S. S. Kumar

A survey on detection of brain tumor from MRI brain images

Brain tumor detection and segmentation is one of the most challenging and time consuming task in medical image processing. MRI (Magnetic Resonance Imaging) is a medical technique, mainly used by the radiologist for visualization of internal structure of the human body without any surgery. MRI provides plentiful information about the human soft tissue, which helps in the diagnosis of brain tumour. Accurate segmentation of MRI image is important for the diagnosis of brain tumor by computer aided clinical tool. After appropriate segmentation of brain MR images, tumor is classified to malignant and benign, which is a difficult task due to complexity and variation in tumor tissue characteristics like its shape, size, gray level intensities and location. Taking in to account the aforesaid challenges, this research is focussed towards highlighting the strength and limitations of earlier proposed classification techniques discussed in the contemporary literature. Besides summarizing the literature, the paper also provides a critical evaluation of the surveyed literature which reveals new facets of research.

A survey on recent computer-aided diagnosis of Melanoma

This paper reviews the earlier period and current technologies for skin cancer detections. Malignant melanoma is one of the most common and the deadliest type of skin cancer. Skin cancer is commonly known as Melanoma. Skin Cancers are of two types- Benign and Malignant Melanoma. Melanoma can be cured completely if it is detected early. Both benign and malignant melanoma resembles similar in appearance at the initial stages. So it is difficult to differentiate both. This is a main problem with the early skin cancer detection. Only an expert dermatologist can classify which one is benign and which one is malignant. This work focuses on developing a new computer- aided diagnosis method for melanoma. With the aim of improving some of existing methods and developing new techniques to facilitate exact, prompt and dependable computer- based diagnosis of melanoma, this makes contributions in various stages of a computer-aided diagnostic system of melanoma; namely, image segmentation or border detection, feature extraction, feature selection, and classification.

Optical character recognition: An overview and an insight

Many researches are going on in the field of optical character recognition (OCR) for the last few decades and a lot of articles have been published. Also a large number of OCR is available commercially. In this literature a review of the OCR history and the various techniques used for OCR development in the chronological order is being done.

Survey on Fetal ECG extraction

Fetal Electrocardiogram (FECG) signal, non-invasively taken from the Abdominal Electrocardiogram (AECG) of a pregnant woman is a efficient diagnostic tool for determining congenital cardiac defects. Clinically significant information in the Fetal Electrocardiogram signal is often masked by Maternal Electrocardiogram (MECG) considered as the most predominant interference, power line interference, and maternal Electromyogram (EMG), baseline wander etc. Fetal Electrocardiogram signal features may not be readily comprehensible due to the very low signal to noise ratio. Therefore Fetal Electrocardiogram should be extracted from composite Abdominal Electrocardiogram for clinical diagnosis. There are many powerful and well advanced methods for this purpose. A methodological review has been made to reveal the effectiveness of available methods which helps in understanding of Fetal ECG signal and its analysis procedures by providing valuable information.

Survey on recent CAD system for liver disease diagnosis

Computer Aided Diagnosis (CAD)systems provides computerized aid to medical practitioners that serves as a second opinion in the detection and diagnosis of diseases. Medical imaging modalities are the most effective non-invasive technique used for the classification of liver diseases. Imaging of abdominal organs for diagnosis of liver disease is usually carried out by Computed tomography. The computer aided diagnosis system consists of mainly four steps like preprocessing, segmentation, feature extraction, feature selection and classification. This article reviews the various recent CAD systems used for the classification of liver diseases using CT scan images and results of the various methods are summarized.

A Novel Approach of Despeckling SAR Images Using Nonlocal Means Filtering

AbstractSynthetic aperture radar (SAR) is a day and night, all weather satellite imaging technology. Inherent property of SAR image is speckle noise which produces granular patterns in the image. Speckle noise occurs due to the interference of backscattered echo from earth’s rough surface. There are various speckle reduction techniques in spatial domain and transform domain. Non local means filtering (NLMF) is the technique used for denoising which uses Gaussian weights. In NLMF algorithm, the filtering is performed by taking the weighted mean of all the pixels in a selected search area. The weight given to the pixel is based on the similarity measure calculated as the weighted Euclidean distance over the two windows. Non local means filtering smoothes out homogeneous areas but edges are not preserved. So a discontinuity adaptive weight is used in order to preserve heterogeneous areas like edges. This technique is called as discontinuity adaptive non local means filtering and is well-adapted and robust in the case of Additive White Gaussian Noise (AWGN) model. But speckle is a multiplicative random noise and hence Euclidean distance is not a good choice. This paper presents evaluation results of using different distance measures for improving the accuracy of the Non local means filtering technique. The results are verified using real and synthetic images and from the results it can be concluded that the usage of Manhattan distance improves the accuracy of NLMF technique. Non local approach is used as a preprocessing or post processing technique for many denoising algorithms. So improving NLMF technique would help improving many of the existing denoising techniques.

Automatic detection of lung nodules using classifiers

In this paper, comparison between three classifiers for lung cancer diagnosis is proposed. Morphological Operations is used for preprocessing of the images and gray level cooccurrence matrix is used for the feature extraction process and SVM, Minimum distance and k-nearest neighbor classifiers are used for classification. Experimental analysis is made with data set to evaluate the performance of the different classifiers. The performance of SVM classifiers is found to be the best based correct and incorrect classification of the classifier.

Brain tumor detection and segmentation using a wrapper based genetic algorithm for optimized feature set

The work here intends to develop an algorithm for optimizing the available feature set for identifying tumor from brain MRI images. A set of features are selected based on texture features. From the large set of features relevant features would be selected using wrapper approach. Further, an optimized subset of the relevant features is generated with the help of Genetic Algorithm. The machine learning with support vector machine algorithm is used for detection and segmentation of tumors in the brain MRI image acquired. The superiority of the algorithm is established by comparing it with the state of the art algorithms such as level set method and fuzzy based methods. The authors are using performance measurement tools including manual segmentation and volume based tools for validating the claim.

Segmentation of chondroblastoma from medical images using modified region growing algorithm

Chondroblastoma is a bone tumor typically found within the cartilage tissue space of bone and unfolds into its surroundings. This tumor reduces the strength of bone and even leads to death if not treated early. Chondroblastoma is diagnosed from X-ray images and the tumor can be removed by surgical methods. For the successful removal, the exact volume of tumor should be known, which can be identified by segmenting the tumor region from the image. Chondroblastoma can be segmented from X-ray image by manual and computer aided methods. Manual segmentation may leads to inter and intra observer errors. This work proposes an efficient segmentation tool called modified region growing method for segmenting chondroblastoma. This work focuses on automatic and accurate segmentation of chondroblastoma which gives better segmentation results than existing methods. The segmentation results are evaluated using dice coefficients, jaccard distance, and coefficient of similarities, spatial overlaps, absolute volume measurement error and figure of merit.

Inhibition of PKCβ Mediates Cardioprotective Activity of Ambrex against Isoproterenol-Induced Myocardial Necrosis: in vivo and in silico Studies

Aims and objectives: The current study characterized the morphology of Ambrex formulation by Scanning Electron Microscopy and assessed its cardioprotective activity against Isoproterenol (ISPH)-induced myocardial necrosis in rats by biochemical and histopathological evaluations, and also attempted to predict the prospective protein-targets of Ambrex and the signaling pathway that mediates this activity through molecular docking approach. Materials and methods: Sprague–Dawley male rats (4 groups, 6 rats per group) chosen for the current study were acclimatized to the laboratory conditions for 7 days prior to actual treatment; they were pretreated with Ambrex (40 mg/kg b.wt/day, p.o) everday for 21 days and then intoxicated with ISPH (85 mg/kg b.wt, s.c) on day-20 and 21 to experimentally induce myocardial necrosis. The extent of ISPH-induced myocardial necrosis was quantified in terms of the serum levels of two cardiac biomarkers: creatine kinase-MB and lactate dehydrogenase. The extent of ISPH-induced oxidative stress was quantified in terms of the tissue levels of five oxidative stress biomarkers: superoxide dismutase, catalase, reduced glutathione, glutathione peroxidase and lipid peroxidation. Results and discussion: The Scanning Electron Microscopy image of Ambrex formulation showed the formation of nanoparticles with thickness of 65 nm, making Ambrex a unique metal-deficient Siddha-medicine based polyherbal nano-formulation characterized and evaluated in India. Pretreatment with Ambrex attenuated the extent of ISPH-induced oxidative stress, lipid peroxidation and generation of reactive oxygen species as reflected by biochemical evaluations, and also ameliorated the degree of ISPH-induced myocardial necrosis and membrane damage as reflected by histopathological evaluations. The results of molecular docking revealed that Withaferin-A and Methyl Commate-A (the key metabolites of Withania somnifera and Ambrex respectively) inhibit Protein KinaseC Beta, and renders Ambrex its cardioprotective activity by maintaining the intracellular antioxidant homeostasis and myocardial membrane architecture.