75% (70/93) of patients and 15% (77/517) of lesions missed on CT were detected on syn-MRI.

Conclusions

The GAN model holds potential for generating synthetic MR images from noncontrast CT data and thus could help sensitively detect individuals among patients with suspected AIS. However, the image similarity performance of the model needs to be improved, and further expert discrimination is strongly recommended.

Bidirectional Mapping Generative Adversarial Networks for Brain MR to PET Synthesis

Fusing multi-modality medical images, such as magnetic resonance (MR) imaging and positron emission tomography (PET), can provide various anatomical and functional information about the human body. However, PET data is not always available for several reasons, such as high cost, radiation hazard, and other limitations. This paper proposes a 3D end-to-end synthesis network called Bidirectional Mapping Generative Adversarial Networks (BMGAN). Image contexts and latent vectors are effectively used for brain MR-to-PET synthesis. Specifically, a bidirectional mapping mechanism is designed to embed the semantic information of PET images into the high-dimensional latent space. Moreover, the 3D Dense-UNet generator architecture and the hybrid loss functions are further constructed to improve the visual quality of cross-modality synthetic images. The most appealing part is that the proposed method can synthesize perceptually realistic PET images while preserving the diverse brain structures of different subjects. Experimental results demonstrate that the performance of the proposed method outperforms other competitive methods in terms of quantitative measures, qualitative displays, and evaluation metrics for classification.

Multi-constraint generative adversarial network for dose prediction in radiotherapy

Radiation therapy (RT) is regarded as the primary treatment for cancer in the clinic, aiming to deliver an accurate dose to the planning target volume (PTV) while protecting the surrounding organs at risk (OARs). To improve the effectiveness of the treatment planning, deep learning methods are widely adopted to predict dose distribution maps for clinical treatment planning. In this paper, we present a novel multi-constraint dose prediction model based on generative adversarial network, named Mc-GAN, to automatically predict the dose distribution map from the computer tomography (CT) images and the masks of PTV and OARs. Specifically, the generator is an embedded UNet-like structure with dilated convolution to capture both the global and local information. During the feature extraction, a dual attention module (DAM) is embedded to force the generator to take more heed of internal semantic relevance. To improve the prediction accuracy, two additional losses, i.e., the locality-constrained loss (LCL) and the self-supervised perceptual loss (SPL), are introduced besides the conventional global pixel-level loss and adversarial loss. Concretely, the LCL tries to focus on the predictions of locally important areas while the SPL aims to prevent the predicted dose maps from the possible distortion at the feature level. Evaluated on two in-house datasets, our proposed Mc-GAN has been demonstrated to outperform other state-of-the-art methods in almost all PTV and OARs criteria.