MRI simulation-based evaluation of image-processing and classification methods

Spatially constrained hyperpolarized 13C MRI pharmacokinetic rate constant map estimation using a digital brain phantom and a U-Net

Fitting rate constants to Hyperpolarized [1-13C]Pyruvate (HP C13) MRI data is a promising approach for quantifying metabolism in vivo. Current methods typically fit each voxel of the dataset using a least-squares objective. With these methods, each voxel is considered independently, and the spatial relationships are not considered during fitting. In this work, we use a convolutional neural network, a U-Net, with convolutions across the 2D spatial dimensions to estimate pyruvate-to-lactate conversion rate, kPL, maps from dynamic HP C13 datasets. We designed a framework for creating simulated anatomically accurate brain data that matches typical HP C13 characteristics to provide large amounts of data for training with ground truth results. The U-Net is initially trained with the digital phantom data and then further trained with in vivo datasets for regularization. In simulation where ground-truth kPL maps are available, the U-Net outperforms voxel-wise fitting with and without spatiotemporal denoising, particularly for low SNR data. In vivo data was evaluated qualitatively, as no ground truth is available, and before regularization the U-Net predicted kPL maps appear oversmoothed. After further training with in vivo data, the resulting kPL maps appear more realistic. This study demonstrates how to use a U-Net to estimate rate constant maps for HP C13 data, including a comprehensive framework for generating a large amount of anatomically realistic simulated data and an approach for regularization. This simulation and architecture provide a foundation that can be built upon in the future for improved performance.

Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative review

Multiple sclerosis (MS) is an autoimmune disease of the brain and spinal cord with both inflammatory and neurodegenerative features. Although advances in imaging techniques, particularly magnetic resonance imaging (MRI), have improved the process of diagnosis, its cause is unknown, a cure remains elusive and the evidence base to guide treatment is lacking. Computational techniques like machine learning (ML) have started to be used to understand MS. Published MS MRI-based computational studies can be divided into five categories: automated diagnosis; differentiation between lesion types and/or MS stages; differential diagnosis; monitoring and predicting disease progression; and synthetic MRI dataset generation. Collectively, these approaches show promise in assisting with MS diagnosis, monitoring of disease activity and prediction of future progression, all potentially contributing to disease management. Analysis quality using ML is highly dependent on the dataset size and variability used for training. Wider public access would mean larger datasets for experimentation, resulting in higher-quality analysis, permitting for more conclusive research. This narrative review provides an outline of the fundamentals of MS pathology and pathogenesis, diagnostic techniques and data types in computational analysis, as well as collating literature pertaining to the application of computational techniques to MRI towards developing a better understanding of MS.

Enhanced Spatial Fuzzy C-Means Algorithm for Brain Tissue Segmentation in T1 Images

Magnetic Resonance Imaging (MRI) plays an important role in neurology, particularly in the precise segmentation of brain tissues. Accurate segmentation is crucial for diagnosing brain injuries and neurodegenerative conditions. We introduce an Enhanced Spatial Fuzzy C-means (esFCM) algorithm for 3D T1 MRI segmentation to three tissues, i.e. White Matter (WM), Gray Matter (GM), and Cerebrospinal Fluid (CSF). The esFCM employs a weighted least square algorithm utilizing the Structural Similarity Index (SSIM) for polynomial bias field correction. It also takes advantage of the information from the membership function of the last iteration to compute neighborhood impact. This strategic refinement enhances the algorithm's adaptability to complex image structures, effectively addressing challenges such as intensity irregularities and contributing to heightened segmentation accuracy. We compare the segmentation accuracy of esFCM against four variants of FCM, Gaussian Mixture Model (GMM) and FSL and ANTs algorithms using four various dataset, employing three measurement criteria. Comparative assessments underscore esFCM's superior performance, particularly in scenarios involving added noise and bias fields.The obtained results emphasize the significant potential of the proposed method in the segmentation of MRI images.

PhoenixMR: A GPU-based MRI simulation framework with runtime-dynamic code execution

BACKGROUND

Simulations of physical processes and behavior can provide unique insights and understanding of real-world problems. Magnetic Resonance Imaging (MRI) is an imaging technique with several components of complexity. Several of these components have been characterized and simulated in the past. However, several computational challenges prevent simulations from being simultaneously fast, flexible, and accurate.

PURPOSE

The simulation of MRI experiments is underutilized by medical physicists and researchers using currently available simulators due to reasons including speed, accuracy, and extensibility constraints. This paper introduces an innovative MRI simulation engine and framework that aims to overcome these issues making available realistic and fast MRI simulation.

METHODS

Using the CUDA C/C++ programing language, an MRI simulation engine (PhoenixMR), incorporating a Turing-complete virtual machine (VM) to simulate abstract spatiotemporal complexities, was developed. This engine solves a set of time-discrete Bloch equations using the symmetric operator splitting technique. An extensible front-end framework package (written in Python) aids the use of PhoenixMR to simplify simulation development.

RESULTS

The PhoenixMR library and front-end codes have been developed and tested. A set of example simulations were performed to demonstrate the ease of use and flexibility of simulation components such as geometrical setup, pulse sequence design, phantom design, and so forth. Initial validation of PhoenixMR is performed by comparing its accuracy and performance against a widely used MRI simulator using identical simulation parameters. Validation results show PhoenixMR simulations are three orders of magnitude faster. There is also strong agreement between models.

CONCLUSIONS

A novel MRI simulation platform called PhoenixMR has been introduced. This research tool is designed to be usable by physicists and engineers interested in performing MRI simulations. Examples are shown demonstrating the accuracy, flexibility, and usability of PhoenixMR in several key areas of MRI simulation.

aXonica: A support package for MRI based Neuroimaging

Magnetic Resonance Imaging (MRI) assists in studying the nervous system. MRI scans undergo significant processing before presenting the final images to medical practitioners. These processes are executed with ease due to excellent software pipelines. However, establishing software workstations is non-trivial and requires researchers in life sciences to be comfortable in downloading, installing, and scripting software that is non-user-friendly and may lack basic GUI. As researchers struggle with these skills, there is a dire need to develop software packages that can automatically install software pipelines speeding up building software workstations and laboratories. Previous solutions include NeuroDebian, BIDS Apps, Flywheel, QMENTA, Boutiques, Brainlife and Neurodesk. Overall, all these solutions complement each other. NeuroDebian covers neuroscience and has a wider scope, providing only 51 tools for MRI. Whereas, BIDS Apps is committed to the BIDS format, covering only 45 software related to MRI. Boutiques is more flexible, facilitating its pipelines to be easily installed as separate containers, validated, published, and executed. Whereas, both Flywheel and Qmenta are propriety, leaving four for users looking for 'free for use' tools, i.e., NeuroDebian, Brainlife, Neurodesk, and BIDS Apps. This paper presents an extensive survey of 317 tools published in MRI-based neuroimaging in the last ten years, along with 'aXonica,' an MRI-based neuroimaging support package that is unbiased towards any formatting standards and provides 130 applications, more than that of NeuroDebian (51), BIDS App (45), Flywheel (70), and Neurodesk (85). Using a technology stack that employs GUI as the front-end and shell scripted back-end, aXonica provides (i) 130 tools that span the entire MRI-based neuroimaging analysis, and allow the user to (ii) select the software of their choice, (iii) automatically resolve individual dependencies and (iv) installs them. Hence, aXonica can serve as an important resource for researchers and teachers working in the field of MRI-based Neuroimaging to (a) develop software workstations, and/or (b) install newer tools in their existing workstations.

New non-local mean methods for MRI denoising based on global self-similarity between values

Magnetic resonance imaging (MRI) is a non-invasive medical imaging technique that provides high-resolution 3D images and valuable insights into human tissue conditions. Even at present, the refinement of denoising methods for MRI remains a crucial concern for improving the quality of the images. This study aims to improve the prefiltered rotationally invariant non-local principal component analysis (PRI-NL-PCA) algorithm. We relaxed the original restrictions using particle swarm optimization to determine optimal parameters for the PCA part of the original algorithm. In addition, we adjusted the prefiltered rotationally invariant non-local mean (PRI-NLM) part by traversing the signal intensities of voxels instead of their spatial positions to reduce duplicate calculations and expand the search volume to the whole image when estimating voxels' signal intensities. The new method demonstrated superior denoising performance compared to the original approach. Moreover, in most cases, the new algorithm ran faster. Furthermore, our proposed method can also be applied to process Gaussian noise in natural images and has the potential to enhance other NLM-based denoising algorithms.

Brain MR image simulation for deep learning based medical image analysis networks

BACKGROUND AND OBJECTIVE

As large sets of annotated MRI data are needed for training and validating deep learning based medical image analysis algorithms, the lack of sufficient annotated data is a critical problem. A possible solution is the generation of artificial data by means of physics-based simulations. Existing brain simulation data is limited in terms of anatomical models, tissue classes, fixed tissue characteristics, MR sequences and overall realism.

METHODS

We propose a realistic simulation framework by incorporating patient-specific phantoms and Bloch equations-based analytical solutions for fast and accurate MRI simulations. A large number of labels are derived from open-source high-resolution T1w MRI data using a fully automated brain classification tool. The brain labels are taken as ground truth (GT) on which MR images are simulated using our framework. Moreover, we demonstrate that the T1w MR images generated from our framework along with GT annotations can be utilized directly to train a 3D brain segmentation network. To evaluate our model further on larger set of real multi-source MRI data without GT, we compared our model to existing brain segmentation tools, FSL-FAST and SynthSeg.

RESULTS

Our framework generates 3D brain MRI for variable anatomy, sequence, contrast, SNR and resolution. The brain segmentation network for WM/GM/CSF trained only on T1w simulated data shows promising results on real MRI data from MRBrainS18 challenge dataset with a Dice scores of 0.818/0.832/0.828. On OASIS data, our model exhibits a close performance to FSL, both qualitatively and quantitatively with a Dice scores of 0.901/0.939/0.937.

CONCLUSIONS

Our proposed simulation framework is the initial step towards achieving truly physics-based MRI image generation, providing flexibility to generate large sets of variable MRI data for desired anatomy, sequence, contrast, SNR, and resolution. Furthermore, the generated images can effectively train 3D brain segmentation networks, mitigating the reliance on real 3D annotated data.

SOLID: a novel similarity metric for mono-modal and multi-modal deformable image registration

Medical image registration is an integral part of various clinical applications including image guidance, motion tracking, therapy assessment and diagnosis. We present a robust approach for mono-modal and multi-modal medical image registration. To this end, we propose the novel shape operator based local image distance (SOLID) which estimates the similarity of images by comparing their second-order curvature information. Our similarity metric is rigorously tailored to be suitable for comparing images from different medical imaging modalities or image contrasts. A critical element of our method is the extraction of local features using higher-order shape information, enabling the accurate identification and registration of smaller structures. In order to assess the efficacy of the proposed similarity metric, we have implemented a variational image registration algorithm that relies on the principle of matching the curvature information of the given images. The performance of the proposed algorithm has been evaluated against various alternative state-of-the-art variational registration algorithms. Our experiments involve mono-modal as well as multi-modal and cross-contrast co-registration tasks in a broad variety of anatomical regions. Compared to the evaluated alternative registration methods, the results indicate a very favorable accuracy, precision and robustness of the proposed SOLID method in various highly challenging registration tasks.

SIMPLEX: Multiple phase-cycled bSSFP quantitative magnetization transfer imaging with physic-guided simulation learning of neural network

Most quantitative magnetization transfer (qMT) imaging methods require acquiring additional quantitative maps (such as T1) for data fitting. A method based on multiple phase-cycled bSSFP was recently proposed to enable high-resolution 3D qMT imaging based on least square fitting without any extra acquisition, and thus has high potential for simplifying the qMT procedure. However, the quantification of qMT parameters with this method was suboptimal, limiting its potential for clinical application despite its simpler protocol and higher spatial resolution. To improve the fitting of qMT data obtained with multiple phase-cycled bSSFP, we propose SIMulation-based Physics-guided Learning of neural network for qMT parameters EXtraction, or SIMPLEX. In contrast to previous deep learning supervised approaches for quantitative MR that require the acquisition of input data and corresponding ground truth for training, we leveraged the MR signal model to generate training samples without expensive data curation. The network was trained exclusively with simulation data by predicting the simulation parameters. The same network was applied directly to in-vivo data without additional training. The approach was verified with both simulation and in-vivo data. SIMPLEX showed a decrease in fitting mean squared error for all simulation data compared to the existing least-square fitting method. The in-vivo experiment revealed that the network performed well with the real in vivo data unseen during training. For all experiments, we observed that SIMPLEX consistently improved the quantification quality of the qMT parameters whilst being more robust to noise compared to the prior technique. The proposed SIMPLEX will expedite the routine clinical application of qMT by providing qMT parameters (exchange rate, pool fraction) as well as T1, T2, and ΔB0 maps simultaneously with high spatial resolution, better reliability, and reduced processing time.

Denoising and uncertainty estimation in parameter mapping with approximate Bayesian deep image priors

PURPOSE

To mitigate the problem of noisy parameter maps with high uncertainties by casting parameter mapping as a denoising task based on Deep Image Priors.

METHODS

We extend the concept of denoising with Deep Image Prior (DIP) into parameter mapping by treating the output of an image-generating network as a parametrization of tissue parameter maps. The method implicitly denoises the parameter mapping process by filtering low-level image features with an untrained convolutional neural network (CNN). Our implementation includes uncertainty estimation from Bernoulli approximate variational inference, implemented with MC dropout, which provides model uncertainty in each voxel of the denoised parameter maps. The method is modular, so the specifics of different applications (e.g., T1 mapping) separate into application-specific signal equation blocks. We evaluate the method on variable flip angle T1 mapping, multi-echo T2 mapping, and apparent diffusion coefficient mapping.

RESULTS

We found that deep image prior adapts successfully to several applications in parameter mapping. In all evaluations, the method produces noise-reduced parameter maps with decreased uncertainty compared to conventional methods. The downsides of the proposed method are the long computational time and the introduction of some bias from the denoising prior.

CONCLUSION

DIP successfully denoise the parameter mapping process and applies to several applications with limited hyperparameter tuning. Further, it is easy to implement since DIP methods do not use network training data. Although time-consuming, uncertainty information from MC dropout makes the method more robust and provides useful information when properly calibrated.

A spatially variant high-order variational model for Rician noise removal

Rician noise removal is an important problem in magnetic resonance (MR) imaging. Among the existing approaches, the variational method is an essential mathematical technique for Rician noise reduction. The previous variational methods mainly employ the total variation (TV) regularizer, which is a first-order term. Although the TV regularizer is able to remove noise while preserving object edges, it suffers the staircase effect. Besides, the adaptability has received little research attention. To this end, we propose a spatially variant high-order variational model (SVHOVM) for Rician noise reduction. We introduce a spatially variant TV regularizer, which can adjust the smoothing strength for each pixel depending on its characteristics. Furthermore, SVHOVM utilizes the bounded Hessian (BH) regularizer to diminish the staircase effect generated by the TV term. We develop a split Bregman algorithm to solve the proposed minimization problem. Extensive experiments are performed to demonstrate the superiority of SVHOVM over some existing variational models for Rician noise removal.

Generating Synthetic Radiological Images with PySynthMRI: An Open-Source Cross-Platform Tool

Synthetic MR Imaging allows for the reconstruction of different image contrasts from a single acquisition, reducing scan times. Commercial products that implement synthetic MRI are used in research. They rely on vendor-specific acquisitions and do not include the possibility of using custom multiparametric imaging techniques. We introduce PySynthMRI, an open-source tool with a user-friendly interface that uses a set of input images to generate synthetic images with diverse radiological contrasts by varying representative parameters of the desired target sequence, including the echo time, repetition time and inversion time(s). PySynthMRI is written in Python 3.6, and it can be executed under Linux, Windows, or MacOS as a python script or an executable. The tool is free and open source and is developed while taking into consideration the possibility of software customization by the end user. PySynthMRI generates synthetic images by calculating the pixelwise signal intensity as a function of a set of input images (e.g., T1 and T2 maps) and simulated scanner parameters chosen by the user via a graphical interface. The distribution provides a set of default synthetic contrasts, including T1w gradient echo, T2w spin echo, FLAIR and Double Inversion Recovery. The synthetic images can be exported in DICOM or NiFTI format. PySynthMRI allows for the fast synthetization of differently weighted MR images based on quantitative maps. Specialists can use the provided signal models to retrospectively generate contrasts and add custom ones. The modular architecture of the tool can be exploited to add new features without impacting the codebase.

An Efficient Ensemble Approach for Alzheimer's Disease Detection Using an Adaptive Synthetic Technique and Deep Learning

Alzheimer's disease is an incurable neurological disorder that leads to a gradual decline in cognitive abilities, but early detection can significantly mitigate symptoms. The automatic diagnosis of Alzheimer's disease is more important due to the shortage of expert medical staff, because it reduces the burden on medical staff and enhances the results of diagnosis. A detailed analysis of specific brain disorder tissues is required to accurately diagnose the disease via segmented magnetic resonance imaging (MRI). Several studies have used the traditional machine-learning approaches to diagnose the disease from MRI, but manual extracted features are more complex, time-consuming, and require a huge amount of involvement from expert medical staff. The traditional approach does not provide an accurate diagnosis. Deep learning has automatic extraction features and optimizes the training process. The Magnetic Resonance Imaging (MRI) Alzheimer's disease dataset consists of four classes: mild demented (896 images), moderate demented (64 images), non-demented (3200 images), and very mild demented (2240 images). The dataset is highly imbalanced. Therefore, we used the adaptive synthetic oversampling technique to address this issue. After applying this technique, the dataset was balanced. The ensemble of VGG16 and EfficientNet was used to detect Alzheimer's disease on both imbalanced and balanced datasets to validate the performance of the models. The proposed method combined the predictions of multiple models to make an ensemble model that learned complex and nuanced patterns from the data. The input and output of both models were concatenated to make an ensemble model and then added to other layers to make a more robust model. In this study, we proposed an ensemble of EfficientNet-B2 and VGG-16 to diagnose the disease at an early stage with the highest accuracy. Experiments were performed on two publicly available datasets. The experimental results showed that the proposed method achieved 97.35% accuracy and 99.64% AUC for multiclass datasets and 97.09% accuracy and 99.59% AUC for binary-class datasets. We evaluated that the proposed method was extremely efficient and provided superior performance on both datasets as compared to previous methods.

Multimodal Image Registration Using a Viscous Fluid Model with the Bhattacharyya Distance

Image registration is an elementary task in medical image processing and analysis, which can be divided into monomodal and multimodal. Direct 3D multimodal registration in volumetric medical images can provide more insight into the interpretation of subsequent image processing applications than 2D methods. This paper is dedicated to the development of a 3D multimodal image registration algorithm based on a viscous fluid model associated with the Bhattacharyya distance. In our approach, a modified Navier-Stoke's equation is exploited as the foundation of the multimodal image registration framework. The hopscotch method is numerically implemented to solve the velocity field, whose values at the explicit locations are first computed and the values at the implicit positions are solved by transposition. The differential of the Bhattacharyya distance is incorporated into the body force function, which is the main driving force for deformation, to enable multimodal registration. A variety of simulated and real brain MR images were utilized to assess the proposed 3D multimodal image registration system. Preliminary experimental results indicated that our algorithm produced high registration accuracy in various registration scenarios and outperformed other competing methods in many multimodal image registration tasks.Clinical Relevance- This facilitates the disease diagnosis and treatment planning that requires accurate 3D multimodal image registration without massive image data and extensive training regardless of the imaging modality.

A Framework for Simulating Cardiac MR Images With Varying Anatomy and Contrast

One of the limiting factors for the development and adoption of novel deep-learning (DL) based medical image analysis methods is the scarcity of labeled medical images. Medical image simulation and synthesis can provide solutions by generating ample training data with corresponding ground truth labels. Despite recent advances, generated images demonstrate limited realism and diversity. In this work, we develop a flexible framework for simulating cardiac magnetic resonance (MR) images with variable anatomical and imaging characteristics for the purpose of creating a diversified virtual population. We advance previous works on both cardiac MR image simulation and anatomical modeling to increase the realism in terms of both image appearance and underlying anatomy. To diversify the generated images, we define parameters: 1)to alter the anatomy, 2) to assign MR tissue properties to various tissue types, and 3) to manipulate the image contrast via acquisition parameters. The proposed framework is optimized to generate a substantial number of cardiac MR images with ground truth labels suitable for downstream supervised tasks. A database of virtual subjects is simulated and its usefulness for aiding a DL segmentation method is evaluated. Our experiments show that training completely with simulated images can perform comparable with a model trained with real images for heart cavity segmentation in mid-ventricular slices. Moreover, such data can be used in addition to classical augmentation for boosting the performance when training data is limited, particularly by increasing the contrast and anatomical variation, leading to better regularization and generalization. The database is publicly available at https://osf.io/bkzhm/ and the simulation code will be available at https://github.com/sinaamirrajab/CMRI.

A comprehensive survey of deep learning research on medical image analysis with focus on transfer learning

This survey aims to identify commonly used methods, datasets, future trends, knowledge gaps, constraints, and limitations in the field to provide an overview of current solutions used in medical image analysis in parallel with the rapid developments in transfer learning (TL). Unlike previous studies, this survey grouped the last five years of current studies for the period between January 2017 and February 2021 according to different anatomical regions and detailed the modality, medical task, TL method, source data, target data, and public or private datasets used in medical imaging. Also, it provides readers with detailed information on technical challenges, opportunities, and future research trends. In this way, an overview of recent developments is provided to help researchers to select the most effective and efficient methods and access widely used and publicly available medical datasets, research gaps, and limitations of the available literature.

Segmentation of Brain Tissues from MRI Images Using Multitask Fuzzy Clustering Algorithm

In recent years, brain magnetic resonance imaging (MRI) image segmentation has drawn considerable attention. MRI image segmentation result provides a basis for medical diagnosis. The segmentation result influences the clinical treatment directly. Nevertheless, MRI images have shortcomings such as noise and the inhomogeneity of grayscale. The performance of traditional segmentation algorithms still needs further improvement. In this paper, we propose a novel brain MRI image segmentation algorithm based on fuzzy C-means (FCM) clustering algorithm to improve the segmentation accuracy. First, we introduce multitask learning strategy into FCM to extract public information among different segmentation tasks. It combines the advantages of the two algorithms. The algorithm enables to utilize both public information among different tasks and individual information within tasks. Then, we design an adaptive task weight learning mechanism, and a weighted multitask fuzzy C-means (WMT-FCM) clustering algorithm is proposed. Under the adaptive task weight learning mechanism, each task obtains the optimal weight and achieves better clustering performance. Simulated MRI images from McConnell BrainWeb have been used to evaluate the proposed algorithm. Experimental results demonstrate that the proposed method provides more accurate and stable segmentation results than its competitors on the MRI images with various noise and intensity inhomogeneity.

A Brief Survey on No-Reference Image Quality Assessment Methods for Magnetic Resonance Images

No-reference image quality assessment (NR-IQA) methods automatically and objectively predict the perceptual quality of images without access to a reference image. Therefore, due to the lack of pristine images in most medical image acquisition systems, they play a major role in supporting the examination of resulting images and may affect subsequent treatment. Their usage is particularly important in magnetic resonance imaging (MRI) characterized by long acquisition times and a variety of factors that influence the quality of images. In this work, a survey covering recently introduced NR-IQA methods for the assessment of MR images is presented. First, typical distortions are reviewed and then popular NR methods are characterized, taking into account the way in which they describe MR images and create quality models for prediction. The survey also includes protocols used to evaluate the methods and popular benchmark databases. Finally, emerging challenges are outlined along with an indication of the trends towards creating accurate image prediction models.

A Fetal Brain magnetic resonance Acquisition Numerical phantom (FaBiAN)

Accurate characterization of in utero human brain maturation is critical as it involves complex and interconnected structural and functional processes that may influence health later in life. Magnetic resonance imaging is a powerful tool to investigate equivocal neurological patterns during fetal development. However, the number of acquisitions of satisfactory quality available in this cohort of sensitive subjects remains scarce, thus hindering the validation of advanced image processing techniques. Numerical phantoms can mitigate these limitations by providing a controlled environment with a known ground truth. In this work, we present FaBiAN, an open-source Fetal Brain magnetic resonance Acquisition Numerical phantom that simulates clinical T2-weighted fast spin echo sequences of the fetal brain. This unique tool is based on a general, flexible and realistic setup that includes stochastic fetal movements, thus providing images of the fetal brain throughout maturation comparable to clinical acquisitions. We demonstrate its value to evaluate the robustness and optimize the accuracy of an algorithm for super-resolution fetal brain magnetic resonance imaging from simulated motion-corrupted 2D low-resolution series compared to a synthetic high-resolution reference volume. We also show that the images generated can complement clinical datasets to support data-intensive deep learning methods for fetal brain tissue segmentation.

The “Coherent Data Set”: Combining Patient Data and Imaging in a Comprehensive, Synthetic Health Record

The “Coherent Data Set” is a novel synthetic data set that leverages structured data from Synthea™ to create a longitudinal, “coherent” patient-level electronic health record (EHR). Comprised of synthetic patients, the Coherent Data Set is publicly available, reproducible using Synthea™, and free of the privacy risks that arise from using real patient data. The Coherent Data Set provides complex and representative health records that can be leveraged by health IT professionals without the risks associated with de-identified patient data. It includes familial genomes that were created through a simulation of the genetic reproduction process; magnetic resonance imaging (MRI) DICOM files created with a voxel-based computational model; clinical notes in the style of traditional subjective, objective, assessment, and plan notes; and physiological data that leverage existing System Biology Markup Language (SBML) models to capture non-linear changes in patient health metrics. HL7 Fast Healthcare Interoperability Resources (FHIR®) links the data together. The models can generate clinically logical health data, but ensuring clinical validity remains a challenge without comparable data to substantiate results. We believe this data set is the first of its kind and a novel contribution to practical health interoperability efforts.

Avoiding data loss: Synthetic MRIs generated from diffusion imaging can replace corrupted structural acquisitions for freesurfer-seeded tractography

Magnetic Resonance Imaging (MRI) motion artefacts frequently complicate structural and diffusion MRI analyses. While diffusion imaging is easily ‘scrubbed’ of motion affected volumes, the same is not true for T1w or T2w ‘structural’ images. Structural images are critical to most diffusion-imaging pipelines thus their corruption can lead to disproportionate data loss. To enable diffusion-image processing when structural images are missing or have been corrupted, we propose a means by which synthetic structural images can be generated from diffusion MRI. This technique combines multi-tissue constrained spherical deconvolution, which is central to many existing diffusion analyses, with the Bloch equations that allow simulation of MRI intensities for given scanner parameters and magnetic resonance (MR) tissue properties. We applied this technique to 32 scans, including those acquired on different scanners, with different protocols and with pathology present. The resulting synthetic T1w and T2w images were visually convincing and exhibited similar tissue contrast to acquired structural images. These were also of sufficient quality to drive a Freesurfer-based tractographic analysis. In this analysis, probabilistic tractography connecting the thalamus to the primary sensorimotor cortex was delineated with Freesurfer, using either real or synthetic structural images. Tractography for real and synthetic conditions was largely identical in terms of both voxels encountered (Dice 0.88–0.95) and mean fractional anisotropy (intrasubject absolute difference 0.00–0.02). We provide executables for the proposed technique in the hope that these may aid the community in analysing datasets where structural image corruption is common, such as studies of children or cognitively impaired persons.

Convolutional Neural Networks for Segmenting Cerebellar Fissures from Magnetic Resonance Imaging

The human cerebellum plays an important role in coordination tasks. Diseases such as spinocerebellar ataxias tend to cause severe damage to the cerebellum, leading patients to a progressive loss of motor coordination. The detection of such damages can help specialists to approximate the state of the disease, as well as to perform statistical analysis, in order to propose treatment therapies for the patients. Manual segmentation of such patterns from magnetic resonance imaging is a very difficult and time-consuming task, and is not a viable solution if the number of images to process is relatively large. In recent years, deep learning techniques such as convolutional neural networks (CNNs or convnets) have experienced an increased development, and many researchers have used them to automatically segment medical images. In this research, we propose the use of convolutional neural networks for automatically segmenting the cerebellar fissures from brain magnetic resonance imaging. Three models are presented, based on the same CNN architecture, for obtaining three different binary masks: fissures, cerebellum with fissures, and cerebellum without fissures. The models perform well in terms of precision and efficiency. Evaluation results show that convnets can be trained for such purposes, and could be considered as additional tools in the diagnosis and characterization of neurodegenerative diseases.

Dual k-space and image-space post-processing for field-cycling MRI under low magnetic field stability and homogeneity conditions

We present a method to correct artifacts typically present in images acquired in field-cycled MRI experiments under poor magnetic field spatial-homogeneity and time-stability conditions. The proposed method was tested in both simulated and experimental data. The experiments were performed using a fast field-cycling MRI relaxometer of own design, based on a current-driven variable-geometry electromagnet. Current instability-induced artifacts in the images were mitigated through a phase correction array resulted from entropy and background minimization. Image distortions due to magnetic field inhomogeneity were compensated through two different approaches, involving a previous determination of the magnetic field homogeneity-map, or an experimental protocol where two images are acquired with inverted readout gradient polarity. Results show that images acquired at extreme conditions can be successfully improved, thus strengthening the possibilities for both low-cost MRI devices and faster field-switched MRI systems.

Kernel graph filtering-A new method for dynamic sinogram denoising

Low count PET (positron emission tomography) imaging is often desirable in clinical diagnosis and biomedical research, but its images are generally very noisy, due to the very weak signals in the sinograms used in image reconstruction. To address this issue, this paper presents a novel kernel graph filtering method for dynamic PET sinogram denoising. This method is derived from treating the dynamic sinograms as the signals on a graph, and learning the graph adaptively from the kernel principal components of the sinograms to construct a lowpass kernel graph spectrum filter. The kernel graph filter thus obtained is then used to filter the original sinogram time frames to obtain the denoised sinograms for PET image reconstruction. Extensive tests and comparisons on the simulated and real life in-vivo dynamic PET datasets show that the proposed method outperforms the existing methods in sinogram denoising and image enhancement of dynamic PET at all count levels, especially at low count, with a great potential in real life applications of dynamic PET imaging.

Technical Note: Four-dimensional deformable digital phantom for MRI sequence development

PURPOSE

MR-guided radiotherapy has different requirements for the images than diagnostic radiology, thus requiring development of novel imaging sequences. MRI simulation is an excellent tool for optimizing these new sequences; however, currently available software does not provide all the necessary features. In this paper, we present a digital framework for testing MRI sequences that incorporates anatomical structure, respiratory motion, and realistic presentation of MR physics.

METHODS

The extended Cardiac-Torso (XCAT) software was used to create T1 , T2 , and proton density maps that formed the anatomical structure of the phantom. Respiratory motion model was based on the XCAT deformation vector fields, modified to create a motion model driven by a respiration signal. MRI simulation was carried out with JEMRIS, an open source Bloch simulator. We developed an extension for JEMRIS, which calculates the motion of each spin independently, allowing for deformable motion.

RESULTS

The performance of the framework was demonstrated through simulating the acquisition of a two-dimensional (2D) cine and demonstrating expected motion ghosts from T2 weighted spin echo acquisitions with different respiratory patterns. All simulations were consistent with behavior previously described in literature. Simulations with deformable motion were not more time consuming than with rigid motion.

CONCLUSIONS

We present a deformable four-dimensional (4D) digital phantom framework for MR sequence development. The framework incorporates anatomical structure, realistic breathing patterns, deformable motion, and Bloch simulation to achieve accurate simulation of MRI. This method is particularly relevant for testing novel imaging sequences for the purpose of MR-guided radiotherapy in lungs and abdomen.

An atlas of classifiers-a machine learning paradigm for brain MRI segmentation

We present the Atlas of Classifiers (AoC)-a conceptually novel framework for brain MRI segmentation. The AoC is a spatial map of voxel-wise multinomial logistic regression (LR) functions learned from the labeled data. Upon convergence, the resulting fixed LR weights, a few for each voxel, represent the training dataset. It can, therefore, be considered as a light-weight learning machine, which despite its low capacity does not underfit the problem. The AoC construction is independent of the actual intensities of the test images, providing the flexibility to train it on the available labeled data and use it for the segmentation of images from different datasets and modalities. In this sense, it does not overfit the training data, as well. The proposed method has been applied to numerous publicly available datasets for the segmentation of brain MRI tissues and is shown to be robust to noise and outreach commonly used methods. Promising results were also obtained for multi-modal, cross-modality MRI segmentation. Finally, we show how AoC trained on brain MRIs of healthy subjects can be exploited for lesion segmentation of multiple sclerosis patients.

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

With the advances of data-driven machine learning research, a wide variety of prediction problems have been tackled. It has become critical to explore how machine learning and specifically deep learning methods can be exploited to analyse healthcare data. A major limitation of existing methods has been the focus on grid-like data; however, the structure of physiological recordings are often irregular and unordered, which makes it difficult to conceptualise them as a matrix. As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interacting nodes connected by edges whose weights can be determined by either temporal associations or anatomical junctions. In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare. We provide an overview of these methods in a systematic manner, organized by their domain of application including functional connectivity, anatomical structure, and electrical-based analysis. We also outline the limitations of existing techniques and discuss potential directions for future research.

Evaluation of MRI Denoising Methods Using Unsupervised Learning

In this paper we evaluate two unsupervised approaches to denoise Magnetic Resonance Images (MRI) in the complex image space using the raw information that k-space holds. The first method is based on Stein’s Unbiased Risk Estimator, while the second approach is based on a blindspot network, which limits the network’s receptive field. Both methods are tested on two different datasets, one containing real knee MRI and the other consists of synthetic brain MRI. These datasets contain information about the complex image space which will be used for denoising purposes. Both networks are compared against a state-of-the-art algorithm, Non-Local Means (NLM) using quantitative and qualitative measures. For most given metrics and qualitative measures, both networks outperformed NLM, and they prove to be reliable denoising methods.

Deep learning-enhanced T1 mapping with spatial-temporal and physical constraint

PURPOSE

To propose a reconstruction framework to generate accurate T₁ maps for a fast MR T₁ mapping sequence.

METHODS

A deep learning-enhanced T₁ mapping method with spatial-temporal and physical constraint (DAINTY) was proposed. This method explicitly imposed low-rank and sparsity constraints on the multiframe T₁ -weighted images to exploit the spatial-temporal correlation. A deep neural network was used to efficiently perform T₁ mapping as well as denoise and reduce undersampling artifacts. Additionally, the physical constraint was used to build a bridge between low-rank and sparsity constraint and deep learning prior, so the benefits of constrained reconstruction and deep learning can be both available. The DAINTY method was trained on simulated brain data sets, but tested on real acquired phantom, 6 healthy volunteers, and 7 atherosclerosis patients, compared with the narrow-band k-space-weighted image contrast filter conjugate-gradient SENSE (NK-CS) method, kt-sparse-SENSE (kt-SS) method, and low-rank plus sparsity (L+S) method with least-squares T₁ fitting and direct deep learning mapping.

RESULTS

The DAINTY method can generate more accurate T₁ maps and higher-quality T₁ -weighted images compared with other methods. For atherosclerosis patients, the intraplaque hemorrhage can be successfully detected. The computation speed of DAINTY was 10 times faster than traditional methods. Meanwhile, DAINTY can reconstruct images with comparable quality using only 50% of k-space data.

CONCLUSION

The proposed method can provide accurate T₁ maps and good-quality T₁ -weighted images with high efficiency.

Magnetic resonance imaging simulation with spin-lock preparations to detect tiny oscillatory magnetic fields

Spin-lock preparation was studied to detect tiny oscillatory magnetic fields such as a neural magnetic field without the blood oxygen level-dependent effect. This approach is a direct measurement and independent of static magnetic field strength. Accordingly, it is anticipated as a feasible functional magnetic resonance imaging (fMRI) in low and ultra-low-field MRI. Several reports have been published on spin-lock preparation but reports on imaging simulation are rare. Research in this area can assist in investigating magnetic resonance signal changes and, accordingly, can help to develop new spin-lock methods. In this study, we propose an imaging simulation method with an analytical solution using the Bloch equation. To demonstrate the feasibility of our proposed method, we compared simulated images with experimental results in which the number of sub-voxels and the amplitude and phase of the target oscillatory magnetic fields varied. In addition, we also applied graphics processing unit parallel computing and investigated the feasibility of avoiding an impracticable calculation time by doing so.

Automatic segmentation of white matter hyperintensities from brain magnetic resonance images in the era of deep learning and big data - A systematic review

BACKGROUND

White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin.

METHOD

We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2.

RESULTS

The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their methods in public repositories.

CONCLUSIONS

We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

Rotated Sphere Haar Wavelet and Deep Contractive Auto-Encoder Network With Fuzzy Gaussian SVM for Pilot's Pupil Center Detection

How to track the attention of the pilot is a huge challenge. We are able to capture the pupil status of the pilot and analyze their anomalies and judge the attention of the pilot. This paper proposes a new approach to solve this problem through the integration of spherical Haar wavelet transform and deep learning methods. First, considering the application limitations of Haar wavelet and other wavelets in spherical signal decomposition and reconstruction, a feature learning method based on the spherical Haar wavelet is proposed. In order to obtain the salient features of the spherical signal, a rotating spherical Haar wavelet is also proposed, which has a consistent scale in the same direction between the reconstructed image and the original image. Second, in order to find a better characteristic representation of the spherical signal, a higher contractive autoencoder (HCAE) is designed for the potential representation of the spherical Haar wavelet coefficients, which has two penalty items, respectively, from Jacobian and two order items from Taylor expansion of the point x for the contract learning of sample space. Third, in order to improve the classification performance, this paper proposes a fuzzy Gaussian support vector machine (FGSVM) as the top classification tool of the deep learning model, which can punish some Gaussian noise from the output of the deep HCAE network (DHCAEN). Finally, a DHCAEN-FGSVM classifier is proposed to identify the location of the pupil center. The experimental results of the public data set and actual data show that our model is an effective method for spherical signal detection.

Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding

Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a cube-based 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervised training. As 3D PET-CSC codes the whole 3D PET image, instead of patches, it alleviates the staircase artifacts commonly presented in traditional patch-based sparse coding methods. Compared with traditional coding methods in Fourier domain, the proposed method extends the 3D CSC to a straightforward approach based on the pursuit of localized cubes. Moreover, we developed the residual-image and order-subset mechanisms to further reduce the computational cost and accelerate the convergence for the proposed 3D PET-CSC method. Experiments based on computer simulations and clinical datasets demonstrate the superiority of 3D PET-CSC compared with other reference methods.

Bayesian non-linear regression with spatial priors for noise reduction and error estimation in quantitative MRI with an application in T1 estimation

PURPOSE

To develop a method that can reduce and estimate uncertainty in quantitative MR parameter maps without the need for hand-tuning of any hyperparameters.

METHODS

We present an estimation method where uncertainties are reduced by incorporating information on spatial correlations between neighbouring voxels. The method is based on a Bayesian hierarchical non-linear regression model, where the parameters of interest are sampled, using Markov chain Monte Carlo (MCMC), from a high-dimensional posterior distribution with a spatial prior. The degree to which the prior affects the model is determined by an automatic hyperparameter search using an information criterion and is, therefore, free from manual user-dependent tuning. The samples obtained further provide a convenient means to obtain uncertainties in both voxels and regions. The developed method was evaluated on T ₁ estimations based on the variable flip angle method.

RESULTS

The proposed method delivers noise-reduced T ₁ parameter maps with associated error estimates by combining MCMC sampling, the widely applicable information criterion, and total variation-based denoising. The proposed method results in an overall decrease in estimation error when compared to conventional voxel-wise maximum likelihood estimation. However, this comes with an increased bias in some regions, predominately at tissue interfaces, as well as an increase in computational time.

CONCLUSIONS

This study provides a method that generates more precise estimates compared to the conventional method, without incorporating user subjectivity, and with the added benefit of uncertainty estimation.

The Application of Deep Convolutional Neural Networks to Brain Cancer Images: A Survey

In recent years, improved deep learning techniques have been applied to biomedical image processing for the classification and segmentation of different tumors based on magnetic resonance imaging (MRI) and histopathological imaging (H&E) clinical information. Deep Convolutional Neural Networks (DCNNs) architectures include tens to hundreds of processing layers that can extract multiple levels of features in image-based data, which would be otherwise very difficult and time-consuming to be recognized and extracted by experts for classification of tumors into different tumor types, as well as segmentation of tumor images. This article summarizes the latest studies of deep learning techniques applied to three different kinds of brain cancer medical images (histology, magnetic resonance, and computed tomography) and highlights current challenges in the field for the broader applicability of DCNN in personalized brain cancer care by focusing on two main applications of DCNNs: classification and segmentation of brain cancer tumors images.

A Mechanistic Investigation into Ischemia-Driven Distal Recurrence of Glioblastoma

Glioblastoma (GBM) is the most aggressive primary brain tumor with a short median survival. Tumor recurrence is a clinical expectation of this disease and usually occurs along the resection cavity wall. However, previous clinical observations have suggested that in cases of ischemia following surgery, tumors are more likely to recur distally. Through the use of a previously established mechanistic model of GBM, the Proliferation Invasion Hypoxia Necrosis Angiogenesis (PIHNA) model, we explore the phenotypic drivers of this observed behavior. We have extended the PIHNA model to include a new nutrient-based vascular efficiency term that encodes the ability of local vasculature to provide nutrients to the simulated tumor. The extended model suggests sensitivity to a hypoxic microenvironment and the inherent migration and proliferation rates of the tumor cells are key factors that drive distal recurrence.

A Modified Higher-Order Singular Value Decomposition Framework With Adaptive Multilinear Tensor Rank Approximation for Three-Dimensional Magnetic Resonance Rician Noise Removal

The magnetic resonance (MR) images are acknowledged to be inevitably corrupted by Rician distributed noise, which adversely affected the image quality for diagnosis purpose. However, the traditional denoising methods may recover the images from corruptions with severe loss of detailed structure and edge information, which would affect the lesion detections and diagnostic decision making. In this study, we challenged improving the Rician noise removal from three-dimensional (3D) MR volumetric data through a modified higher-order singular value decomposition (MHOSVD) method. The proposed framework of MHOSVD involved a parameterized logarithmic nonconvex penalty function for low-rank tensor approximation (LRTA) algorithm optimization to suppress the image noise in MR dataset. Reference cubes were extracted from the noisy image volume, and block matching was performed according to nonlocal similarity for a fourth-order tensor construction. Then the LRTA problem was implemented by tensor factorization approaches, and the ranks of unfolding matrices along different modes of the tensor were estimated utilizing an adaptive nonconvex low-rank method. The denoised MR images were finally restored through aggregating all recovered cubes. We investigated the proposed algorithm MHOSVD on both the synthetic and real clinic 3D MR images for Rician noise removal, and relative results demonstrated that the MHOSVD can recover images with fine structures and detailed edge preservation with heavy noise even as high as 15% of the maximum intensity. The experimental results were also compared along with several classical denoising methods; the MHOSVD exhibited a sufficient improvement in noise-removal performance at various noise conditions in terms of different measurement indices such as peak signal-to-noise ratio and structural similarity index metrics. Based upon the comparison, the proposed MHOSVD has proved a relative state-of-the-art performance with excellent detailed structure reservation.

Image Denoising Using Non-Local Means (NLM) Approach in Magnetic Resonance (MR) Imaging: A Systematic Review

The non-local means (NLM) noise reduction algorithm is well known as an excellent technique for removing noise from a magnetic resonance (MR) image to improve the diagnostic accuracy. In this study, we undertook a systematic review to determine the effectiveness of the NLM noise reduction algorithm in MR imaging. A systematic literature search was conducted of three databases of publications dating from January 2000 to March 2020; of the 82 publications reviewed, 25 were included in this study. The subjects were categorized into four major frameworks and analyzed for each research result. Research in NLM noise reduction for MR images has been increasing worldwide; however, it was found to have slightly decreased since 2016. It was found that the NLM technique was most frequently used on brain images taken using the general MR imaging technique; these were most frequently performed during simultaneous real and simulated experimental studies. In particular, comparison parameters were frequently used to evaluate the effectiveness of the algorithm on MR images. The ultimate goal is to provide an accurate method for the diagnosis of disease, and our conclusion is that the NLM noise reduction algorithm is a promising method of achieving this goal.

Development of a method for the Bloch image simulation of biological tissues

PURPOSE

The purpose of this study is to develop a method for the Bloch image simulation of biological tissues including various chemical components and T₂* distribution.

METHODS

The nuclear spins in the object material were modeled as a spectral intensity function Sr→ω defined by superposition of Lorentz functions with various central precession frequencies and the half width of 1/(πT₂'), where 1/T₂' is a relaxation rate attributable to microscopic field inhomogeneity in a voxel. Four-dimensional numerical phantoms were created to simulate Sr→ω and used for MRI simulations of the phantoms containing water and fat protons. Single slice multiple (16) gradient-echo sequences (ΔTE = 2.2 and 1.384 ms) were used for experiments at 1.5 T and 3 T and MRI simulations to evaluate the validity of the approach.

RESULTS

Experimentally measured image intensities of the multiple gradient-echo imaging sequences were well reproduced by the MRI simulations. The correlation coefficients between the experimentally measured image intensities and those numerically simulated were 0.9895 to 0.9992 for the 4-component phantom at 1.5 T and 0.9580 to 0.9996 for the 7-component phantom at 3 T.

CONCLUSION

T₂* and chemical shift effects were successfully implemented in the MRI simulator (BlochSolver). Because this approach can be applied to other MRI simulators, the method developed in this study is useful for MRI simulation of biological tissues containing water and fat protons.

Semantic segmentation of cerebrospinal fluid and brain volume with a convolutional neural network in pediatric hydrocephalus-transfer learning from existing algorithms

Background

For the segmentation of medical imaging data, a multitude of precise but very specific algorithms exist. In previous studies, we investigated the possibility of segmenting MRI data to determine cerebrospinal fluid and brain volume using a classical machine learning algorithm. It demonstrated good clinical usability and a very accurate correlation of the volumes to the single area determination in a reproducible axial layer. This study aims to investigate whether these established segmentation algorithms can be transferred to new, more generalizable deep learning algorithms employing an extended transfer learning procedure and whether medically meaningful segmentation is possible.

Methods

Ninety-five routinely performed true FISP MRI sequences were retrospectively analyzed in 43 patients with pediatric hydrocephalus. Using a freely available and clinically established segmentation algorithm based on a hidden Markov random field model, four classes of segmentation (brain, cerebrospinal fluid (CSF), background, and tissue) were generated. Fifty-nine randomly selected data sets (10,432 slices) were used as a training data set. Images were augmented for contrast, brightness, and random left/right and X/Y translation. A convolutional neural network (CNN) for semantic image segmentation composed of an encoder and corresponding decoder subnetwork was set up. The network was pre-initialized with layers and weights from a pre-trained VGG 16 model. Following the network was trained with the labeled image data set. A validation data set of 18 scans (3289 slices) was used to monitor the performance as the deep CNN trained. The classification results were tested on 18 randomly allocated labeled data sets (3319 slices) and on a T2-weighted BrainWeb data set with known ground truth.

Results

The segmentation of clinical test data provided reliable results (global accuracy 0.90, Dice coefficient 0.86), while the CNN segmentation of data from the BrainWeb data set showed comparable results (global accuracy 0.89, Dice coefficient 0.84). The segmentation of the BrainWeb data set with the classical FAST algorithm produced consistent findings (global accuracy 0.90, Dice coefficient 0.87). Likewise, the area development of brain and CSF in the long-term clinical course of three patients was presented.

Conclusion

Using the presented methods, we showed that conventional segmentation algorithms can be transferred to new advances in deep learning with comparable accuracy, generating a large number of training data sets with relatively little effort. A clinically meaningful segmentation possibility was demonstrated.

Multiswarm Artificial Bee Colony algorithm based on spark cloud computing platform for medical image registration

BACKGROUND

Over the years, medical image registration has been widely used in various fields. However, different application characteristics, such as scale, computational complexity, and optimization goals, can cause problems. Therefore, developing an optimization algorithm based on clustering calculation is crucial.

METHOD

To solve the aforementioned problem, a multiswarm artificial bee colony (MS-ABC) multi-objective optimization algorithm based on clustering calculation is proposed. This algorithm can accelerate the resolution of complex problems on the Spark platform. Experiments show that the algorithm can optimize certain conventional complex problems and perform medical image registration tests.

RESULT

Results show that the MS-ABC algorithm demonstrates excellent performance in medical image registration tests. The optimization results of the MS-ABC algorithm for conventional problems are similar to those of existing algorithms; however, its performance is more time efficient for complex problems, especially when additional goals are needed.

CONCLUSION

The MS-ABC algorithm is applied to the Spark platform to accelerate the resolution of complex application problems. It can solve the problem of traditional algorithms regarding long calculation time, especially in the case of highly complex and large amounts of data, which can substantially improve data-processing efficiency.

Incremental Dilations Using CNN for Brain Tumor Classification

Brain tumor classification is a challenging task in the field of medical image processing. Technology has now enabled medical doctors to have additional aid for diagnosis. We aim to classify brain tumors using MRI images, which were collected from anonymous patients and artificial brain simulators. In this article, we carry out a comparative study between Simple Artificial Neural Networks with dropout, Basic Convolutional Neural Networks (CNN), and Dilated Convolutional Neural Networks. The experimental results shed light on the high classification performance (accuracy 97%) of Dilated CNN. On the other hand, Dilated CNN suffers from the gridding phenomenon. An incremental, even number dilation rate takes advantage of the reduced computational overhead and also overcomes the adverse effects of gridding. Comparative analysis between different combinations of dilation rates for the different convolution layers, help validate the results. The computational overhead in terms of efficiency for training the model to reach an acceptable threshold accuracy of 90% is another parameter to compare the model performance.

Virtual clinical trials in medical imaging: a review

The accelerating complexity and variety of medical imaging devices and methods have outpaced the ability to evaluate and optimize their design and clinical use. This is a significant and increasing challenge for both scientific investigations and clinical applications. Evaluations would ideally be done using clinical imaging trials. These experiments, however, are often not practical due to ethical limitations, expense, time requirements, or lack of ground truth. Virtual clinical trials (VCTs) (also known as in silico imaging trials or virtual imaging trials) offer an alternative means to efficiently evaluate medical imaging technologies virtually. They do so by simulating the patients, imaging systems, and interpreters. The field of VCTs has been constantly advanced over the past decades in multiple areas. We summarize the major developments and current status of the field of VCTs in medical imaging. We review the core components of a VCT: computational phantoms, simulators of different imaging modalities, and interpretation models. We also highlight some of the applications of VCTs across various imaging modalities.