Online ISSN: 2515-8260

Keywords : Segmentation

Automated classification of Oral Squamous cell carcinoma stages detection using Deep Learning Techniques

Dr. Abinaya. R; Aditya. Y; Dr. Bala Brahmeswara Kadaru

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 1111-1119

Deep learning have earned major popularity in the today world by captured best results in medical analysis field. This research explained the stages of Oral squamous cell carcinoma using the convolution neural network model in deep Learning. Whenever the pathologist examine the photomicrograph image they faced a lot of difficulties to process and finding the stages of oral squamous cell carcinoma into poorly differentiated, medium differentiated and low differentiated. To avoid the difficulties of stages differentiation, the convolution neural network model has been implemented in this research. In the methodology part of Deep learning basically needs large number of data to perform good result so in this work image augmentation was performed to improve the better performance level of deep learning. Finally segmentation has been implemented and the segmented values are given to the convolution neural networks and it gives better accuracy of 85% when compared with all other deep learning techniques


J. , Vijayaraj; D. Loganathan

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 2, Pages 3417-3440

Lung cancer is also the most serious illness of the day for smokers. Small cell lung cancer
(SCLC) is the fatal type of lung cancer. This days, tumour detection is getting difficult. It is only
in the final stage that this form of lung cancer can be detected. Computer assisted identification
(CAD) and diagnosis mechanisms for lung cancer are an essential indicator of lung
segmentation, as the execution of those mechanisms is based on the execution of computed
tomography (CT) lung segmentation images. Image recognition system is commonly used for
early identification and treatment. Lung cancer prediction, hereditary cell identification and
environmental factors are essential factors in the development of lung cancer prevention
strategies. By predicting the movement of tumour cell it will be easier to control the tumour
spreading. This can be achieved to decrease the growth of the tumour cells using the motion
prediction model. So this paper contrasts the methods used at the earlier level to identify lung

Plant Curl Disease Detection And Classification Using Active Contour And Fourier Descriptor

M. Bala Naga Bhushanamu; M. Purnachandra Rao; K. Samatha

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 5, Pages 1088-1105

Automatic plant leaf curl detection is an important step towards the development of Computer-aided crop damage analysis systems. It helps in analyzing the health condition of the plants through leaf images. Image processing techniques are recently being used to analyze the condition of the leaf and identify the disease that inflicted the crop. Leaf curl disease can be identified by analyzing the edges of the leaf. This paper presents a procedure to identify the curl disease occurring in plant leaves using active contour, Fourier feature descriptor, and deep learning. Active contour is used to identify the shape of the leaf. The edge contour of the leaf is then given to the Fourier feature descriptor. The feature extracted using the Fourier descriptor is invariant to the angle and size of the leaf. The same feature vector is produced in any given angle and size of the leaf in the image. The features are trained using 1D CNN. The model can then be used to classify new images and automatically identify the leaf have curl disease or not. The experimental results prove that the proposed algorithm produces good results in identifying the leaf curl disease.

Automatic detection of satellite images using blob detection and boundary tracking techniques

Abhay Chaturvedi; Aasheesh Shukla

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 524-530

Automatic detection of vehicles data has been widely used in the area of traffic surveillance system where the efficient traffic management along with safety is the main concept. This project depicts the count of the vehicles present at that particular area of traffic using the data provided by the satellite. The satellite captures the image of the particular traffic junction. This satellite image is further processed in order to find the count of the vehicles. The image contains unwanted objects along with the vehicles. For that image, apply thresholding techniques to detect the vehicles and such that unwanted objects whose gray scale values are below the threshold level will be removed. The designed system converts the satellite captured image into gray scale image. This gray scale image is then converted into binary image. It is proposed to develop a unique algorithm for detecting the vehicles using thresholding techniques. If the intensity value is greater than the threshold value, 8-bit of value 255 is assigned else 8-bit of value 0 will be assigned. The edges of the objects present in the binary image will be obtained. Noise will be reduced using filters. The bright areas which are bounded will shows the vehicles present in the image. Boundary formation is useful for detecting the objects in the image. Using Blob detection method, the properties of the objects are depicted and using the Moore Boundary tracking algorithm the boundaries of the objects are detected. Detecting the vehicles and finding the count of the vehicles are the objectives of this project.


Mrs. R.Reena Roy; Dr. G.S. Anandha Mala; C. Sarika; S. Shruthi; S. Sripradha

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2981-2991

Segmentation of Pancreas with high accuracy in computerized tomography (CT) results is considered to be a basic issue in both medical image processing and computer-aided diagnosis (CAD). Pancreas segmentation is considered as a difficult task due to its uncertainity in location and in analysis of organs, while it takes very minute division of the entire abdominal CT scans. Because of the accelerated development of the CAD system and therefore the serious need for antiseptic treatments, pancreas segmentation with high accuracy of results is demanded. A new approach is used in this paper, for automated pancreas segmentation of CT images using inter-/intra-slice circumstancial instruction with preprocessing, segmentation, feature extraction, classification.

Automated Diagnosis of Malarial Parasite in Red Blood Cells

Mr K.P.K Devan; Dr G. S. Anandha Mala; Deepthi Salunkey. K; Grace Cynthia. R; Madhumitha. J

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2718-2725

The traditional system for detecting the infection has been the manual process of diagnosing the stained slides under a microscope. This manual process might consume more time for producing the results and the availability of medical experts is not always assured. Considering this as the primary concern we proposed a strategy which limits the human error while recognizing the presence of malarial parasite in the blood sample by using Image Processing. Hence by automating the diagnosis process, results can be acquired relatively quicker and more accuracy can be expected. The technologies and techniques to patently extract the required features and efficiently classify the infected samples are surveyed. This paper presents a survey of various approaches to automate the detection and classification of infected and uninfected cells.


R. Beaulah Jeyavathana; Kalpana G; K.V. Kanimozhi

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 1766-1771

Tuberculosis is one of the perilous infectious diseases that can be categorized by the evolution of tubercles in the tissues. This disease mainly affects the lungs and also the other parts of our body. Five stages are being used to detect tuberculosis disease. They are pre-processing an image, segmenting the lungs and Extracting the feature, Feature Selection and Classification. The optimal features are selected by Modified Random forest. Finally, Support Vector Machine classifier method is used for image classification. The proposed system accuracy results are better than the existing method inclassification.

An Efficient Brain Tumor Classification And Detection Using Evolutionary Approach For Healthcare System

Vinoth Kumar. V; Dr. Paluchamy. B

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 3, Pages 658-670

The growth of irregular cells within the brain region with the prearrangement of tissues is characterized as a Brain Tumor that leads death to people. Comparing to other categories of cancers, a brain tumor is the most deadly disease that has to be detected and treated in the previous stage. Due to cells' complex formation, the tumor detection process is complicated with simple image processing methodologies. Moreover, for providing proper and efficient treatment to the patients, an exact cancer segmentation and classification technique must process the input of brain images as Magnetic Resonance Imaging (MRI) scans. Based on that, this paper develops a novel approach called Soft Computing based Brain Tumor Detection and Classification (SC-BTDC) with the obtained MRI. In the present scenario of tumor detection from image processing, soft computing techniques play a significant role. Hence, it is adopted in this work. The method contains phases such as pre-processing, Fuzzy c-Means clustering-based segmentation, feature extraction, and image classification. The median pre-processing filter and edge detection methods are incorporated for noise removal and clearly define the image in the stage of the median pre-processing filter. Further, FCM based clustering is performed for the image segmentation process, following, factors of Gray Level Co-Occurrence Matrix (GLCM) found feature extraction is established. The final phase includes the classification process using the soft computing technique called Artificial Neural Network (ANN) classification. The proposed system acquires a higher accuracy rate and is compared with various existing algorithms for proving the efficiency and minimum loss of the proposed algorithm.


K. Jeevitha; A. Iyswariya; V. RamKumar; S. Mahaboob Basha; V. Praveen Kumar

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 1342-1348

Due to the advancement of computer technology image-processing techniques have become increasingly important in a wide variety of applications. Image segmentation plays a important role in image processing. Image segmentation refers to partition of an image into different regions that are similar and different in some characteristics like color, intensity or texture. Different algorithms and techniques have been developed for image segmentation. This paper investigates and compiles some of the technologies used for image segmentation. The various segmentation techniques like Edge Detection, Threshold, Region based, Feature Based Clustering and Neural Network Image Segmentation were discussed in this paper