Synthesizing anonymized and labeled TOF-MRA patches for brain vessel segmentation using generative adversarial networks

A review of self-supervised, generative, and few-shot deep learning methods for data-limited magnetic resonance imaging segmentation

Magnetic resonance imaging (MRI) is a ubiquitous medical imaging technology with applications in disease diagnostics, intervention, and treatment planning. Accurate MRI segmentation is critical for diagnosing abnormalities, monitoring diseases, and deciding on a course of treatment. With the advent of advanced deep learning frameworks, fully automated and accurate MRI segmentation is advancing. Traditional supervised deep learning techniques have advanced tremendously, reaching clinical-level accuracy in the field of segmentation. However, these algorithms still require a large amount of annotated data, which is oftentimes unavailable or impractical. One way to circumvent this issue is to utilize algorithms that exploit a limited amount of labeled data. This paper aims to review such state-of-the-art algorithms that use a limited number of annotated samples. We explain the fundamental principles of self-supervised learning, generative models, few-shot learning, and semi-supervised learning and summarize their applications in cardiac, abdomen, and brain MRI segmentation. Throughout this review, we highlight algorithms that can be employed based on the quantity of annotated data available. We also present a comprehensive list of notable publicly available MRI segmentation datasets. To conclude, we discuss possible future directions of the field-including emerging algorithms, such as contrastive language-image pretraining, and potential combinations across the methods discussed-that can further increase the efficacy of image segmentation with limited labels.

Evaluating synthetic neuroimaging data augmentation for automatic brain tumour segmentation with a deep fully-convolutional network

Gliomas observed in medical images require expert neuro-radiologist evaluation for treatment planning and monitoring, motivating development of intelligent systems capable of automating aspects of tumour evaluation. Deep learning models for automatic image segmentation rely on the amount and quality of training data. In this study we developed a neuroimaging synthesis technique to augment data for training fully-convolutional networks (U-nets) to perform automatic glioma segmentation. We used StyleGAN2-ada to simultaneously generate fluid-attenuated inversion recovery (FLAIR) magnetic resonance images and corresponding glioma segmentation masks. Synthetic data were successively added to real training data (n = 2751) in fourteen rounds of 1000 and used to train U-nets that were evaluated on held-out validation (n = 590) and test sets (n = 588). U-nets were trained with and without geometric augmentation (translation, zoom and shear), and Dice coefficients were computed to evaluate segmentation performance. We also monitored the number of training iterations before stopping, total training time, and time per iteration to evaluate computational costs associated with training each U-net. Synthetic data augmentation yielded marginal improvements in Dice coefficients (validation set +0.0409, test set +0.0355), whereas geometric augmentation improved generalization (standard deviation between training, validation and test set performances of 0.01 with, and 0.04 without geometric augmentation). Based on the modest performance gains for automatic glioma segmentation we find it hard to justify the computational expense of developing a synthetic image generation pipeline. Future work may seek to optimize the efficiency of synthetic data generation for augmentation of neuroimaging data.

PRIMIS: Privacy-preserving medical image sharing via deep sparsifying transform learning with obfuscation

OBJECTIVE

The primary objective of our study is to address the challenge of confidentially sharing medical images across different centers. This is often a critical necessity in both clinical and research environments, yet restrictions typically exist due to privacy concerns. Our aim is to design a privacy-preserving data-sharing mechanism that allows medical images to be stored as encoded and obfuscated representations in the public domain without revealing any useful or recoverable content from the images. In tandem, we aim to provide authorized users with compact private keys that could be used to reconstruct the corresponding images.

METHOD

Our approach involves utilizing a neural auto-encoder. The convolutional filter outputs are passed through sparsifying transformations to produce multiple compact codes. Each code is responsible for reconstructing different attributes of the image. The key privacy-preserving element in this process is obfuscation through the use of specific pseudo-random noise. When applied to the codes, it becomes computationally infeasible for an attacker to guess the correct representation for all the codes, thereby preserving the privacy of the images.

RESULTS

The proposed framework was implemented and evaluated using chest X-ray images for different medical image analysis tasks, including classification, segmentation, and texture analysis. Additionally, we thoroughly assessed the robustness of our method against various attacks using both supervised and unsupervised algorithms.

CONCLUSION

This study provides a novel, optimized, and privacy-assured data-sharing mechanism for medical images, enabling multi-party sharing in a secure manner. While we have demonstrated its effectiveness with chest X-ray images, the mechanism can be utilized in other medical images modalities as well.

All answers are in the images: A review of deep learning for cerebrovascular segmentation

Cerebrovascular imaging is a common examination. Its accurate cerebrovascular segmentation become an important auxiliary method for the diagnosis and treatment of cerebrovascular diseases, which has received extensive attention from researchers. Deep learning is a heuristic method that encourages researchers to derive answers from the images by driving datasets. With the continuous development of datasets and deep learning theory, it has achieved important success for cerebrovascular segmentation. Detailed survey is an important reference for researchers. To comprehensively analyze the newest cerebrovascular segmentation, we have organized and discussed researches centered on deep learning. This survey comprehensively reviews deep learning for cerebrovascular segmentation since 2015, it mainly includes sliding window based models, U-Net based models, other CNNs based models, small-sample based models, semi-supervised or unsupervised models, fusion based models, Transformer based models, and graphics based models. We organize the structures, improvement, and important parameters of these models, as well as analyze development trends and quantitative assessment. Finally, we have discussed the challenges and opportunities of possible research directions, hoping that our survey can provide researchers with convenient reference.

Medical image data augmentation: techniques, comparisons and interpretations

Designing deep learning based methods with medical images has always been an attractive area of research to assist clinicians in rapid examination and accurate diagnosis. Those methods need a large number of datasets including all variations in their training stages. On the other hand, medical images are always scarce due to several reasons, such as not enough patients for some diseases, patients do not want to allow their images to be used, lack of medical equipment or equipment, inability to obtain images that meet the desired criteria. This issue leads to bias in datasets, overfitting, and inaccurate results. Data augmentation is a common solution to overcome this issue and various augmentation techniques have been applied to different types of images in the literature. However, it is not clear which data augmentation technique provides more efficient results for which image type since different diseases are handled, different network architectures are used, and these architectures are trained and tested with different numbers of data sets in the literature. Therefore, in this work, the augmentation techniques used to improve performances of deep learning based diagnosis of the diseases in different organs (brain, lung, breast, and eye) from different imaging modalities (MR, CT, mammography, and fundoscopy) have been examined. Also, the most commonly used augmentation methods have been implemented, and their effectiveness in classifications with a deep network has been discussed based on quantitative performance evaluations. Experiments indicated that augmentation techniques should be chosen carefully according to image types.

Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism

The inverse design method based on a generative adversarial network (GAN) combined with a simulation neural network (sim-NN) and the self-attention mechanism is proposed in order to improve the efficiency of GAN for designing nanophotonic devices. The sim-NN can guide the model to produce more accurate device designs via the spectrum comparison, whereas the self-attention mechanism can help to extract detailed features of the spectrum by exploring their global interconnections. The nanopatterned power splitter with a 2 μm × 2 μm interference region is designed as an example to obtain the average high transmission (>94%) and low back-reflection (<0.5%) over the broad wavelength range of 1200~1650 nm. As compared to other models, this method can produce larger proportions of high figure-of-merit devices with various desired power-splitting ratios.

Synchronous Medical Image Augmentation framework for deep learning-based image segmentation

Various deep learning (DL) models are widely applied in medical image analysis, and their performance depends on the scale and diversity of available training data. However, medical images often suffer from difficulty in data acquisition, imbalance in sample categories, and high cost of labeling. In addition, most image augmentation approaches mainly focus on image synthesis only for classification tasks, and rarely consider the synthetic image-label pairs for image segmentation tasks. In this paper, we focus on the medical image augmentation for DL-based image segmentation and the synchronization between augmented image samples and their labels. We design a Synchronous Medical Image Augmentation (SMIA) framework, which includes two modules based on stochastic transformation and synthesis, and provides diverse and annotated training sets for DL models. In the transform-based SMIA module, for each medical image sample and its tissue segments, a subset of SMIA factors with a random number of factors and stochastic parameter values are selected to simultaneously generate augmented samples and the paired tissue segments. In the synthesis-based SMIA module, we randomly replace the original tissues with the augmented tissues using an equivalent replacement method to synthesize new medical images, which can well maintain the original medical implications. DL-based image segmentation experiments on bone marrow smear and dermoscopic images demonstrate that the proposed SMIA framework can generate category-balanced and diverse training data, and have a positive impact on the performance of the models.

Generative Consistency for Semi-Supervised Cerebrovascular Segmentation From TOF-MRA

Cerebrovascular segmentation from Time-of-flight magnetic resonance angiography (TOF-MRA) is a critical step in computer-aided diagnosis. In recent years, deep learning models have proved its powerful feature extraction for cerebrovascular segmentation. However, they require many labeled datasets to implement effective driving, which are expensive and professional. In this paper, we propose a generative consistency for semi-supervised (GCS) model. Considering the rich information contained in the feature map, the GCS model utilizes the generation results to constrain the segmentation model. The generated data comes from labeled data, unlabeled data, and unlabeled data after perturbation, respectively. The GCS model also calculates the consistency of the perturbed data to improve the feature mining ability. Subsequently, we propose a new model as the backbone of the GSC model. It transfers TOF-MRA into graph space and establishes correlation using Transformer. We demonstrated the effectiveness of the proposed model on TOF-MRA representations, and tested the GCS model with state-of-the-art semi-supervised methods using the proposed model as backbone. The experiments prove the important role of the GCS model in cerebrovascular segmentation. Code is available at https://github.com/MontaEllis/SSL-For-Medical-Segmentation.

Pairwise attention-enhanced adversarial model for automatic bone segmentation in CT images

Objective. Bone segmentation is a critical step in screw placement navigation. Although the deep learning methods have promoted the rapid development for bone segmentation, the local bone separation is still challenging due to irregular shapes and similar representational features.Approach. In this paper, we proposed the pairwise attention-enhanced adversarial model (Pair-SegAM) for automatic bone segmentation in computed tomography images, which includes the two parts of the segmentation model and discriminator. Considering that the distributions of the predictions from the segmentation model contains complicated semantics, we improve the discriminator to strengthen the awareness ability of the target region, improving the parsing of semantic information features. The Pair-SegAM has a pairwise structure, which uses two calculation mechanics to set up pairwise attention maps, then we utilize the semantic fusion to filter unstable regions. Therefore, the improved discriminator provides more refinement information to capture the bone outline, thus effectively enhancing the segmentation models for bone segmentation.Main results. To test the Pair-SegAM, we selected the two bone datasets for assessment. We evaluated our method against several bone segmentation models and latest adversarial models on the both datasets. The experimental results prove that our method not only exhibits superior bone segmentation performance, but also states effective generalization.Significance. Our method provides a more efficient segmentation of specific bones and has the potential to be extended to other semantic segmentation domains.

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.

Deep learning in neuroimaging data analysis: Applications, challenges, and solutions

Methods for the analysis of neuroimaging data have advanced significantly since the beginning of neuroscience as a scientific discipline. Today, sophisticated statistical procedures allow us to examine complex multivariate patterns, however most of them are still constrained by assuming inherent linearity of neural processes. Here, we discuss a group of machine learning methods, called deep learning, which have drawn much attention in and outside the field of neuroscience in recent years and hold the potential to surpass the mentioned limitations. Firstly, we describe and explain the essential concepts in deep learning: the structure and the computational operations that allow deep models to learn. After that, we move to the most common applications of deep learning in neuroimaging data analysis: prediction of outcome, interpretation of internal representations, generation of synthetic data and segmentation. In the next section we present issues that deep learning poses, which concerns multidimensionality and multimodality of data, overfitting and computational cost, and propose possible solutions. Lastly, we discuss the current reach of DL usage in all the common applications in neuroimaging data analysis, where we consider the promise of multimodality, capability of processing raw data, and advanced visualization strategies. We identify research gaps, such as focusing on a limited number of criterion variables and the lack of a well-defined strategy for choosing architecture and hyperparameters. Furthermore, we talk about the possibility of conducting research with constructs that have been ignored so far or/and moving toward frameworks, such as RDoC, the potential of transfer learning and generation of synthetic data.

The role of generative adversarial networks in brain MRI: a scoping review

The performance of artificial intelligence (AI) for brain MRI can improve if enough data are made available. Generative adversarial networks (GANs) showed a lot of potential to generate synthetic MRI data that can capture the distribution of real MRI. Besides, GANs are also popular for segmentation, noise removal, and super-resolution of brain MRI images. This scoping review aims to explore how GANs methods are being used on brain MRI data, as reported in the literature. The review describes the different applications of GANs for brain MRI, presents the most commonly used GANs architectures, and summarizes the publicly available brain MRI datasets for advancing the research and development of GANs-based approaches. This review followed the guidelines of PRISMA-ScR to perform the study search and selection. The search was conducted on five popular scientific databases. The screening and selection of studies were performed by two independent reviewers, followed by validation by a third reviewer. Finally, the data were synthesized using a narrative approach. This review included 139 studies out of 789 search results. The most common use case of GANs was the synthesis of brain MRI images for data augmentation. GANs were also used to segment brain tumors and translate healthy images to diseased images or CT to MRI and vice versa. The included studies showed that GANs could enhance the performance of AI methods used on brain MRI imaging data. However, more efforts are needed to transform the GANs-based methods in clinical applications.

Toward Sharing Brain Images: Differentially Private TOF-MRA Images With Segmentation Labels Using Generative Adversarial Networks

Sharing labeled data is crucial to acquire large datasets for various Deep Learning applications. In medical imaging, this is often not feasible due to privacy regulations. Whereas anonymization would be a solution, standard techniques have been shown to be partially reversible. Here, synthetic data using a Generative Adversarial Network (GAN) with differential privacy guarantees could be a solution to ensure the patient's privacy while maintaining the predictive properties of the data. In this study, we implemented a Wasserstein GAN (WGAN) with and without differential privacy guarantees to generate privacy-preserving labeled Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) image patches for brain vessel segmentation. The synthesized image-label pairs were used to train a U-net which was evaluated in terms of the segmentation performance on real patient images from two different datasets. Additionally, the Fréchet Inception Distance (FID) was calculated between the generated images and the real images to assess their similarity. During the evaluation using the U-Net and the FID, we explored the effect of different levels of privacy which was represented by the parameter ϵ. With stricter privacy guarantees, the segmentation performance and the similarity to the real patient images in terms of FID decreased. Our best segmentation model, trained on synthetic and private data, achieved a Dice Similarity Coefficient (DSC) of 0.75 for ϵ = 7.4 compared to 0.84 for ϵ = ∞ in a brain vessel segmentation paradigm (DSC of 0.69 and 0.88 on the second test set, respectively). We identified a threshold of ϵ <5 for which the performance (DSC <0.61) became unstable and not usable. Our synthesized labeled TOF-MRA images with strict privacy guarantees retained predictive properties necessary for segmenting the brain vessels. Although further research is warranted regarding generalizability to other imaging modalities and performance improvement, our results mark an encouraging first step for privacy-preserving data sharing in medical imaging.

Generative Adversarial Networks in Brain Imaging: A Narrative Review

Artificial intelligence (AI) is expected to have a major effect on radiology as it demonstrated remarkable progress in many clinical tasks, mostly regarding the detection, segmentation, classification, monitoring, and prediction of diseases. Generative Adversarial Networks have been proposed as one of the most exciting applications of deep learning in radiology. GANs are a new approach to deep learning that leverages adversarial learning to tackle a wide array of computer vision challenges. Brain radiology was one of the first fields where GANs found their application. In neuroradiology, indeed, GANs open unexplored scenarios, allowing new processes such as image-to-image and cross-modality synthesis, image reconstruction, image segmentation, image synthesis, data augmentation, disease progression models, and brain decoding. In this narrative review, we will provide an introduction to GANs in brain imaging, discussing the clinical potential of GANs, future clinical applications, as well as pitfalls that radiologists should be aware of.

Generative Adversarial Networks in Medical Image augmentation: A review

OBJECT

With the development of deep learning, the number of training samples for medical image-based diagnosis and treatment models is increasing. Generative Adversarial Networks (GANs) have attracted attention in medical image processing due to their excellent image generation capabilities and have been widely used in data augmentation. In this paper, a comprehensive and systematic review and analysis of medical image augmentation work are carried out, and its research status and development prospects are reviewed.

METHOD

This paper reviews 105 medical image augmentation related papers, which mainly collected by ELSEVIER, IEEE Xplore, and Springer from 2018 to 2021. We counted these papers according to the parts of the organs corresponding to the images, and sorted out the medical image datasets that appeared in them, the loss function in model training, and the quantitative evaluation metrics of image augmentation. At the same time, we briefly introduce the literature collected in three journals and three conferences that have received attention in medical image processing.

RESULT

First, we summarize the advantages of various augmentation models, loss functions, and evaluation metrics. Researchers can use this information as a reference when designing augmentation tasks. Second, we explore the relationship between augmented models and the amount of the training set, and tease out the role that augmented models may play when the quality of the training set is limited. Third, the statistical number of papers shows that the development momentum of this research field remains strong. Furthermore, we discuss the existing limitations of this type of model and suggest possible research directions.

CONCLUSION

We discuss GAN-based medical image augmentation work in detail. This method effectively alleviates the challenge of limited training samples for medical image diagnosis and treatment models. It is hoped that this review will benefit researchers interested in this field.

Transfer Learning Approaches for Neuroimaging Analysis: A Scoping Review

Deep learning algorithms have been moderately successful in diagnoses of diseases by analyzing medical images especially through neuroimaging that is rich in annotated data. Transfer learning methods have demonstrated strong performance in tackling annotated data. It utilizes and transfers knowledge learned from a source domain to target domain even when the dataset is small. There are multiple approaches to transfer learning that result in a range of performance estimates in diagnosis, detection, and classification of clinical problems. Therefore, in this paper, we reviewed transfer learning approaches, their design attributes, and their applications to neuroimaging problems. We reviewed two main literature databases and included the most relevant studies using predefined inclusion criteria. Among 50 reviewed studies, more than half of them are on transfer learning for Alzheimer's disease. Brain mapping and brain tumor detection were second and third most discussed research problems, respectively. The most common source dataset for transfer learning was ImageNet, which is not a neuroimaging dataset. This suggests that the majority of studies preferred pre-trained models instead of training their own model on a neuroimaging dataset. Although, about one third of studies designed their own architecture, most studies used existing Convolutional Neural Network architectures. Magnetic Resonance Imaging was the most common imaging modality. In almost all studies, transfer learning contributed to better performance in diagnosis, classification, segmentation of different neuroimaging diseases and problems, than methods without transfer learning. Among different transfer learning approaches, fine-tuning all convolutional and fully-connected layers approach and freezing convolutional layers and fine-tuning fully-connected layers approach demonstrated superior performance in terms of accuracy. These recent transfer learning approaches not only show great performance but also require less computational resources and time.

Image Features of Magnetic Resonance Angiography under Deep Learning in Exploring the Effect of Comprehensive Rehabilitation Nursing on the Neurological Function Recovery of Patients with Acute Stroke

This study was to explore the effects of imaging characteristics of magnetic resonance angiography (MRA) based on deep learning on the comprehensive rehabilitation nursing on the neurological recovery of patients with acute stroke. In this study, 84 patients with acute stroke who were treated in hospital were selected as the research objects, and they were rolled into a control group (routine care) and an experimental group (comprehensive rehabilitation care). The dense dilated block-convolution neural network (DD-CNN) algorithm under deep learning for cerebrovascular was adopted to assess the effect of comprehensive rehabilitation care on the neurological recovery of patients with acute stroke. The results showed that the Berg scale scores, Fugl-Meyer scores, and Functional Independence Measure (FIM) scores of the experimental group of patients after 6 weeks and 12 weeks of comprehensive rehabilitation nursing were greatly different from those before treatment, showing statistical differences (P < 0.05). Compared with conventional magnetic resonance imaging (MRI) images, MRA images based on CNN algorithm, Dense Net algorithm, and DD-CNN algorithm can more clearly show the patient's cerebral artery occlusion. The average dice similarity coefficient (DSC) values of CNN algorithm, Dense Net algorithm, and DD-CNN algorithm were determined to be 84.3%, 95.7%, and 97.8%, respectively; the average sensitivity (Sen) values of the three algorithms were 76.1%, 95.4%, and 96.8%, respectively; and the average accuracy (Acc) values were 87.9%, 96.3%, and 97.9%, respectively. Thus, there were statistically obvious differences among the three algorithms in terms of average values of DSC, Sen, and Acc (P < 0.05). The MRA images processed by the DD-CNN algorithm showed that the degree of neurological recovery of the experimental group was observably greater than that of the control group, and the difference was statistically obvious (P < 0.05). In short, the image features of MRA based on the deep learning DD-CNN algorithm showed good application value in studying the effect of comprehensive rehabilitation nursing on the neurological recovery of patients with acute stroke, and it was worthy of promotion.

Deep Learning Based Centerline-Aggregated Aortic Hemodynamics: An Efficient Alternative to Numerical Modelling of Hemodynamics

Image-based patient-specific modelling of hemodynamics are gaining increased popularity as a diagnosis and outcome prediction solution for a variety of cardiovascular diseases. While their potential to improve diagnostic capabilities and thereby clinical outcome is widely recognized, these methods require considerable computational resources since they are mostly based on conventional numerical methods such as computational fluid dynamics (CFD). As an alternative to the numerical methods, we propose a machine learning (ML) based approach to calculate patient-specific hemodynamic parameters. Compared to CFD based methods, our approach holds the benefit of being able to calculate a patient-specific hemodynamic outcome instantly with little need for computational power. In this proof-of-concept study, we present a deep artificial neural network (ANN) capable of computing hemodynamics for patients with aortic coarctation in a centerline aggregated (i.e. locally averaged) form. Considering the complex relation between vessels shape and hemodynamics on the one hand and the limited availability of suitable clinical data on the other, a sufficient accuracy of the ANN may however not be achieved with available data only. Another key aspect of this study is therefore the successful augmentation of available clinical data. Using a statistical shape model, additional training data was generated which substantially increased the ANNs accuracy, showcasing the ability of ML based methods to perform in-silico modelling tasks previously requiring resource intensive CFD simulations.

Iterative stripe artifact correction framework for TOF-MRA

The purpose of this study is to develop a practical stripe artifacts correction framework on three-dimensional (3-D) time-of-flight magnetic resonance angiography (TOF-MRA) obtained by multiple overlapping thin slab acquisitions (MOTSA) technology. In this work, the stripe artifacts in TOF-MRA were considered as a part of image texture. To separate the image structure and the texture, the relative total variation (RTV) was firstly employed to smooth the TOF-MRA for generating the template image with fewer image textures. Then a residual image was generated, which was the difference between the template image and the raw TOF-MRA. The residual image was served as the image texture, which contained the image details and stripe artifacts. Then, we obtained the artifact image from the residual image via a filter in a specific direction since the image artifacts appeared as stripes. The image details were then produced from the difference between the artifact image and the image texture. To produce the corrected images, we finally compensated the image details to the RTV smoothing image. The proposed method was continued until the stripe artifacts during the iteration vary as little as possible. The digital phantom and the real patients' TOF-MRA were used to test the approach. The spatial uniformity was increased from 74% to 82% and the structural similarity was improved from 86% to 98% in the digital phantom test by using the proposed algorithm. Our approach proved to be highly successful in eliminating stripe artifacts in real patient data tests while retaining image details. The proposed iterative framework on TOF-MRA stripe artifact correction is effective and appealing for enhancing the imaging performance of multi-slab 3-D acquisitions.