A new brain MRI image segmentation strategy based on wavelet transform and K-means clustering

Brain Magnetic Resonance Imaging (MRI) image segmentation is one of the critical technologies of clinical medicine, and is the basis of three-dimensional reconstruction and downstream analysis between normal tissues and diseased tissues. However, there are various limitations in brain MRI images, such as gray irregularities, noise, and low contrast, reducing the accuracy of the brain MRI images segmentation. In this paper, we propose two optimization solutions for the fuzzy clustering algorithm based on local Gaussian probability fuzzy C-means (LGP-FCM) model and anisotropic weight fuzzy C-means (AW-FCM) model and apply it in brain MRI image segmentation. An FCM clustering algorithm is proposed based on AW-FCM. By introducing the new neighborhood weight calculation method, each point has the weight of anisotropy, effectively overcomes the influence of noise on the image segmentation. In addition, the LGP model is introduced in the objective function of fuzzy clustering, and a fuzzy clustering segmentation algorithm based on LGP-FCM is proposed. A clustering segmentation algorithm of adaptive scale fuzzy LGP model is proposed. The neighborhood scale corresponding to each pixel in the image is automatically estimated, which improves the robustness of the model and achieves the purpose of precise segmentation. Extensive experimental results demonstrate that the proposed LGP-FCM algorithm outperforms comparison algorithms in terms of sensitivity, specificity and accuracy. LGP-FCM can effectively segment the target regions from brain MRI images.

For the problem of low accuracy by the traditional K-means clustering algorithm to segment noised brain magnetic resonance imaging (MRI) images. This paper proposed an improved K-means algorithm. The traditional K-means algorithm only considers the brain image gray value itself, ignoring the relationship between pixels. Due to the characteristics of brain MRI image adjacent pixels most likely belonging to the same class, this paper adopts average value of small neighborhood of each image pixel and image gray value to compose a new sample point, in order to reduce the impact of noise on the clustering accuracy. Experimental results show that the improved K-means algorithm can effectively improve the segmentation accuracy of the noised brain MRI image.

In order to improve the accuracy of brain magnetic resonance imaging (MRI) classification and to reduce classification time, this paper proposes a brain MRI image classification algorithm combined with transfer learning and support vector machine (SVM). Firstly, the three deep convolutional neural networks pre-trained on the ImageNet database, AlexNet, VGG16 and GoogleNet, are used as feature extractors to extract the features of brain MRI images in the Harvard Medical School Website database. The feature extraction process does not require to fine-tune the transferred networks. Then, the features extracted in each convolutional neural network are combined to form a feature vector of each brain MRI image and it is input to the SVM for classification. Finally the SVM classified the brain MRI images into healthy, Alzheimer's disease, and stroke. The experimental results show that the classification accuracy can achieve 100%, and the classification time is only 26 seconds. Compared with the brain MRI image classification algorithm proposed by the literature, the accuracy of the proposed method is increased by 8.67%, 1.09%, 0.55%, respectively. The proposed method can provide effective help for the diagnosis of brain diseases.

A Parkinson's disease-related nuclei segmentation network based on CNN-Transformer interleaved encoder with feature fusion.

In this paper, we presented precise and proficient techniques for measuring the human thalamus, medial dorsal and the pulvinar nucleus with magnetic resonance imaging (MRI). In spite of the fact that thalamic nuclei are not straightforwardly visible on traditional MRI image. We applied a novel and competent image pre-processing techniques to enhance the visual quality of MRI image. In addition to this we have used various segmentation algorithms to accurately extract entire thalamus from brain MRI images. Diffusion MRI is used to extract various nucleus of thalamus. Several optimal features such as textures, morphological are derived from thalamus and medial dorsal regions which are then used to train the artificial neural network model (ANN). Our artificial neural network model accurately classifies between schizophrenic and healthy subjects based on thalamic anatomy for larger sample sizes.

Rationale:Brain magnetic resonance imaging (MRI) images of atypical teratoid rhabdoid tumor (ATRT) often present heterogeneous signals of various cells without remarkable features of the disease. We describe a unique case of atypical brain MRI images presenting as an type II neurofibromatosis and explore some diagnostic hints.Patient concerns:A 1-year-and-7-month-old boy admitted to our department with a 7-day history of drowsiness and 2-day history of emesis, and his presenting complaint was repeated vomit. On physical examination, he had drowsiness, positive sun set sign, slow light reflection, high muscular tension of limbs and 55 cm head circumference. MRI presented masses of bilateral auditory nerve distribution area, the fourth ventricle and right frontal lobe, obstructive hydrocephalus, and amplified cisterna magna. Particularly, dumbbell shape tumor in left cerebellopontine angle area and the fourth ventricle showed iso- or hypo-intensity on T1-weighted image and mix-intensity on T2-weighted image with irregular frontier, obvious mutual high and low signal on T2-weighted image, and growing along cerebrospinal fluid pathway.Diagnosis:The diagnosis of type II neurofibromatosis (NF-II) was considered pre-operatively. After surgery, postoperative histopathology confirmed the diagnosis of ATRT.Interventions:After ventriculo-peritoneal (VP) shunt, no evidence of tumor was inspected in cerebrospinal fluid, and enhancement MRI showed heterogeneous contrast signal on dumbbell shape tumor. We executed an incomplete microsurgery for dumbbell shape lesion in left auditory nerve distribution area and the fourth ventricle for differential diagnosis and facilitating further treatment.Outcomes:The patient did not recover well postoperatively and suffered from severe pulmonary infection. Refusing further intervention in view of poor prognosis of ATRT, the patient was transferred to another hospital for rehabilitation care. The patient died from progressive tumor and respiratory failure after 2 months.Lessons:The diagnosis of ATRT can be challenging, in our case due to the disturbance of bilateral auditory nerve distribution area tumors. Under MRI, Irregular frontier, obvious mutual high and low signal on T2-weighted image, growing along cerebrospinal fluid pathway, and heterogeneous contrast enhancement should lead the clinician to strongly consider ATRT.

Nowadays, sparse representation has been widely used in Magnetic Resonance Imaging (MRI). The commonly used sparse representation methods are based on symmetrical partition, which have not considered the complex structure of MRI image. In this paper, we proposed a sparse representation method for the brain MRI image, called GNAMlet transform, which is based on the gradient information and the non-symmetry and anti-packing model. The proposed sparse representation method can reduce the lost detail information, improving the reconstruction accuracy. The experiment results show the superiority of the proposed transform for the brain MRI image representation in comparison with some state-of-the-art sparse representation methods.

The location of the tumor, the evaluation of its shape, its position and its interactions with nearby brain structures, etc. are signs and desired indicators. Nowadays clinical tools for in vivo observation areas of the brain such as X-ray scanner, the magnetic resonance imaging (MRI) et., are numerous. Among these techniques, MRI is increasingly used in clinical routine. The image allows precise localization of different structures. However, observation and tumor image analysis prove to be a delicate exercise that requires to use multiple acquisitions under different protocols. In this article we present a new method for detecting and extracting tumor regions applied on brain MRI images. This method consists of three main stages: (i) Extracting the region of interest (the brain) by using the EMBE method. (ii) to study and to make an histogram analysis of the MRI image in order to create learning and initialize the classification algorithm for retrieving and locating the tumor. (iii) Detection and extraction of the tumor, by using by the classification algorithm “Support Vector Machine”. The image will be split into two components which are Tumor class and No-tumor class. Our method will be completed by a characterization of the tumor area to specify its geometric properties. This work will help the radiologists in handling the numerous number of MRI images they have to deal daily. Our contribution will facilitate tumor detection and extraction in a most minimal time.

Recently, the Magnetic Resonance Imaging (MRI) images have limited and unsatisfactory resolutions due to various constraints such as physical, technological and economic considerations. Super-resolution techniques can obtain high-resolution MRI images. The traditional methods obtained the resolution enhancement of brain MRI by interpolations, affecting the accuracy of the following diagnose process. The requirement for brain image quality is fast increasing. In this paper, we propose an image super-resolution (SR) method based on overcomplete dictionaries and inherent similarity of an image to recover the high-resolution (HR) image from a single low-resolution (LR) image. We explore the nonlocal similarity of the image to tentatively search for similar blocks in the whole image and present a joint reconstruction method based on compressive sensing (CS) and similarity constraints. The sparsity and self-similarity of the image blocks are taken as the constraints. The proposed method is summarized in the following steps. First, a dictionary classification method based on the measurement domain is presented. The image blocks are classified into smooth, texture and edge parts by analyzing their features in the measurement domain. Then, the corresponding dictionaries are trained using the classified image blocks. Equally important, in the reconstruction part, we use the CS reconstruction method to recover the HR brain MRI image, considering both nonlocal similarity and the sparsity of an image as the constraints. This method performs better both visually and quantitatively than some existing methods.

In recent years, brain health has received increasing attention, but conventional acquisition of brain MRI (magnetic resonance imaging) images still suffer from issues such as missing data, artifacts, and high costs, which hinders research and diagnosis. With the application of deep learning in medical image synthesis, low-cost, efficient, and high-quality medical MRI synthesis techniques have become a prominent research focus and have gradually matured. However, traditional methods for synthesizing magnetic resonance imaging (MRI) mostly rely on generative adversarial networks, which require fine-tuning of parameters and learning rates to achieve stringent Nash equilibrium conditions, leading to problems such as gradient explosions and mode collapse. Building upon the latest research in synthetic models DDPM (denoising diffusion probabilistic model), we propose a novel approach for 2D brain MRI image synthesis based on a lightweight denoising diffusion probabilistic model. This method improves the attention module in the denoising diffusion probabilistic model to make it more lightweight. Additionally, we adopt the smooth L1 loss function as a replacement for the traditional mean absolute error (L1 loss) by comparing the error between the 2D brain MRI images with added noise and the real noise for training the model. Finally, we validate the proposed model on the MRI Brain Tumor Classification dataset, demonstrating that it achieves high-quality synthesis results while significantly reducing the parameter count of the DDPM model.

Background/Objectives: In recent years, medical imaging plays an important role to detect diseases. Especially, Magnetic Resonance Imaging (MRI) images are indispensable for tumor detection. In medical image processing, the Region Based Segmentation (RBS) algorithms have attained an essentially significance to detect the tumor and are utilized for optimum results with the segregation of tumor part in the MRI image. The aim of the work is to provide effective algorithm to extract tumor and size, the process of de-noising technique, segmentation and extraction is the best way for this. At first, the enhanced de-noising method helps to enhance the MRI image to extract the tumor alone. Methods/Statistical Analysis: In image processing, automatic image segmentation plays a vital role and for RBS, the selection of seed has to done automatically to achieve this. Even if this technique is well performed with noises, the images are difficult to segment due to pixel similarity and the presence of noise. The noises can be removed by the combinations of median and Stationary Wavelet Transform (SWT) before preceding this, contrast enhancement is needed. In this paper, the combined features of de-noising technique are used for minimizing the effect of noises in the MRI brain images. After the process of denoising, the segmented results will be a better one than non-de-noise (i.e. Original) images. The extracted tumor results are compared by the various quality metrics as MSE, PSNR, NCC, AD, NAE, SE etc. with the ground truth image. This enhanced de-noising technique is used to test 50 images and is performance evaluated based on their MSE and PSNR. Findings: The enhanced de-noising technique gives better result than existing de-noising technique. Thus, the tumor extraction can be done easily. Improvements/Applications: This technique is used mainly for medical imaging applications.

Objective: To report results of BG-12 on tertiary magnetic resonance imaging (MRI)-related outcomes from the Phase 3 DEFINE study. Background BG-12 is an experimental oral treatment for relapsing-remitting multiple sclerosis (RRMS) that may have anti-inflammatory and neuroprotective effects via the Nrf2 pathway. DEFINE, a randomized, double-blind, placebo-controlled study evaluating BG-12 over 2 years in RRMS patients, showed significant reductions in clinical relapses, accumulation of disability progression, and number of lesions on brain MRI images. Design/Methods: Patients aged 18-55 years with RRMS (McDonald criteria) and EDSS score of 0.0-5.0 were enrolled. Patients were randomized 1:1:1 to placebo or BG-12 240 mg twice (BID) or three times daily (TID). A subset of patients from 76 sites had MRI scans at baseline, 24 weeks, 1 year, and 2 years. Tertiary endpoints included brain atrophy from 6 months to 2 years measured using the SIENA method and the volume of T2, gadolinium-enhancing (Gd+), and T1 hypointense lesions at 1 and 2 years. Results: The MRI intent-to-treat cohort comprised 540 patients. The median percent whole brain volume change from 6 months to 2 years was -0.660% in placebo compared with -0.460% and -0.550% in the BG-12 BID and TID groups, respectively, representing reductions of 30% (P=0.0214) and 17% (P=0.2478) versus placebo. Over 2 years, the median percent change of T2 hyperintense lesion volume from baseline was 20.1% with placebo versus -6.2% (P Conclusions: Results of the MRI analysis of the DEFINE study demonstrate reduced brain atrophy and lesion volume compared with placebo and supports BG-129s potential as an effective oral treatment for RRMS patients. Supported by: Biogen Idec Inc. Disclosure: Dr. Arnold has received personal compensation for activities with Bayer Healthcare, Biogen Idec, Genentech, Inc., NeuroRx Research, Roche Diagnostics Corporation, Schering, Serono, Inc., and Teva Neuroscience. Dr. Arnold Dr. Arnold has received research support from Bayer Healthcare, Biogen Idec, Genentech, Inc., NeuroRx Research, Roche Diagnostics Corporation, Schering, Serono, Inc., and Teva Neuroscience. Dr. Gold has received personal compensation for activities with Bayer Pharmaceuticals Corporation, Biogen Idec, Merck Serono, Teva Neuroscience. Dr. Gold has received personal compensation in an editorial capacity for Therapeutic Advances in Neurological Disorders. Dr. Gold has received (royalty or license fee or contractual rights) payments from Biogen Idec. Dr. Gold has received research support from Bayer Pharmaceuticals Corporation, Biogen Idec, Merck Serono, Novartis and Teva Neuroscience. Dr. Kappos has received research support from Acorda Therapeutics, Actelion, Allozyne, BaroFold, Inc., Bayer Pharmaceuticals Corporation, Bayhill Therapeutics, Biogen Idec, Boehringer Ingelheim Pharmaceuticals, Inc, Elan Corporation, Genmab, GlaxoSmithKline, Inc., Glenmark Pharma, Merck Serono, MediciNova, Novartis, Sanofi-Aventis Pharmaceuticals, Santhera Pharmaceuticals, Shire, Roche Diagnostics, Teva Neuroscience, UCB Pharma, Pfizer Inc, Swiss MS Society, Swiss National Research Foundation, European Union, Gianni Rubatto Foundation, Novartis and Roche Research Foundations. Dr. Bar-Or has received personal compensation for activities with Aventis Pharmaceuticals, Bayhill Therapeutics, Biogen Idec, Berlex Laboratories, Eli Lilly & Company, Genentech, Inc., GlaxoSmithKline, Ono Pharmaceutical, Diogenix, Roche Diagnostics Corporation, Merck Serono, Novartis, Teva Neuroscience. Dr. Giovannoni has received personal compensation for activities with Bayer-Pharmaceuticals Corporation, Biogen Idec, Five Prime Therapeutics, Inc, Genzyme Corporation, Ironwood Pharmaceuticals, Merck Serono, Novartis, Teva Neuroscience, Sanofi-Aventis Pharmaceuticals and Vertex Pharmaceuticals as a speaker, consultant and/or serving on data monitoring boards. Dr. Selmaj has received personal compensation for activities with Genzyme, Ono, and Biogen Idec. Dr. Zhang has received personal compensation for activities with Biogen Idec as an employee. Dr. Stephan has received personal compensation for activities with Biogen Idec as an employee. Dr. Stephan has received research support from Biogen Idec. Dr. Dawson has received personal compensation for activities with Biogen Idec Inc. as an employee.

In this paper, we describe a new biometric approach based on geometrical characteristics of brain shape. Specifically, we use these geometrics characteristics as a biometric feature to identify individuals. For this purpose, Magnetic Resonance Imaging (MRI) images are considered. We show that using a single slice from an MRI volumetric image, acquired at a given level, one can extract many significant geometrical descriptors related to inter-individual variability of brain shape that can be also used to identify individuals. Explicitly, the proposed biometric approach combines two main phases. In the first phase, features extraction (FE) are achieved in order to obtain brain geometrical descriptors vector, called in this work GDB vector. A second phase is called similarity measurement (SM). Finally, the proposed algorithm is evaluated on the Open Access Series of Imaging Studies (OASIS) database containing brain MRI Images. Results using 220 classes show that high accuracy of 98.76% to identify individuals are obtained.

The harmony searching (HS) algorithm is a kind of optimization search algorithm currently applied in many practical problems. The HS algorithm constantly revises variables in the harmony database and the probability of different values that can be used to complete iteration convergence to achieve the optimal effect. Accordingly, this study proposed a modified algorithm to improve the efficiency of the algorithm. First, a rough set algorithm was employed to improve the convergence and accuracy of the HS algorithm. Then, the optimal value was obtained using the improved HS algorithm. The optimal value of convergence was employed as the initial value of the fuzzy clustering algorithm for segmenting magnetic resonance imaging (MRI) brain images. Experimental results showed that the improved HS algorithm attained better convergence and more accurate results than those of the original HS algorithm. In our study, the MRI image segmentation effect of the improved algorithm was superior to that of the original fuzzy clustering method.

Automatic Segmentation of Magnetic Resonance (MR) Images plays an important role in medical image processing. Segmentation is the process of extracting the brain tissue components such as grey matter (GM), white matter (WM) and cerebrospinal fluids (CSF). The volumetric analysis of the segmented tissues helps in determining the amount of GM loss in specific disease pathology. Among the various segmentation techniques, fuzzy c means (FCM) is the most widely used one. The performance of traditional FCM is considerably reduces in noisy MR images. However, in the clinical analysis accurate segmentation of MR image is very important and crucial for the early diagnosis and prognosis. This paper put forward an Artificial Neural Network based segmentation to map the longitudinal structural changes overtime in Frontotemporal dementia (FTD) subjects that could be a better cue to impending behavioural changes. Our proposed approach has achieved an average classification accuracy of 96.7%, 96.4% and 97.96% for GM, WM and CSF respectively.