Brain MRI Intelligent Diagnostic Using an Improved Deep Convolutional Neural Network

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.

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.

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.

Brain tumors are abnormal tissue that grow uncontrolled and affect a patient's neurological function. Brain tumors come in different shapes and characteristics. Moreover, its location also differs for each patient. Brain tumors can be detected using machine learning algorithms using magnetic resonance imaging (MRI) images. However, a different machine-learning comparison is limited and needs further investigation. This study aims to compare three machine-learning methods, i.e., Support Vector Machine (SVM), Naive Bayes (NB), and Artificial Neural Network Back Propagation (ANN-BP) algorithms for detecting brain tumors. Before the comparison started, MRI image quality was enhanced by performing denoising, histogram equalization, and thresholding. After that, Gray Level Co-occurrence Matrix feature extraction was performed. MRI brain images in JPEG format were acquired from an open-access database. One thousand brain tumor and 1000 normal tumor images are used as the training data, while 100 brain tumor and 100 normal tumor images are used as testing data. Each algorithm's accuracy, precision, sensitivity, and Matthews Correlation Coefficient (MCC) are evaluated and reported. The study showed that the SVM algorithm acquired the highest performance in detecting brain tumors, followed by ANN-BP and NB. The highest accuracy, precision, sensitivity, and MCC values for testing in SVM were 98,75%, 98,22%, 99,30%, and 0,9751, respectively. Meanwhile, in testing, the highest accuracy, precision, sensitivity, and MCC values were 90.50%, 98.80%, 82.00%, and 0.8220, respectively. In conclusion, this study showed the superiority of the SVM algorithm in detecting brain tumor compared to ANN-BP and NB by performing image enhancement steps and GLCM feature extraction before its detection.

For the problem of low accuracy using K-means clustering algorithm to segment noisy brain magnetic resonance imaging (MRI) images, this paper proposed a strategy to improve segmentation accuracy. Firstly, the strategy uses wavelet transform to brain MRI image denoising, secondly, brain MRI image is segmented by k-means clustering algorithm. Experimental results show that the proposed strategy can effectively improve the segmentation accuracy of the noisy MRI brain image and is universal to some extent.

Segmentation and classification of brain tumors from MRI images based on adaptive mechanisms and ELDP feature descriptor

Brain tumors are among the deadliest diseases in the modern world. This study proposes an optimized machine-learning approach for the detection and identification of the type of brain tumor (glioma, meningioma, or pituitary tumor) in brain images recorded using magnetic resonance imaging (MRI). The Gaussian features of the image are extracted using speed-up robust features (SURF), whereas its non-linear features are obtained using KAZE, owing to their high performance against rotation, scaling, and noise problems. To retrieve local-level information, all brain MRI images are segmented into an 8 × 8 pixel grid. To enhance the accuracy and reduce the computational time, the variance-based k-means clustering and PSO-ReliefF algorithms are employed to eliminate the redundant features of the brain MRI images. Finally, the performance of the proposed hybrid optimized feature vector is evaluated using various machine learning classifiers. An accuracy of 96.30% is obtained with 169 features using a support vector machine (SVM). Furthermore, the computational time is also reduced to 1 min compared to the non-optimized features used for training of the SVM. The findings are also compared with previous research, demonstrating that the suggested approach might assist physicians and doctors in the timely detection of brain tumors.

This paper uses the concept of intensity-curvature to highlight human brain vasculature imaged through magnetic resonance imaging (MRI). Two model functions are fitted to the MRI data. The model functions are: 1) the bivariate cubic polynomial (B32D), 2) the bivariate cubic Lagrange polynomial (G42D). The concept of intensity-curvature entails the calculation of the classic-curvature and the two intensity-curvature terms (ICTs): before and after interpolation. When the two intensity-curvature terms are calculated on a pixel-by-pixel basis across the image, they become two additional images. Through the use of the aforementioned ICT images it is possible to highlight and filter the human brain vasculature imaged with MRI. Moreover, the inverse Fourier transformation of the difference between the k-space of the MRI and the k-space of the ICT provides vessels identification. In essence, this research presents evidence that MRI images of the human brain can be studied through two additional domains: the intensity-curvature terms.

Image segmentation of brain low-grade glioma (LGG) magnetic resonance imaging (MRI) contributes tremendously to diagnosis, classification and treatment of the disease. A tangible, accurate, reliable and fast image segmentation technique is demanded in clinical diagnosis and research. The emerging machine learning technique has been demonstrated its unique capability in the field of medical image processing, including medical image segmentation. Support vector machine (SVM) and convolutional neural network (CNN) are two widely used machine learning methods. In this work, image segmentation tools based on SVM and CNN are developed and evaluated for brain LGG MR image segmentation studies. The segmentation performance in terms of accuracy and cost is quantitatively analyzed and compared between the SVM and CNN techniques developed. Computed on the Google CoLab, each of the 109 SVM models represents an individual patient, is trained using a single image of that patient and takes a few seconds to complete. The CNN model is trained on a drastically larger dataset of 19,760 data augmented images and takes approximately 2 hours to obtain the most optimal result. The SVM models achieved an average and median accuracy of 0.937 and 0.976 respectively, precision of 0.456 and 0.535 respectively, recall of 0.878 and 0.906 respectively, and F1 score of 0.546 and 0.662 respectively. Although the CNN model required a significantly longer calculation time, it surpassed the SVM models in performance in LGG MR image segmentation, achieving an accuracy of 0.998, a precision of 0.999, a recall of 0.999 and an F1 score of 0.999. This study shows that SVM with appropriate filtering techniques is capable of obtaining reliable and fast segmentation of brain LGG MR images with sufficient accuracy and limited image data. CNN technique outperforms SVM in the accuracy of segmentation with requirements of significantly enlarged data set, long computation time and high-performance computer.

Magnetic resonance imaging (MRI) is the gold standard method to study brain anatomy in vivo. Using MRI, subtle alterations to white matter structures in the brain are observed prior to cognitive decline associated with the ageing process, and neurodegenerative diseases such as Alzheimer's disease. Detection of such alterations provides hope for early clinical diagnosis. While MRI is essential to detect subtle alterations to brain structure in vivo, the technique is less suited to study and image the distribution of biochemical markers within specific brain structures. Consequently, the chemical changes that drive, or are associated with MRI-detectable alterations to white matter are not well understood. Herein, we describe (to the best of our knowledge) the first application of a complementary imaging approach that incorporates in vivo MRI with ex vivo Fourier transform infrared (FTIR) spectroscopic imaging on the same brain tissue. The combined workflow is used to detect and associate markers of altered biochemistry (FTIR) with anatomical changes to brain white matter (MRI). We have applied this combination of techniques to the senescence accelerated murine prone strain 8 (SAMP8) mouse model (n = 6 animals in each group, analysed across two ageing time points, 6 and 12 months). The results have demonstrated alterations to lipid composition and markers of disturbed metabolism during ageing are associated with loss of white matter volume.

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.

In the current study, we examined the effectiveness of classification of patients with Alzheimer's disease (AD) and healthy subjects (HS) based on brain magnetic resonance imaging (MRI) using the existence probability of various tissue types. This method quantitatively evaluates brain structural changes between two time points using existence probabilities obtained by image segmentation of brain images into four region types: gray matter (GM), white matter (WM), cerebrospinal fluid (CSF) and background. Assuming a linear relationship between the probabilities at two points, we obtained a 4×4 matrix including16 coefficients reflecting probability changes (CPCs). We performed classification of 10 AD patients and 10 HS using CPCs as features. We tested three kinds of features, excluding the CPCs that corresponded to background: all nine CPCs, diagonal CPCs reflecting structural preservation, and six non-diagonal CPCs showing structural changes, such as atrophy. Although nine CPCs showed the best performance in terms of average accuracy (77%), the maximum accuracy was 95% when non-diagonal CPCs were used as features and images at the first and last time points were compared.

At present, digital image processing plays a vital role in medical imaging areas and specifically in magnetic resonance imaging (MRI) of brain images such as axial and coronal sections. This article mainly focused on the MRI brain images. The existing methods such as total variation (MC), parallel MRI, modified pyramidal dual‐tree direction filter, adaptive dictionary selection algorithm, classifier methods, and fuzzy clustering techniques are poor in image eminence and precision. Thus, this article presents a novel approach consisting of denoising followed by segmentation. The objective of these proposed methods was visual eminence improvement of medical images to examine tumor extent using an adaptive partial differential equation (APDE)‐based analysis with soft threshold function in denoising. The fourth order, nonlinear APDE was used to denoise the image depending on gradient and Laplacian operators associated with the new adaptive Haar‐type wavelet transform. A second approach was the new convergent K‐means clustering for segmentation. The convergent K‐means procedure diminishes the summation of the squared deviations of structures in a cluster from the center. The significance of these proposed methods was to compute their performances in terms of mean squared error, peak signal‐to‐noise ratio, structure similarity, segmentation accuracy, false hit, missed‐term, and elapsed time. The results were analyzed with the MATLAB software.

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.

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.