Brain Magnetic Resonance Imaging Images Research Articles

Clinical evaluation of super-resolution for brain MRI images based on generative adversarial networks

In magnetic resonance imaging (MRI), reducing long scan times is an urgent issue that could be addressed with super-resolution (SR) techniques. Most of the SR networks using deep neural networks (DNNs) have been evaluated only based on numeric metrics, and the image restoration quality for individual lesions is not evaluated sufficiently. Here, we evaluated the performances of different types of SR networks using DNNs for brain MRI, in terms of diagnostic performance and image quality. We focused on comparing the performance between generative adversarial networks (GANs) and non-GAN networks. There was a trade-off in such restoration quality between GAN- and non-GAN-based SRs, with the GANs being more accurate in restoring images of anatomical structures but less accurate in restoring those of lesions; non-GANs showed the opposite tendency. The non-GAN SRs were preferable in terms of diagnostic performance and image quality. This result suggested that the evaluation of DNN performance for lesions might be changed drastically by adding a clinical evaluation perspective. The dependence of network architecture on network performance obtained in this study will provide guidance for future development of SR DNN for medical images.

Denoising of Images Using Deep Convolutional Autoencoders for Brain Tumor Classification

In the acquisition of images of the human body, medical imaging devices are crucial. The Magnetic Resonance Imaging (MRI) system detects tissue anomalies and tumours in the body of people. During the forming process, the MRI images are degraded by different kind of noises. It is difficult to remove certain noises, accompanied by the segmentation of images in order to classify anomalies. The most commonly explored areas of this period are automatic tumour detection systems using Magnetic Resonance Imaging. In the medical sector, timely and exact identification of frequencies is a problem. Automated systems are efficient that reduce human errors when tumour is detected. In recent years, many approaches have been proposed to do this, but there are still several drawbacks and a wide range of improvements on these methodologies are still needed. The image processing mechanism is widely used to improve early detection and treatment stages in the field of medical sciences. Sometimes the doctor can misdiagnose the image of MRI because of noise levels. To date, Deep Convolution Neural Networks (DCNN) have demonstrated excellent classification and segmentation efficiency. This paper proposes a technique for the image denoising using DCNN based Auto Encoders (DCNNAE) for achieving better accuracy rates in brain tumour prediction. In this paper we propose a deep convolution denoising auto encoder to remove noise from images and over fit the model problem by developing a deep convolution neural network for brain MRI image tumour prediction. The proposed model is compared with the existing methods and the results exhibits that the proposed model performance levels are better than the existing ones.

Adjacent slices feature transformer network for single anisotropic 3D brain MRI image super-resolution

Magnetic resonance imaging (MRI) is widely used in clinical applications. However, due to the limitations in signal-to-noise ratio, physical properties of the scanner and scanning time, MRI images are usually acquired in low resolution, which restrains the accuracy of segmentation and recognition tasks. Recently, convolutional neural network (CNN) super-resolution methods have shown great potential in improving the resolution of MRI. Unfortunately, current methods neglect the data continuity and prior information of MRI images. In this paper, we handle the anisotropic 3D brain MRI images SR task as the problem of inserting new slices between adjacent in-plane slices. Then, we propose a novel adjacent slices feature transformer (ASFT) network to utilize the similarity of adjacent slices. Specifically, the backbone of the ASFT network consists of a series of stacked multi-branch features transformation and extraction (MFTE) blocks. In each MFTE block, we construct new spatial attention to focus on features from specific areas in reference branches and use channel attention to enhance the most valuable information. In addition, we propose a hybrid loss function with content and gradient information to refine the pixels and structures of the reconstructed image. We also introduce global residual learning to reduce the difficulty of network training. Experimental results show that the ASFT network gains the PSNR of 43.68 dB, 40.96 dB, and 41.22 dB with the scale factor of ×2 on the public Kirby21, ANVIL-adult, and MSSEG datasets, respectively. When compared with state-of-the-art MRI SR methods, the ASFT network achieves superior quantitative and qualitative performance.

Risk Factors of Restroke in Patients with Lacunar Cerebral Infarction Using Magnetic Resonance Imaging Image Features under Deep Learning Algorithm.

This study was aimed to explore the magnetic resonance imaging (MRI) image features based on the fuzzy local information C-means clustering (FLICM) image segmentation method to analyze the risk factors of restroke in patients with lacunar infarction. In this study, based on the FLICM algorithm, the Canny edge detection algorithm and the Fourier shape descriptor were introduced to optimize the algorithm. The difference of Jaccard coefficient, Dice coefficient, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), running time, and segmentation accuracy of the optimized FLICM algorithm and other algorithms when the brain tissue MRI images were segmented was studied. 36 patients with lacunar infarction were selected as the research objects, and they were divided into a control group (no restroke, 20 cases) and a stroke group (restroke, 16 cases) according to whether the patients had restroke. The differences in MRI imaging characteristics of the two groups of patients were compared, and the risk factors for restroke in lacunar infarction were analyzed by logistic multivariate regression. The results showed that the Jaccard coefficient, Dice coefficient, PSNR value, and SSIM value of the optimized FLICM algorithm for segmenting brain tissue were all higher than those of other algorithms. The shortest running time was 26 s, and the highest accuracy rate was 97.86%. The proportion of patients with a history of hypertension, the proportion of patients with paraventricular white matter lesion (WML) score greater than 2 in the stroke group, the proportion of patients with a deep WML score of 2, and the average age of patients in the stroke group were much higher than those in the control group (P < 0.05). Logistic multivariate regression showed that age and history of hypertension were risk factors for restroke after lacunar infarction (P < 0.05). It showed that the optimized FLICM algorithm can effectively segment brain MRI images, and the risk factors for restroke in patients with lacunar infarction were age and hypertension history. This study could provide a reference for the diagnosis and prognosis of lacunar infarction.

18F]Fluoromethylcholine PET/CT for CNS lymphoma assessment: a new tool

Background Central nervous system (CNS) lymphomas are a rare subset of lymphoma, which are associated with a poor outcome. The gold standard for CNS imaging is with gadolinium-enhanced magnetic resonance imaging (MRI); however, there are a number of limitations, including some patients with small persistent abnormalities from scarring due to focal haemorrhage or from a previous biopsy, which can be difficult to discern from residual tumour. [18F]Fluoromethylcholine positron emission tomography–computed tomography (FCH-PET/CT) uses an analogue of choline, which due to the upregulation of choline kinase in tumour cells, allows increased uptake of FCH. As there is minimal background grey matter uptake of FCH, FCH-PET/CT can be used in CNS imaging and provide a useful tool for response assessment. Methods This is a cohort study, where we identified 40 patients with a diagnosis of primary or secondary CNS lymphoma between 1st November 2011 and 10th October 2019. Results 26 of the 40 patients (65%) had concordant results. Of the discordant results, 11 out of 14 had partial response (PR) on MRI but showed a metabolic complete response (mCR) on FCH-PET. The overall response rates (ORR) were similar between the two modalities (90% for MRI versus 95% with FCT-PET/CT). Conclusion We conclude that FCH-PET/CT is a reasonable alternative mode of imaging to gadolinium-enhanced MRI brain imaging, providing a new tool for assessment of CNS lymphoma.

Analisa Perbandingan Citra Hasil Segmentasi Menggunakan Metode K-Means dan Fuzzy C Means pada Citra Input Terkompresi

&lt;p&gt;&lt;em style="text-align: justify; text-indent: 14.2pt;"&gt;&lt;span style="font-family: 'Times New Roman',serif; mso-ansi-language: EN;" lang="EN"&gt;In pattern recognition, image processing plays a role in automatically separating objects from the background. In addition, the object will be processed by the pattern classifier. In the medical world, image processing plays a very important role. CT Scan (Computed Tomography) or CAT Scan (Computed Axial Tomography) is an example of an image processing application that can be used to view fragments or cross sections of parts of the human body. Tomography is the process of producing two-dimensional images from three-dimensional film through several one-dimensional scans. Magnetic resonance imaging (MRI) is the image most often used in the field of radiology. MRI images can display the anatomical details of objects clearly in multiple sections (multiplanar) without changing the patient's position. In this study, two methods were compared, namely K-Means and Fuzzy C Means, in a segmentation process with the aim of separating between normal areas or areas with disturbances (lesions). The images used are brain and chest MRI images with a total of 10 MRI images. The image quality of the segmentation results is compared with the quality test using the Variation of Information (VOI) parameters, Global Consistency Error (GCE), MSE (Mean Square Error), PSNR (Peak Signal to Noise Ratio) and segmentation time.&lt;/span&gt;&lt;/em&gt;&lt;/p&gt;&lt;pre style="text-align: justify; text-indent: 14.2pt;"&gt;&lt;em&gt;&lt;span style="font-family: 'Times New Roman',serif; mso-ansi-language: EN;" lang="EN"&gt;In pattern recognition, image processing plays a role in automatically separating objects from the background. In addition, the object will be processed by the pattern classifier. In the medical world, image processing plays a very important role. CT Scan (Computed Tomography) or CAT Scan (Computed Axial Tomography) is an example of an image processing application that can be used to view fragments or cross sections of parts of the human body. Tomography is the process of producing two-dimensional images from three-dimensional film through several one-dimensional scans. Magnetic resonance imaging (MRI) is the image most often used in the field of radiology. MRI images can display the anatomical details of objects clearly in multiple sections (multiplanar) without changing the patient's position. In this study, two methods were compared, namely K-Means and Fuzzy C Means, in a segmentation process with the aim of separating between normal areas or areas with disturbances (lesions). The images used are brain and chest MRI images with a total of 10 MRI images. The image quality of the segmentation results is compared with the quality test using the Variation of Information (VOI) parameters, Global Consistency Error (GCE), MSE (Mean Square Error), PSNR (Peak Signal to Noise Ratio) and segmentation time.&lt;/span&gt;&lt;/em&gt;&lt;/pre&gt;

Preoperative Magnetic Resonance Imaging Radiomics for Predicting Early Recurrence of Glioblastoma.

PurposeEarly recurrence of glioblastoma after standard treatment makes patient care challenging. This study aimed to assess preoperative magnetic resonance imaging (MRI) radiomics for predicting early recurrence of glioblastoma.Patients and MethodsA total of 122 patients (training cohort: n = 86; validation cohort: n = 36) with pathologically confirmed glioblastoma were included in this retrospective study. Preoperative brain MRI images were analyzed for both radiomics and the Visually Accessible Rembrandt Image (VASARI) features of glioblastoma. Models incorporating MRI radiomics, the VASARI parameters, and clinical variables were developed and presented in a nomogram. Performance was assessed based on calibration, discrimination, and clinical usefulness.ResultsThe nomogram consisting of the radiomic signatures, the VASARI parameters, and blood urea nitrogen (BUN) values showed good discrimination between the patients with early recurrence and those with later recurrence, with an area under the curve of 0.85 (95% CI, 0.77-0.94) in the training cohort and 0.84 [95% CI, 0.71-0.97] in the validation cohort. Decision curve analysis demonstrated favorable clinical application of the nomogram.ConclusionThis study showed the potential usefulness of preoperative brain MRI radiomics in predicting the early recurrence of glioblastoma, which should be helpful in personalized management of glioblastoma.

Generating Synthesized Computed Tomography (CT) from Magnetic Resonance Imaging Using Cycle-Consistent Generative Adversarial Network for Brain Tumor Radiation Therapy

<h3>Purpose/Objective(s)</h3> Brain tumor is the most common malignant tumor of the head and neck in China, postoperative radiotherapy is one of the main methods to improve the survival rate of patients. Magnetic resonance imaging (MRI) has the advantage of its soft tissue contrast, for the sake of getting the tumor boundary accurately, it is necessary to combine CT/MR image fusing in gross tumor volume (GTV) delineation. In order to avoid the uncertainty caused by multimodal images registration and reduce unnecessary radiation dose, replacing CT with MRI has become one of the research hotspots in the field of radiotherapy. The aim of this study was to use unregistered MRI and CT images from brain tumor patients to generate pseudo-CT images based on a cycle-consistent generative adversarial network (CycleGAN) framework. <h3>Materials/Methods</h3> T1, T2-weighted MRI and CT-simulation images of the whole brain were collected from 31 brain tumor patients. In this work, we have used a CycleGAN framework to generate pseudo-CT images from MRI, this model is capable of image-to-image translation using unpaired MRI and CT images in an unsupervised learning method. Due to the influence of head frame in CT-simulation images and the different scanning range, imaging resolution and contrast of each patient, preprocessing of MRI and CT images, such as clipping, background removal, resampling and normalization, was required firstly. Secondly, in order to compensate for the insufficient to separate all major tissue types by the single MR sequence, each patient's T1/T2-weighted MR image pair was served as the input of the CycleGAN framework after registering and fusing. Finally, a simple cross-validation study, randomly selecting 70% samples as the training set and the remaining images as the testing set, was performed to compare the quality of synthetic CT and real CT image. <h3>Results</h3> The CycleGAN method produced the overall average MAE below 0.24 ± 0.02 and the 0.79 ± 0.03 SSIM value for the testing set images, the heterogeneity between the synthetic CT image and the actual CT image was acceptable. <h3>Conclusion</h3> We successfully realized the image-to-image translation using unregistered MRI and CT images based on the CycleGAN framework. The evaluation of pseudo-CT image showed the feasibility and accuracy of this method, which can effectively reduce the error caused by multi-mode image registration in gross tumor volume (GTV) delineation for brain tumor patients.

Magnitude Normalized and OTSU Intensity based Brain Tumor Detection Using Magnetic Resonance Images

Brain tumor is a deadly disease and its categorization is challenging due to the diversified characteristics of tumor cells. Currently, computer-aided techniques for brain tumor identification in the early stages are proposed with magnetic resonance imaging (MRI). In recent pre-trained models, features are obtained from bottom layers that vary from natural images to medical images. Moreover, attributable to disequilibrium and complication of noise and intensity of these lesions of brain tumors in MRI is yet considered to be the laborious strategy. To resolve these issues, an intensity-based segmentation method called, Magnitude Normalized Filtering and Otsu Intensity-based segmentation (MNF-OIS) is utilized. First, with the Brain MRI images provided as input, normalized pre-processed images are obtained by utilizing the Magnitude Normalized Saddle Median Filtering model. Next, Otsu Intensity-based segmentation is applied to the pre-processed image to obtain Convergence optimized segmented image. With the resultant segmented image testing on brain MRI images are made for brain tumor identification. MNF-OIS method is evaluated in terms of tumor detection time, convergence time, and accuracy. The experimental outcomes verify that the MNF-OIS method improved brain tumor detection accuracy by 7%, reduced the convergence time by 22%, and minimized tumor detection time by 32% as compared to existing Deep learning convolutional neural networks and DeepSeg, respectively.

A brief report on incidence, radiographic feature and prognostic significance of brain MRI changes after anti-PD-1/PD-L1 therapy in advanced non-small cell lung cancer.

Neurologic immune-related adverse events (nirAEs) are uncommon but potentially lethal complications of immune checkpoint inhibitor (ICI) treatment. However, the incidence, radiographic features and prognostic significance of brain magnetic resonance imaging (MRI) changes after ICI treatment remain largely unknown. Consecutive patients with advanced non-small cell lung cancer (NSCLC) at three participating institutions receiving anti-PD-1/PD-L1 therapy from June 2017 to September 2020 were screened, and those who received brain MRI within 6weeks before ICI initiation and at least one follow-up brain MRI after ICI treatment were included. Serial brain MRI images were independently reviewed by two experienced radiologists. With a median follow-up of 13.2months, 27 (20.0%) of the 135 enrolled patients developed certain kind of brain MRI aberration. The 1-, 2- and 3-year cumulative incidence of brain MRI aberration was 17.1%, 36.3% and 52.2%, respectively. Brain MRI aberration indicative of stroke, mimicking typical white matter lesions and presenting as T2-hyperintensity suggestive of CNS vasculitis or encephalitis, was documented in 11, 9 and 4 patients, respectively. Patients with brain MRI aberration had higher clinical benefit rate (p = 0.030), longer progression-free survival (p = 0.015) and a tendency of improved overall survival (p = 0.054). Brain MRI aberrations developed after ICI treatment are not uncommon, and their manifestations vary a lot. Patients developing brain MRI aberrations tended to have better prognosis, which needed to be further investigated.

An Extended Fuzzy C-Means Segmentation for an Efficient BTD With the Region of Interest of SCP

Magnetic resonance imaging (MRI) is the primary source to diagnose a brain tumor or masses in the medical sciences. It is emerging to detect the tumors from the scanned MRI brain images at early stages for the best treatments. Existing image segmentation techniques, morphological, fuzzy c-means are wildly successful in the extraction region of interest (ROI) in brain image segmentation. Proper extraction of ROIs is useful for regularizing the regions of tumors from the brain image with effective binarization in the segmentation. However, the existing techniques are limiting the irregular boundaries or shapes in tumor segmentation. Thus, this paper presents the proposed work extending the FCM with the spatial correlated pixel (RSCP), known as FCM-RSCP. It overcomes the problem of irregular boundaries by assessing correlated spatial information during segmentation. Benchmarked MRI brain images are used in the experiment for demonstrating the efficiency of the proposed methodology.

Compression of MRI brain images based on automatic extraction of tumor region

In the compression of medical images, region of interest (ROI) based techniques seem to be promising, as they can result in high compression ratios while maintaining the quality of region of diagnostic importance, the ROI, when image is reconstructed. In this article, we propose a set-up for compression of brain magnetic resonance imaging (MRI) images based on automatic extraction of tumor. Our approach is to first separate the tumor, the ROI in our case, from brain image, using support vector machine (SVM) classification and region extraction step. Then, tumor region (ROI) is compressed using Arithmetic coding, a lossless compression technique. The non-tumorous region, non-region of interest (NROI), is compressed using a lossy compression technique formed by a combination of discrete wavelet transform (DWT), set partitioning in hierarchical trees (SPIHT) and arithmetic coding (AC). The classification performance parameters, like, dice coefficient, sensitivity, positive predictive value and accuracy are tabulated. In the case of compression, we report, performance parameters like mean square error and peak signal to noise ratio for a given set of bits per pixel (bpp) values. We found that the compression scheme considered in our setup gives promising results as compared to other schemes.

IAS-NET: Joint intraclassly adaptive GAN and segmentation network for unsupervised cross-domain in neonatal brain MRI segmentation.

In neonatal brain magnetic resonance image (MRI) segmentation, the model we trained on the training set (source domain) often performs poorly in clinical practice (target domain). As the label of target-domain images is unavailable, this cross-domain segmentation needs unsupervised domain adaptation (UDA) to make the model adapt to the target domain. However, the shape and intensity distribution of neonatal brain MRI images across the domains are largely different from adults'. Current UDA methods aim to make synthesized images similar to the target domain as a whole. But it is impossible to synthesize images with intraclass similarity because of the regional misalignment caused by the cross-domain difference. This will result in generating intraclassly incorrect intensity information from target-domain images. To address this issue, we propose an IAS-NET (joint intraclassly adaptive generative adversarial network (GAN) (IA-NET) and segmentation) framework to bridge the gap between the two domains for intraclassalignment. Our proposed IAS-NET is an elegant learning framework that transfers the appearance of images across the domains from both image and feature perspectives. It consists of the proposed IA-NET and a segmentation network (S-NET). The proposed IA-NET is a GAN-based adaptive network that contains one generator (including two encoders and one shared decoder) and four discriminators for cross-domain transfer. The two encoders are implemented to extract original image, mean, and variance features from source and target domains. The proposed local adaptive instance normalization algorithm is used to perform intraclass feature alignment to the target domain in the feature-map level. S-NET is a U-net structure network that is used to provide semantic constraint by a segmentation loss for the training of IA-NET. Meanwhile, it offers pseudo-label images for calculating intraclass features of the target domain. Source code (in Tensorflow) is available at https://github.com/lb-whu/RAS-NET/. Extensive experiments are carried out on two different data sets (NeoBrainS12 and dHCP), respectively. There exist great differences in the shape, size, and intensity distribution of magnetic resonance (MR) images in the two databases. Compared to baseline, we improve the average dice score of all tissues on NeoBrains12 by 6% through adaptive training with unlabeled dHCP images. Besides, we also conduct experiments on dHCP and improved the average dice score by 4%. The quantitative analysis of the mean and variance of the synthesized images shows that the synthesized image by the proposed is closer to the target domain both in the full brain or within each class than that of the comparedmethods. In this paper, the proposed IAS-NET can improve the performance of the S-NET effectively by its intraclass feature alignment in the target domain. Compared to the current UDA methods, the synthesized images by IAS-NET are more intraclassly similar to the target domain for neonatal brain MR images. Therefore, it achieves state-of-the-art results in the compared UDA models for the segmentation task.

Adaptive Removal of high-density salt-and-pepper noise (ARSPN) for robust ROI detection used in watermarking of MRI images of the brain

This paper presents a novel window-based method to remove high-density salt-and-pepper noise for optimal ROI (Region Of Interest) detection of brain MRI (Magnetic Resonance Imaging) images. The output of this system is used in watermarking and extracting hidden data in this type of image. In this method, for each pixel of the noisy input image, an adaptive n × n window is considered in the neighborhood of that pixel. If they are not noisy, the pixels of this window are weighted according to their distance from the desired pixel, and the weighted sum of the neighboring pixels is averaged. Then the noisy pixel replaces with the resulting value. This paper consists of three main sections: ROI detection, noise removal block, and evaluation of the proposed method against different densities of salt-and-pepper noise in the range of 1%–98%. ROI obtained by this method is the same before and after the noise. The final image has an acceptable PSNR (Peak Signal-to-Noise Ratio) for noise with various densities. Based on the experimental results obtained by the high efficient proposed noise removal method using 208 images from seven Databases (DBs), the maximum value is 61.7% for the 1% noise density and 26.4% for the 98% noise density.

Nature-inspired solution for coronavirus disease detection and its impact on existing healthcare systems

Coronavirus is an infectious life-threatening disease and is mainly transmitted through infected person coughs, sneezes, or exhales. This disease is a global challenge that demands advanced solutions to address multiple dimensions of this pandemic for health and wellbeing. Different types of medical and technological-based solutions have been proposed to control and treat COVID-19. Machine learning is one of the technologies used in Magnetic Resonance Imaging (MRI) classification whereas nature-inspired algorithms are also adopted for image optimization. In this paper, we combined the machine learning and nature-inspired algorithm for brain MRI images of COVID-19 patients namely Machine Learning and Nature Inspired Model for Coronavirus (MLNI-COVID-19). This model improves the MRI image classification and optimization for better diagnosis. This model will improve the overall performance especially the area of brain images that is neglected due to the unavailability of the dataset. COVID-19 has a serious impact on the patient brain. The proposed model will help to improve the diagnosis process for better medical decisions and performance. The proposed model is evaluated with existing algorithms and achieved better performance in terms of sensitivity, specificity, and accuracy.

Diagnosis of Alzheimer’s Disease Based on the Modified Tresnet

In the medical field, Alzheimer’s disease (AD), as a neurodegenerative brain disease which is very difficult to diagnose, can cause cognitive impairment and memory decline. Many existing works include a variety of clinical neurological and psychological examinations, especially computer-aided diagnosis (CAD) methods based on electroencephalographic (EEG) recording or MRI images by using machine learning (ML) combined with different preprocessing steps such as hippocampus shape analysis, fusion of embedded features, and so on, where EEG dataset used for AD diagnosis is usually is large and complex, requiring extraction of a series of features like entropy features, spectral feature, etc., and it has seldom been applied in the AD detection based on deep learning (DL), while MRI images were suitable for both ML and DL. In terms of the structural MRI brain images, few differences could be found in brain atrophy among the three situations: AD, mild cognitive impairment (MCI), and Normal Control (NC). On the other hand, DL methods have been used to diagnose AD incorporating MRI images in recent years, but there have not yet been many selective models with very deep layers. In this article, the Gray Matter (GM) Magnetic Resonance Imaging (MRI) is automatically extracted, which could better distinguish among the three types of situations like AD, MCI, and NC, compared with Cerebro Spinal Fluid (CSF) and White Matter (WM). Firstly, FMRIB Software Library (FSL) software is utilized for batch processing to remove the skull, cerebellum and register the heterogeneous images, and the SPM + cat12 tool kits in MATLAB is used to segment MRI images for obtaining the standard GM MRI images. Next, the GM MRI images are trained by some new neural networks. The characteristics of the training process are as follows: (1) The Tresnet, as the network that achieves the best classification effect among several new networks in the experiment, is selected as the basic network. (2) A multi-receptive-field mechanism is integrated into the network, which is inspired by neurons that can dynamically adjust the receptive fields according to different stimuli. (3) The whole network is realized by adding multiple channels to the convolutional layer, and the size of the convolution kernel of each channel can be dynamically adjusted. (4) Transfer learning method is used to train the model for speeding up the learning and optimizing the learning efficiency. Finally, we achieve the accuracies of 86.9% for AD vs. NC, 63.2% for AD vs. MCI vs. NC respectively, which outperform the previous approaches. The results demonstrate the effectiveness of our approach.

Fuzzy System Based Medical Image Processing for Brain Disease Prediction.

The present work aims to explore the performance of fuzzy system-based medical image processing for predicting the brain disease. The imaging mechanism of NMR (Nuclear Magnetic Resonance) and the complexity of human brain tissues cause the brain MRI (Magnetic Resonance Imaging) images to present varying degrees of noise, weak boundaries, and artifacts. Hence, improvements are made over the fuzzy clustering algorithm. A brain image processing and brain disease diagnosis prediction model is designed based on improved fuzzy clustering and HPU-Net (Hybrid Pyramid U-Net Model for Brain Tumor Segmentation) to ensure the model safety performance. Brain MRI images collected from a Hospital, are employed in simulation experiments to validate the performance of the proposed algorithm. Moreover, CNN (Convolutional Neural Network), RNN (Recurrent Neural Network), FCM (Fuzzy C-Means), LDCFCM (Local Density Clustering Fuzzy C-Means), and AFCM (Adaptive Fuzzy C-Means) are included in simulation experiments for performance comparison. Results demonstrate that the proposed algorithm has more nodes, lower energy consumption, and more stable changes than other models under the same conditions. Regarding the overall network performance, the proposed algorithm can complete the data transmission tasks the fastest, basically maintaining at about 4.5 s on average, which performs remarkably better than other models. A further prediction performance analysis reveals that the proposed algorithm provides the highest prediction accuracy for the Whole Tumor under DSC (Dice Similarity Coefficient), reaching 0.936. Besides, its Jaccard coefficient is 0.845, proving its superior segmentation accuracy over other models. In a word, the proposed algorithm can provide higher accuracy, a more apparent denoising effect, and the best segmentation and recognition effect than other models while ensuring energy consumption. The results can provide an experimental basis for the feature recognition and predictive diagnosis of brain images.

Performance Comparison of Different Pre-Trained Deep Learning Models in Classifying Brain MRI Images

A brain tumor is a collection of abnormal cells formed as a result of uncontrolled cell division. If tumors are not diagnosed in a timely and accurate manner, they can cause fatal consequences. One of the commonly used techniques to detect brain tumors is magnetic resonance imaging (MRI). MRI provides easy detection of abnormalities in the brain with its high resolution. MR images have traditionally been studied and interpreted by radiologists. However, with the development of technology, it becomes more difficult to interpret large amounts of data produced in reasonable periods. Therefore, the development of computerized semi-automatic or automatic methods has become an important research topic. Machine learning methods that can predict by learning from data are widely used in this field. However, the extraction of image features requires special engineering in the machine learning process. Deep learning, a sub-branch of machine learning, allows us to automatically discover the complex hierarchy in the data and eliminates the limitations of machine learning. Transfer learning is to transfer the knowledge of a pre-trained neural network to a similar model in case of limited training data or the goal of reducing the workload. In this study, the performance of the pre-trained Vgg-16, ResNet50, Inception v3 models in classifying 253 brain MR images were evaluated. The Vgg-16 model showed the highest success with 94.42% accuracy, 83.86% recall, 100% precision and 91.22% F1 score. This was followed by the ResNet50 model with an accuracy of 82.49%.The findings obtained in this study were compared with similar studies in the literature and it was found that it showed higher success than most studies.

Fusion of Higher Order Spectra and Texture Extraction Methods for Automated Stroke Severity Classification with MRI Images

This paper presents a scientific foundation for automated stroke severity classification. We have constructed and assessed a system which extracts diagnostically relevant information from Magnetic Resonance Imaging (MRI) images. The design was based on 267 images that show the brain from individual subjects after stroke. They were labeled as either Lacunar Syndrome (LACS), Partial Anterior Circulation Syndrome (PACS), or Total Anterior Circulation Stroke (TACS). The labels indicate different physiological processes which manifest themselves in distinct image texture. The processing system was tasked with extracting texture information that could be used to classify a brain MRI image from a stroke survivor into either LACS, PACS, or TACS. We analyzed 6475 features that were obtained with Gray-Level Run Length Matrix (GLRLM), Higher Order Spectra (HOS), as well as a combination of Discrete Wavelet Transform (DWT) and Gray-Level Co-occurrence Matrix (GLCM) methods. The resulting features were ranked based on the p-value extracted with the Analysis Of Variance (ANOVA) algorithm. The ranked features were used to train and test four types of Support Vector Machine (SVM) classification algorithms according to the rules of 10-fold cross-validation. We found that SVM with Radial Basis Function (RBF) kernel achieves: Accuracy (ACC) = 93.62%, Specificity (SPE) = 95.91%, Sensitivity (SEN) = 92.44%, and Dice-score = 0.95. These results indicate that computer aided stroke severity diagnosis support is possible. Such systems might lead to progress in stroke diagnosis by enabling healthcare professionals to improve diagnosis and management of stroke patients with the same resources.

Fuzzy Clustering Algorithm-Segmented MRI Images in Analysis of Effects of Mental Imagery on Neurorehabilitation of Stroke Patients

The study focused on the automatic segmentation of Magnetic Resonance Imaging (MRI) images of stroke patients and the therapeutic effects of Mental Imagery on motor and neurological functions after stroke. First, the traditional fuzzy c-means (FCM) algorithm was optimized, and the optimized one was defined as filter-based FCM (FBFCM). 62 stroke patients were selected as the research subjects and randomly divided into the experimental group and the control group. The control group accepted the conventional rehabilitation training, and the experimental group accepted Mental Imagery on the basis of the control group. They all had the MRI examination, and their brain MRI images were segmented by the FBFCM algorithm. The MRI images before and after treatment were analyzed to evaluate the therapeutic effects of Mental Imagery on patients with motor and nerve dysfunction after stroke. The results showed that the segmentation coefficient of the FBFCM algorithm was 0.9315 and the segmentation entropy was 0.1098, which were significantly different from those of the traditional fuzzy c-means (FCM) algorithm. ( P &lt; 0.05 ), suggesting that the FBFCM algorithm had good segmentation effects on brain MRI images of stroke patients. After Mental Imagery, it was found that the patient’s Function Independent Measure (FIM) score was 99.04 ± 8.19, the Modified Barthel Index (MBI) score was 51.29 ± 4.35, the Fugl-Meyer (FMA) score was 61.01 ± 4.16, the neurological deficit degree in stroke (NFDS) score was 11.48 ± 2.01, the NIH Stroke Scale (NIHSS) score was 10.36 ± 1.69, and the clinical effective rate was 87.1%, all significantly different from those of the conventional rehabilitation training group ( P &lt; 0.05 ). Additionally, the brain area activated by Mental Imagery was more extensive. In conclusion, the FBFCM algorithm demonstrates superb capabilities in segmenting MRI images of stroke patients and is worth promotion in clinic. Mental Imagery can promote the neurological rehabilitation of patients by activating relevant brain areas of patients.