Prediction of Cancerous Cell by Cluster Based Biomedical CT Image and Analysis

Abstract

Medical and health arena is advanced in recent years with the technological influence especially using image processing techniques and algorithms. Biomedical Image processing resolves many cons of manual disease recognition. In this paper we have depicted the automated clinical diagnosis for tumor detection based on segmentation of CT scan images towards lungs cancer, ovary cancer and liver cancer. Tumor is an exceptional expansion generated by human cells reproducing themselves in an unconstrained manner. Accurate detection of size and location of tumour plays a vital role in the diagnosis of tumor. Clustering plays a specific role in Image object segmentation both in Gray and RGB based Bio-medical images. We have taken different CT scanned Image of three main sources of diseases processing for detection of tumor based on three major life killer disease with the steps of image processing keeping prominence on noise removal, contrast enhancement by stretching.

A Skin Cancer Image Detection Interface Tool Using VLF Support Vector Machine Classification

“…Feature extraction is a method of reducing dimension where a large number of picture element ties are consistently represented in such a way that the crucial components of the image are effectively captured, where features are the prominent attributes applicable for figuring out certain applications and to lay out important properties of images. So, the main objective of using feature extraction method is to draw a bead on reducing the number of features by constructing new features of the master features [9]. Therein feature extraction, the visual content of the images is captured for the reason of reducing the amount of required resources.…”

“…Consider the uni-dimensional discriminate function F with screening data S and preparing data P as shown in Eq. (9).…”

“…An unsupervised algorithm categorizes the input data point into multiple groups or clusters, based on their inherent distance from each other. To calculate the input data and perform the natural clustering, the K-means algorithm is used [8,9]. The points are grouped around centroids as shown in Eq.…”

Forgery Detection of Fake Currency Using Image Derivative Based Segmentation Technique

“…The points at which the image brightness adjustment occurs rapidly are usually furnished in a set of edges of curved line segments. Originally edge detection is a derivative-based method that is classified into first-order and second-order derivative filters [5][6][7][8][9][10][11][12]. Firstorder derivative-based filters work better with thick edges while second-order ones give better results with thinner or finer edges.…”

Use of Statistical Techniques to Analyze Textures in Medical Images for Tumor Detection and Evaluation

“…This observation, however, does not extend to textures that differ in a third or higher order, and cannot readily be discerned by the naked eye. Segmentation divides an image into discrete fields, so that the pixels in each region are similar and there is a visible distinction between regions, according to Agrawal [7].…”