Classification of Brain Tumors Using Hybridized Convolutional Neural Network in Brain MRI images

In this research article, we have proposed a novel technique to operate on the Magnetic Resonance Imaging (MRI) data images which can be classified as image classification, segmentation and image denoising. With the efficient utilization of MRI images the medical experts are able to identify the medical disorders such as tumors which are correspondent to the brain. The prime agenda of the study is to organize brain into healthy and brain with tumor in brain with the test MRI data as considered. The MRI based technique is an methodology to study brain tumor based information for the better detailing of the internal body images when compared to other technique such as Computed Tomography (CT).Initially the MRI image is denoised using Anisotropic diffusion filter, then MRI image is segmented using Morphological operations, to classify the images for the disorder CNN based hybrid technique is incorporated, which is associated with five different set of layers with the pairing of pooling and convolution layers for the comparatively improved performance than other existing technique. The considered data base for the designed model is a publicly available and tested KAGGLE database for the brain MRI images which has resulted in the accuracy of 88.1%.

Skin Lesion Segmentation in Dermoscopy Imagery

The main purpose of this study is to find an optimum method for segmentation of skin lesion images. In the present world, Skin cancer has proved to be the most deadly disease. The present research paper has developed a model which encompasses two gradations, the first being pre-processing for the reduction of unwanted artefacts like hair, illumination or many other by enhanced technique using threshold and morphological operations to attain higher accuracy and the second being segmentation by using k-mean with optimized Firefly Algorithm (FFA) technique. The online image database from the International Skin Imaging Collaboration (ISIC) archive dataset and dermatology service of Hospital Pedro Hispano (PH2) dataset has been used for input sample images. The parameters on which the proposed method is measured are sensitivity, specificity, dice coefficient, jacquard index, execution time, accuracy, error rate. From the results, authors have observed proposed model gives the average accuracy value of huge number of cancer images using ISIC dataset is 98.9% and using PH2 dataset is 99.1% with minimize average less error rate. It also estimates the dice coefficient value 0.993 using ISIC and 0.998 using PH2 datasets. However, the results for the rest of the parameters remain quite the same. Therefore the outcome of this model is highly reassuring.

Images Processing for Segmentation Neisseria Bacteria Cells

This paper introduces the segmentation of Neisseria bacterial meningitis images. Images segmentation is an operation of identifying the homogeneous location in a digital image. The basic idea behind segmentation called thresholding, which be classified as single thresholding and multiple thresholding. To perform images segmentation, transformations and morphological operations processes are used to segment the images, as well as image transformation an edge detecting, filling operation, design structure element, and arithmetic operations technique is used to implement images segmentation. The images segmentation represent significant step in extracting images features and diagnoses the disease by computer software applications.

A SIFT Description Approach for Non-Uniform Illumination and Other Invariants

The new improvement keypoint description technique of image-based recognition for rotation, viewpoint and non-uniform illumination situations is presented. The technique is relatively simple based on two procedures, i.e., the keypoint detection and the keypoint description procedure. The keypoint detection procedure is based on the SIFT approach, Top-Hat filtering, morphological operations and average filtering approach. Where this keypoint detection procedure can segment the targets from uneven illumination particle images. While the keypoint description procedures are described and implemented using the Hu moment invariants. Where the central moments are being unchanged under image translations. The sensitivity, accuracy and precision rate of data sets were evaluated and compared. The data set are provided by color image database with variants uniform and non-uniform illumination, viewpoint and rotation changes. The evaluative results show that the approach is superior to the other SIFTs in terms of uniform illumination, non-uniform illumination and other situations. Additionally, the paper demonstrates the high sensitivity of 100%, high accuracy of 83.33% and high precision rate of 80.00%. Comparisons to other SIFT approaches are also included.

An Efficient Framework for the Segmentation of Glioma Brain Tumor Using Image Fusion and Co-Active Adaptive Neuro Fuzzy Inference System Classification Method

The image segmentation of any irregular pixels in Glioma brain image can be considered as difficult. There is a smaller difference between the pixel intensity of both tumor and non-tumor images. The proposed method stated that Glioma brain tumor is detected in brain MRI image by utilizing image fusion based Co-Active Adaptive Neuro Fuzzy Inference System (CANFIS) categorization technique. The low resolution brain image pixels are improved by contrast through image fusion method. This paper uses two different wavelet transforms such as, Discrete and Stationary for fusing two brain images for enhancing the internal regions. The pixels in contrast enhanced image is transformed into multi scale, multi frequency and orientation format through Gabor transform approach. The linear features can be obtained from this Gabor transformed brain image and it is being used to distinguish the non-tumor Glioma brain image from the tumor affected brain image through CANFIS method in this paper. The feature extraction and its impacts are being assigned on the proposed Glioma detection method is also examined in terms of detection rate. Then, morphological operations are involved on the resultant of classified Glioma brain image used to address and segment the tumor portions. The proposed system performance is analyzed with respect to various segmentation approaches. The proposed work simulation results can be compared with different state-of-the art techniques with respect to various parameter metrics and detection rate.

Mesenteric cyst detection and segmentation by multiple K-means clustering and iterative Gaussian filtering

<span lang="EN-US">In this article a fully automated machine-vision technique for the detection and segmentation of mesenteric cysts in computed tomography (CT) images of the abdominal space is presented. The proposed technique involves clustering, filtering, morphological operations and evaluation processes to detect and segment mesenteric cysts in the abdomen regardless of their texture variation and location with respect to other surrounding abdominal organs. The technique is comprised of various processing phases, which include K-means clustering, iterative Gaussian filtering, and an evaluation of the segmented regions using area-normalized histograms and Euclidean distances. The technique was tested using 65 different abdominal CT scan images. The results showed that the technique was able to detect and segment mesenteric cysts and achieved 99.31%, 98.44%, 99.84%, 98.86% and 99.63% for precision, recall, specificity, dice score coefficient and accuracy respectively as quantitative performance measures which indicate very high segmentation accuracy.</span>

Automated Building Detection from Airborne LiDAR and Very High-Resolution Aerial Imagery with Deep Neural Network

The detection of buildings in the city is essential in several geospatial domains and for decision-making regarding intelligence for city planning, tax collection, project management, revenue generation, and smart cities, among other areas. In the past, the classical approach used for building detection was by using the imagery and it entailed human–computer interaction, which was a daunting proposition. To tackle this task, a novel network based on an end-to-end deep learning framework is proposed to detect and classify buildings features. The proposed CNN has three parallel stream channels: the first is the high-resolution aerial imagery, while the second stream is the digital surface model (DSM). The third was fixed on extracting deep features using the fusion of channel one and channel two, respectively. Furthermore, the channel has eight group convolution blocks of 2D convolution with three max-pooling layers. The proposed model’s efficiency and dependability were tested on three different categories of complex urban building structures in the study area. Then, morphological operations were applied to the extracted building footprints to increase the uniformity of the building boundaries and produce improved building perimeters. Thus, our approach bridges a significant gap in detecting building objects in diverse environments; the overall accuracy (OA) and kappa coefficient of the proposed method are greater than 80% and 0.605, respectively. The findings support the proposed framework and methodologies’ efficacy and effectiveness at extracting buildings from complex environments.

Sickle cell segmentation and classification for thalassemia aid diagnosis

Background: Thalassemia is a hereditary blood disease in which abnormal red blood cells (RBCs) carry insufficient oxygen throughout the body. Conventional methods of thalassemia detection through a complete blood count (CBC) test and peripheral blood smear image still possess a lot of weaknesses. Methods: This paper proposes a hybrid segmentation method to segment the RBCs. It incorporates adaptive thresholding and canny edge method to segment the RBCs. Morphological operations are performed to clean the leftovers. Shape and texture features are extracted using the segmented masks and the gray level co-occurrence matrix. Data imbalance treatment is used for solving the imbalance cell type class in distribution. In the data resampling layer, the synthetic minority oversampling technique (SMOTE), adaptive synthetic sampling (ADASYN), and random over sampling (ROS) are performed and evaluated using the decision tree and logistic regression. In the classification layer, the decision tree, random forest classifier and support vector machine (SVM) are assessed and compared for the best performance in classification. Results:The proposed method outperforms the other methods in the image segmentation layer with the structural similarity index measure (SSIM) of 89.88%. In the data resampling layer, ADASYN is employed as it is more accurate than the SMOTE and ROS. The random forest classifier is chosen at the classification layer as it is more accurate than the decision tree and support vector machine (SVM). Conclusions:The proposed method is tested on the latest dataset of erythrocyteIDB3 and it solves the issues of imbalanced data due to the insufficient cell classes.

Threshold Estimation Based on Local Minima for Nucleus and Cytoplasm Segmentation

Background: Image segmentation is a process of partitioning the input image into its separate objects or regions. It is an essential step in image processing to segment the regions of interest (ROI) for further processing. We propose a method for segmenting neucleus and cytoplasm from the white blood cells (WBC).Methods: Initially, the method computes an initial value based on the minimum and maximum values of the input image. Then, a histogram of the input image is computed and then approximated to obtain function values. The method searches for the first local maximum and local minimum from the approximated function values. We approximate the required threshold from the first local minimum and the computed initial value based on defined conditions. The threshold is applied to the input image to binarize it and then perform post-processing to obtain the final segmented nucleus. We segment the whole WBC before segmenting the cytoplasm depending on the complexity of the objects in the image. For WBCs which are well separated from the RBCs, n thresholds are generated and then produce n thresholded images. Then, a standard Otsu method is used to binarize the average of the produced images. Morphological operations are applied on the binarized image and then use a single-pixel point from the segmented nucleus to segment the WBCs. For images in which RBCs touch the WBCs, we segment the whole WBC using SLIC and watershed methods. The cytoplasm is obtained by subtracting the segmented nucleus from the segmented WBC. Results: The method is tested on two different public data sets. Performance analysis is done and the results show that the proposed method segments well the nucleus and cytoplasm. Conclusion: We propose a method for nuclei and cytoplasm segmentation based on the local minima of the approximated function values from the histogram of image. The method has demonstrated its utility in segmenting nuclei, WBCs and cytoplasm and the results are reasonable.

Investigations of Medical Image Segmentation Methods with Inclusion Mathematical Morphological Operations

Medical image segmentation research is becoming efficient by using mathematical morphological (MM) operators. There are different methods in image segmentation such as supervised and unsupervised segmentations. The MM operators are much effective, in developing a computer aided diagnosis (CAD) system. Medical image such as mammograms, generally they are of low contrast, such that radiologists face difficulties in observing the results. Due to this, diagnosis fails to generate high rate false positives and false negatives. In the proposed work improvement of quality of image segmentation with inclusion of morphological operations with other methods such as watershed transform, fuzzy logic based techniques, curvelets and MRF to detect the masses and calcifications in mammograms. Classification of masses and evaluation of segmentation process are done with artificial neural network and other performance metrics. These methods lead to increase in the accuracy, specificity and sensitivity of mammography and reduce unnecessary biopsies.