Thermographic Image Analysis Method in Detection of Canine Bone Cancer (Osteosarcoma)

Size: px
Start display at page:

Download "Thermographic Image Analysis Method in Detection of Canine Bone Cancer (Osteosarcoma)"

Transcription

1 2012 5th International Congress on Image and Signal Processing (CISP 2012) Thermographic Image Analysis Method in Detection of Canine Bone Cancer (Osteosarcoma) Maryamsadat Amini, Peng Liu and Scott E Umbaugh Computer Vision and Image Processing Laboratory Electrical and Computer Engineering Southern Illinois University Edwardsville (SIUE) Edwardsville, IL , USA Dominic J. Marino and Catherine A. Loughin Long Island Veterinary Specialists (LIVS) 163 South Service Road Plainview, NY, USA Abstract Bone cancer is a pathologic condition which may occur for both humans and canines. This tumor develops quickly from within the bone tissue and become painful as it grows outward. A metastasized bone tumor may be cured by amputation, otherwise it will be fatal. The current diagnostic imaging methods for bone cancer are X-rays, Computed Tomography scan (CT scan), and Magnetic Resonance Imaging (MRI). The disadvantages of these methods include not enough detail in X-ray images, high dose of radiation from CT scans, and high expense of the timeconsuming MRI method. In most of the bone cancer cases, when this tumor is detected by these imaging methods, it has already metastasized. The study is to investigate whether it is possible to detect canine bone cancer by thermography imaging. This alternative imaging method will decrease diagnostic time, expenses and prevent radiation exposure. The best classification success rate obtained in this study is 80.77%. Keywords-bone cancer; osteosarcoma; thermographic image analysis ; feature extraction; pattern classification; CVIPtools I. INTRODUCTION Thermography is a noninvasive diagnostic imaging technique that represents the cutaneous temperature distribution in the form of a color image. Various conditions of disease or injury can influence local dermal microcirculation and temperature. The correlation between temperature recordings and the presence of a disease or injury is the clinical basis for thermography. Clinically, thermography can be used as a diagnostic tool to improve interpretation of physical examination results [1]. Canine bone cancer (or osteosarcoma; osteo = bone, sarcoma = cancer) is a common type of cancer that grows fast and may be fatal. Larger breeds are more prone to bone cancer. Bone cancer most frequently occurs in middle-aged, older dogs, and usually in the limbs, which is called appendicular osteosarcoma. Tumorous bone is not as strong as normal bone and tends to break with slight injury. These types of breaks, which never heal, are called pathologic fractures [2]. Unfortunately, in most of the bone cancer cases, when the tumor is detected by current diagnostic methods such as X- rays, MRI, and biopsy, the malignancy has already metastasized to the adjacent tissues and organs. The metastasized bone tumor may be cured by amputation, otherwise it is fatal. This has encouraged the researchers to look for alternative diagnostic imaging systems such as thermography. The investigation here is to determine if the thermography imaging technique enables the detection of the abnormality even before its visual detection by providing physiological information, which ultimately accelerates the treatment procedure. The investigation includes three main steps: Image segmentation and mask creation Feature selection and extraction Data normalization and pattern classification II. MATERIALS A. Thermographic Images A thermographic image (thermogram) is a color image in which each color represents a specific temperature. The thermograms used in this study use an 18-shade color map. The color map describes warmer temperatures as white and red and cooler temperatures as blue and black. The thermographic images were taken from 22 dogs with bone cancer confirmed by biopsy, in the same room with temperature being controlled at 21 C. The camera was located approximately 1.5 to 4.6 m from the dogs, depending on the region of interest (ROI). The method for imaging includes full left and right lateral limb views of both forelimbs and hind limbs, and cranial and caudal views [1]. A total number of 197 thermal images including cancer and non-cancer classes with four different limb regions are used; full-limb, shoulder/hip, elbow/knee, and wrist. The number of images in each region, considering both cancer and non-cancer classes, are 26 for full-limb region, 35 for shoulder/hip region, 84 for elbow/knee region, and 52 for wrist region. Examples of the thermographic images of the four limb regions of a healthy dog (non-cancer) and a dog diagnosed with cancer (cancer) are shown in Fig. 1 and in Fig. 2, respectively /10/$ IEEE 599

2 Figure 1. (Left to right) full-limb, hip, knee, and wrist regions of non-cancer images including their corresponding ROIs Figure 2. (Left to right) full-limb, shoulder, elbow, and wrist regions of cancer images including their corresponding ROI In the most of the cases, only one of the limbs of each dog is affected by bone cancer. Therefore, the limb opposite the cancerous one is considered as a non-cancer limb. According to this fact, approximately half of the total thermal images are categorized as non-cancer images. B. Masks In order to focus only on the tumor and its metastasized areas of each image, a total number of 197 masks are created (one mask per each image) manually based on the ROI determined by the veterinarian specialists. The masks are created by using the Computer Vision and Image Processing tools (CVIPtools) software [3]. Fig. 3 shows an original image, its corresponding mask, and the mask performance in the ROI extraction. C. Programs and Softwares CVIPtools is used in the manual mask creation for the image segmentation step. This software allows for the manual processing of one image at a time and produces an instant result [3]. Four color normalization methods are implemented on the original images. The four color normalization methods are Luminance, Norm-Grey, Norm-RGB, and Norm-RGB-Lum. The methods are utilized to remap colors corresponding to the different temperatures in the thermographic images. Although each color represents a specific temperature with in each image, the color to temperature mapping for an image is affected by the camera setting at the time of the image capture. Therefore one color may represent several different temperatures across the images which is caused by camera recalibration between each image capture [4]. The Luminance method generates a gray level value for each color component based on the linear equation in which each color band is weighted as follows: GreyLevel = 0.3 Red Green Blue (1) In the Norm-Gray method, temperatures from the minimum to the maximum are mapped to the gray levels from 0 to 255. The gray level of each pixel in the normalized image represents the corresponding pixel temperature in the original image. Norm-RGB is similar to the Norm-Grey, but temperatures are mapped to a continuous version of the original color palette instead of gray levels from 0 to 255. Norm-RGB-Lum method applies Luminance color normalization method to the Norm-RGB result [4]. The results of the four color normalization methods and their corresponding original image are shown in Fig. 4. The Computer Vision and Image Processing-Feature Extraction and Pattern Classification (CVIP-FEPC) software provides both feature extraction and pattern classification in a single run [5]. This software implements each pattern classification method on all the combinations of the features selected by the user. The pattern classification results are reported by a total correctnesss classification rate and also the classification rate for each class, by which the sensitivity and specificity of each set of experiment can be calculated. By using the software, the best feature set for each experiment can be extracted according to the best classification success rate. Figure 3. Original image and its corresponding mask extraction illustrating the ROI Figure 4. (Left to right) Luminance, Norm-Grey, Norm-RGB, Norm-RGB- and the original Lum color normalized images image Long Island Veterinary Specialists, Veterinary Thermographic Image Analysis: Canine Bone Cancer, 2012 Southern Illinois University Edwardsville, School of Engineering, Electrical and Computer Engineering Department 600

3 The Partek Discovery Suite is data analysis software used to apply six different pattern classification methods [6]. In this study, the best feature sets selected by the best CVIP-FEPC classification success rates are analyzed by these other pattern classification methods. III. METHODS The research study follows three principal steps to determine the diagnostic ability of thermographic images for canine bone cancer detection. The procedure is: Image segmentation and mask creation Feature selection and extraction Data normalization and pattern classification The first step provides only the ROI of the thermal images by mask creation to avoid storage and analysis of unnecessary information. All of the image masks are created manually. In the second step, several features such as histogram and texture features, which are used for analysis and classification, are extracted. In the last step, the extracted information are normalized and classified into two classes of cancer and noncancer. Also, the classification correctness metrics (or the success rates) are evaluated for each of the implemented pattern classification method. The number of sample images that are classified correctly represents the success rate, in other words, the success rates indicate whether the thermal images correlate with biopsy results. The procedure is applied on either the original or one of the four types of color normalized images which makes a total of five different experiment sets. Since each of the experimental sets is performed on each of the four limb regions and the total images, a total number of 25 different experimental sets are analyzed based on the different limb regions and color normalization methods. A. Mask Creation At first, the manual masks are created based on the ROIs determined for each image by the veterinarian specialist in the Long Island Veterinary Specialists (LIVS). The masks are created by using the original images. However, they can be applied to extract the ROI for both of the original and color normalized images. Extracting the ROI decreases the complexity (time and memory) of the image processing procedure. B. Feature Selection and Extraction In this step, the feature types to be extracted for each experiment set are defined. Each experiment set includes as many single experiments as the number of all combinations of selected feature types. For experiment sets using original images, 10 feature types are extracted including spectral, four histogram, and five texture feature types. The histogram feature types include histogram standard deviation, skew, energy, and entropy. The texture features are texture energy, inertia, correlation, inverse difference, and entropy. The total number of 10 feature types produces 1024 experiments implemented on all combinations of the selected features. After color normalization, we can rely on each color to be a specific temperature in all the images, so the histogram mean feature also is added to the mentioned 10 feature types for experiment sets using color normalized images. Totally, each experiment set implemented using color normalized images includes 2048 different experiments to analyze each combination of the 11 feature types. The mentioned number for each feature represents only the number of different types of histogram, texture, and spectral features. However, in the real experiments with the CVIP- FEPC, the total number of 43 features is extracted for original images and 46 features for the color normalized images. Since each histogram feature is extracted for three bands of red, green, and blue (RGB), the four types of histogram features would be in total 12 features. In case of using color normalized images, the total number of 15 histogram features are extracted. Also, for each type of texture feature (five types), the range and average of the four directions are calculated which results in total 10 texture features. Moreover, the spectral feature is measured for three rings and three sectors. The spectral features of each sector and each ring are extracted for three color bands (RGB) which makes 18 spectral features. The number of 18 spectral features also should be added to three features of the spectral DC value for three color bands, so in total there are 21 spectral features. C. Data Normalization and Pattern Classification All the extracted feature values are normalized using the data normalization methods including standard normal density normalization and softmax scaling with r = 1 [7]. Feature extraction, data normalization, and pattern classification are implemented by CVIP-FEPC, simultaneously. In addition to CVIP-FEPC, Partek Discovery Suite is also used for applying more pattern classification methods. In both of the CVIP-FEPC and the Partek software, full leave-one-out is the selected testing method for all the performed experiments. The pattern classification method of K-Nearest-Neighbor (KNN) with K = 4 is applied in the CVIP-FEPC. The CVIP- FEPC experiments are performed on all the combinations of the (10 or 11) feature types and two mentioned data normalization methods, which make the experiment sets comprise 2048 or 4096 single experiments. The experimental sets not only give us the pattern classification results but also provide the significant feature types by the ranking of the classification success rates including their corresponding feature sets. The feature sets related to the best classification success rates are selected to insert to the Partek software for other pattern classification methods analysis. Therefore, we implement six pattern classification methods provided by the Partek software only on the feature sets including significant feature types. By using the Partek software, six different pattern classification methods are applied including linear discriminant analysis with equal prior probability, linear discriminant analysis with proportional prior probability, nearest centroid with equal prior probability, KNN with K = 1, 3, and 5. Overall, we obtain the classification success rates of the seven different pattern classification methods on the same data 601

4 (best feature sets selected by the best results of the KNN with K = 4). Based on the success rates comparison of the seven classification methods, the KNN with K = 1 (Nearest- Neighbor) performance is better than other methods. Accordingly, we implemented the Nearest-Neighbor pattern classification method again, but this time, this classification method is applied on all the combinations of the (10 or 11) feature types by CVIP-FEPC. By ranking the success rates with their corresponding feature sets, we determined the best feature sets obtained by the best Nearest-Neighbor classification results. IV. RESULTS Totally, 200 different sets of experiments are implemented by the CVIP-FEPC and Partek software, from which 50 experiment sets are executed by CVIP-FEPC, and the Partek software is applied for 150 experiment sets. From CVIP-FEPC experiments, 25 experiment sets are performed by KNN with K = 4 classification method for five limb region conditions (four limb regions and total limb regions), and five color normalization conditions (four color normalization methods and non-color normalization). The best success rates produced by KNN with K = 4 is illustrated in Figure X. As shown in Figure X, among all the 25 CVIP-FEPC experiment sets using KNN with K = 4, the full-limb region with Norm-RGB-Lum color normalized images produces the best classification success rate of 76.92% with a sensitivity value of 84.62% and a specificity value of 69.23%. A total number of 150 experiments are executed with the Partek software, including all combinations of the five limb region conditions, five color normalization conditions, and six classification methods. The best correct classification rates obtained by the Partek software are shown in Figure Y in Appendix A. In the experiments, the best correct classification rate, 80.77%, is obtained by the full-limb region images which are color normalized by Norm-RGB-Lum and classified by the Nearest-Neighbor. Among all the six classification methods, Nearest-Neighbor and KNN with K = 3 and K = 5 produced the highest classification rates (shown in Figure Y), from which Nearest-Neighbor performance was better for more limb regions. This encourages us to perform Nearest-Neighbor classification method by CVIP-FEPC to determine the best feature sets from all the combinations of the (10 or 11) selected feature types. A total number of 25 experiment sets are performed by CVIP-FEPC to determine the most significant feature types based on the Nearest-Neighbor best classification success rates. The experiment sets includes all combinations of the five limb region conditions and five color normalization conditions. The best success rates for each limb region are shown in Figure Z in Appendix A. The highest classification success rate is 80.77% (shown in Figure Z) with a sensitivity value of 92.31% and specificity value of 69.23%. The best success rate is achieved by Norm-RGB-Lum color normalized images of the full-limb region. According to the best success rates of the KNN with K = 4 and their corresponding feature sets, histogram standard deviation, histogram skew, and texture correlation appear frequently in the feature sets. Also, based on the best success rates of the Nearest-Neighbor classification method, histogram standard deviation, histogram skew, and texture inverse difference are the most three significant features. V. SUMMARY The purpose of this research study is to determine the capability of thermographic imaging for canine bone cancer detection. The currently used diagnostic imaging methods provide significant disadvantages. Although, in all the experiments performed in this study, we apply heterogeneous data including canine with different breeds and genders, the color normalized images with Norm-RGB-Lum of the full-limb region produced the best classification success rate of 80.77%. The number of thermal images in the specific experiment is 26 including 13 cancer and 13 non-cancer thermograms. Three features are extracted in the experiment which are texture inverse difference, histogram skew, and histogram entropy with using standard normal density data normalization method. The best success rate is obtained by Nearest-Neighbor method. Given more thermographic images it may be possible to perform separate experiments for each canine breed which may increase the success rates. VI. FUTURE SCOPE In this study, we performed the analysis for different canine breeds in a single set of experiments, due to the small amount of data available. We may be able to increase the success rates by implementing the experiments for each breed separately. REFERENCES [1] C. A. Loughin, DVM, and D. J. Marino, DVM, Evaluation of thermographic imaging of the limbs of healthy dogs, American veterinary Medical Association (AVMA), vol. 68, No. 10, pp , October [2] Vetinfo. The dog bone cancer. Retrieved 15 May [3] Computer Vision and Image processing Tools (CVIPtools). Retrieved [4] S. E Umbaugh, P. Solt, Veterinary thermographic image analysis. Data and temperature normalization. SIUE CVIP Laboratory report number , January 23, 2008, unpublished. [5] CVIP-FEPC. Retrieved [6] Partek Discovery Suite. Retrieved [7] S. E Umbaugh, Digital image processing and analysis: human and computer applications with CVIPtools, second edition, The CRC Press, Boca Raton, FL,

5 Appendix A CVIP-FEPC Best Classification Success Rates KNN with K = % 74.28% 73.08% % 65.48% CVIP-FEPC Best Classification Success Rates Nearest-Neighbor % 76.92% % 69.05% % Figure X. CVIP-FEPC best classification success rates for KNN with K = 4 method based on each limb region Figure Z. CVIP-FEPC best classification success rates for Nearest-Neighbor method based on each limb region Partek Best Classification Success Rates % 80.77% 71.40% 65.48% 77.57% Figure Y. Partek best classification success rates with their corresponding classification methods based on each limb region 603

Rupture Disease. by Jiyuan Fu, Bachelor of Science

Rupture Disease. by Jiyuan Fu, Bachelor of Science 1 Using Thermographic Image Analysis in Detection of Canine Anterior Cruciate Ligament Rupture Disease by Jiyuan Fu, Bachelor of Science A Thesis Submitted in Partial Fulfillment of the Requirements for

More information

The Institute of Telecommunications and Computer Sciences, UTP University of Science and Technology, Bydgoszcz , Poland

The Institute of Telecommunications and Computer Sciences, UTP University of Science and Technology, Bydgoszcz , Poland Computer Technology and Application 6 (2015) 64-69 doi: 10.17265/1934-7332/2015.02.002 D DAVID PUBLISHIN An Image Analysis of Breast Thermograms Ryszard S. Choras The Institute of Telecommunications and

More information

Tumor Detection and classification of Medical MRI UsingAdvance ROIPropANN Algorithm

Tumor Detection and classification of Medical MRI UsingAdvance ROIPropANN Algorithm International Journal of Engineering Research and Advanced Technology (IJERAT) DOI:http://dx.doi.org/10.31695/IJERAT.2018.3273 E-ISSN : 2454-6135 Volume.4, Issue 6 June -2018 Tumor Detection and classification

More information

Improving the detection of excessive activation of ciliaris muscle by clustering thermal images

Improving the detection of excessive activation of ciliaris muscle by clustering thermal images 11 th International Conference on Quantitative InfraRed Thermography Improving the detection of excessive activation of ciliaris muscle by clustering thermal images *University of Debrecen, Faculty of

More information

Computer-Aided Detection system for Hemorrhage contained region

Computer-Aided Detection system for Hemorrhage contained region Computer-Aided Detection system for Hemorrhage contained region Myat Mon Kyaw Faculty of Information and Communication Technology University of Technology (Yatanarpon Cybercity), Pyin Oo Lwin, Myanmar

More information

Extraction and Features of Tumour from MR brain images

Extraction and Features of Tumour from MR brain images IOSR Journal of Electronics and Communication Engineering (IOSR-JECE) e-issn: 2278-2834,p- ISSN: 2278-8735.Volume 13, Issue 2, Ver. I (Mar. - Apr. 2018), PP 67-71 www.iosrjournals.org Sai Prasanna M 1,

More information

Chapter 3 Set Redundancy in Magnetic Resonance Brain Images

Chapter 3 Set Redundancy in Magnetic Resonance Brain Images 16 Chapter 3 Set Redundancy in Magnetic Resonance Brain Images 3.1 MRI (magnetic resonance imaging) MRI is a technique of measuring physical structure within the human anatomy. Our proposed research focuses

More information

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks

Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Computer-Aided Diagnosis in Abdominal and Cardiac Radiology Using Neural Networks Du-Yih Tsai, Masaru Sekiya and Yongbum Lee Department of Radiological Technology, School of Health Sciences, Faculty of

More information

Mass Classification Method in Mammogram Using Fuzzy K-Nearest Neighbour Equality

Mass Classification Method in Mammogram Using Fuzzy K-Nearest Neighbour Equality Mass Classification Method in Mammogram Using Fuzzy K-Nearest Neighbour Equality Abstract: Mass classification of objects is an important area of research and application in a variety of fields. In this

More information

Global Journal of Engineering Science and Research Management

Global Journal of Engineering Science and Research Management ADVANCED K-MEANS ALGORITHM FOR BRAIN TUMOR DETECTION USING NAIVE BAYES CLASSIFIER Veena Bai K*, Dr. Niharika Kumar * MTech CSE, Department of Computer Science and Engineering, B.N.M. Institute of Technology,

More information

Automated Lesion Detection Methods for 2D and 3D Chest X-Ray Images

Automated Lesion Detection Methods for 2D and 3D Chest X-Ray Images Automated Lesion Detection Methods for 2D and 3D Chest X-Ray Images Takeshi Hara, Hiroshi Fujita,Yongbum Lee, Hitoshi Yoshimura* and Shoji Kido** Department of Information Science, Gifu University Yanagido

More information

Available Online through

Available Online through Available Online through www.ijptonline.com ISSN: 0975-766X CODEN: IJPTFI Research Article ANALYSIS OF CT LIVER IMAGES FOR TUMOUR DIAGNOSIS BASED ON CLUSTERING TECHNIQUE AND TEXTURE FEATURES M.Krithika

More information

Prostate Detection Using Principal Component Analysis

Prostate Detection Using Principal Component Analysis Prostate Detection Using Principal Component Analysis Aamir Virani (avirani@stanford.edu) CS 229 Machine Learning Stanford University 16 December 2005 Introduction During the past two decades, computed

More information

Conference Biomedical Engineering

Conference Biomedical Engineering Automatic Medical Image Analysis for Measuring Bone Thickness and Density M. Kovalovs *, A. Glazs Image Processing and Computer Graphics Department, Riga Technical University, Latvia * E-mail: mihails.kovalovs@rtu.lv

More information

A Systematic Analysis System for CT Liver Image Classification and Image Segmentation by Local Entropy Method

A Systematic Analysis System for CT Liver Image Classification and Image Segmentation by Local Entropy Method A Systematic Analysis System for CT Liver Image Classification and Image Segmentation by Local Entropy Method A.Anuja Merlyn 1, A.Anuba Merlyn 2 1 PG Scholar, Department of Computer Science and Engineering,

More information

BRAIN CANCER CLASSIFICATION USING BACK PROPAGATION NEURAL NETWORK AND PRINCIPLE COMPONENT ANALYSIS Ganesh Ram Nayak 1, Mr.

BRAIN CANCER CLASSIFICATION USING BACK PROPAGATION NEURAL NETWORK AND PRINCIPLE COMPONENT ANALYSIS Ganesh Ram Nayak 1, Mr. International Journal of Technical Research and Applications e-issn:2320-8163, www.ijtra.com Volume 2, Issue 4 (July-Aug 2014), PP. 26-31 BRAIN CANCER CLASSIFICATION USING BACK PROPAGATION NEURAL NETWORK

More information

FINDING THE TRUE EDGE IN CTA

FINDING THE TRUE EDGE IN CTA FINDING THE TRUE EDGE IN CTA by: John A. Rumberger, PhD, MD, FACC Your patient has chest pain. The Cardiac CT Angiography shows plaque in the LAD. You adjust the viewing window trying to evaluate the stenosis

More information

COMPARISION OF NORMAL Vs HERNIATED CERVICAL IMAGES USING GRAY LEVEL TEXTURE FEATURES

COMPARISION OF NORMAL Vs HERNIATED CERVICAL IMAGES USING GRAY LEVEL TEXTURE FEATURES COMPARISION OF NORMAL Vs HERNIATED CERVICAL IMAGES USING GRAY LEVEL TEXTURE FEATURES C.Malarvizhi 1 and P.Balamurugan 2 1 Ph.D Scholar, India 2 Assistant Professor,India Department Computer Science, Government

More information

Region-based Segmentation

Region-based Segmentation Region-based Segmentation Image Segmentation Group similar components (such as, pixels in an image, image frames in a video) to obtain a compact representation. Applications: Finding tumors, veins, etc.

More information

A Robust Brain MRI Classification with GLCM Features

A Robust Brain MRI Classification with GLCM Features A Robust Brain MRI with GLCM Features Sahar Jafarpour Zahra Sedghi Mehdi Chehel Amirani ABSTRACT Automated and accurate classification of brain MRI is such important that leads us to present a new robust

More information

Global Thresholding Techniques to Classify Dead Cells in Diffusion Weighted Magnetic Resonant Images

Global Thresholding Techniques to Classify Dead Cells in Diffusion Weighted Magnetic Resonant Images Global Thresholding Techniques to Classify Dead Cells in Diffusion Weighted Magnetic Resonant Images Ravi S 1, A. M. Khan 2 1 Research Student, Department of Electronics, Mangalore University, Karnataka

More information

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY

INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY INTERNATIONAL JOURNAL OF PURE AND APPLIED RESEARCH IN ENGINEERING AND TECHNOLOGY A PATH FOR HORIZING YOUR INNOVATIVE WORK REVIEW ON CONTENT BASED IMAGE RETRIEVAL BY USING VISUAL SEARCH RANKING MS. PRAGATI

More information

3-D MRI Brain Scan Classification Using A Point Series Based Representation

3-D MRI Brain Scan Classification Using A Point Series Based Representation 3-D MRI Brain Scan Classification Using A Point Series Based Representation Akadej Udomchaiporn 1, Frans Coenen 1, Marta García-Fiñana 2, and Vanessa Sluming 3 1 Department of Computer Science, University

More information

Refraction Corrected Transmission Ultrasound Computed Tomography for Application in Breast Imaging

Refraction Corrected Transmission Ultrasound Computed Tomography for Application in Breast Imaging Refraction Corrected Transmission Ultrasound Computed Tomography for Application in Breast Imaging Joint Research With Trond Varslot Marcel Jackowski Shengying Li and Klaus Mueller Ultrasound Detection

More information

TUMOR DETECTION IN MRI IMAGES

TUMOR DETECTION IN MRI IMAGES TUMOR DETECTION IN MRI IMAGES Prof. Pravin P. Adivarekar, 2 Priyanka P. Khatate, 3 Punam N. Pawar Prof. Pravin P. Adivarekar, 2 Priyanka P. Khatate, 3 Punam N. Pawar Asst. Professor, 2,3 BE Student,,2,3

More information

Calculating the Distance Map for Binary Sampled Data

Calculating the Distance Map for Binary Sampled Data MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Calculating the Distance Map for Binary Sampled Data Sarah F. Frisken Gibson TR99-6 December 999 Abstract High quality rendering and physics-based

More information

Blood Microscopic Image Analysis for Acute Leukemia Detection

Blood Microscopic Image Analysis for Acute Leukemia Detection I J C T A, 9(9), 2016, pp. 3731-3735 International Science Press Blood Microscopic Image Analysis for Acute Leukemia Detection V. Renuga, J. Sivaraman, S. Vinuraj Kumar, S. Sathish, P. Padmapriya and R.

More information

Medical Image Feature, Extraction, Selection And Classification

Medical Image Feature, Extraction, Selection And Classification Medical Image Feature, Extraction, Selection And Classification 1 M.VASANTHA *, 2 DR.V.SUBBIAH BHARATHI, 3 R.DHAMODHARAN 1. Research Scholar, Mother Teresa Women s University, KodaiKanal, and Asst.Professor,

More information

Machine Learning for Medical Image Analysis. A. Criminisi

Machine Learning for Medical Image Analysis. A. Criminisi Machine Learning for Medical Image Analysis A. Criminisi Overview Introduction to machine learning Decision forests Applications in medical image analysis Anatomy localization in CT Scans Spine Detection

More information

IMAGE PROCESSING AND MACHINE LEARNING FOR THE DIAGNOSIS OF MELANOMA CANCER

IMAGE PROCESSING AND MACHINE LEARNING FOR THE DIAGNOSIS OF MELANOMA CANCER IMAGE PROCESSING AND MACHINE LEARNING FOR THE DIAGNOSIS OF MELANOMA CANCER Arushi Raghuvanshi 1 and Marek Perkowski Department of Electrical and Computer Engineering, Portland State University, Portland,

More information

Classification of Hyperspectral Breast Images for Cancer Detection. Sander Parawira December 4, 2009

Classification of Hyperspectral Breast Images for Cancer Detection. Sander Parawira December 4, 2009 1 Introduction Classification of Hyperspectral Breast Images for Cancer Detection Sander Parawira December 4, 2009 parawira@stanford.edu In 2009 approximately one out of eight women has breast cancer.

More information

The UK Teleradiology Market: Size, Trends & Forecasts ( ) February 2018

The UK Teleradiology Market: Size, Trends & Forecasts ( ) February 2018 The UK Teleradiology Market: Size, Trends & Forecasts (2018-2022) February 2018 The UK Teleradiology Market : Coverage Executive Summary and Scope Introduction/Market Overview Market Analysis Dynamics

More information

Texture-Based Detection of Myositis in Ultrasonographies

Texture-Based Detection of Myositis in Ultrasonographies Texture-Based Detection of Myositis in Ultrasonographies Tim König 1, Marko Rak 1, Johannes Steffen 1, Grit Neumann 2, Ludwig von Rohden 2, Klaus D. Tönnies 1 1 Institut für Simulation & Graphik, Otto-von-Guericke-Universität

More information

Hybrid Approach for MRI Human Head Scans Classification using HTT based SFTA Texture Feature Extraction Technique

Hybrid Approach for MRI Human Head Scans Classification using HTT based SFTA Texture Feature Extraction Technique Volume 118 No. 17 2018, 691-701 ISSN: 1311-8080 (printed version); ISSN: 1314-3395 (on-line version) url: http://www.ijpam.eu ijpam.eu Hybrid Approach for MRI Human Head Scans Classification using HTT

More information

Detection of Leukemia in Blood Microscope Images

Detection of Leukemia in Blood Microscope Images I J C T A, 9(5), 2016, pp. 63-67 International Science Press Detection of Leukemia in Blood Microscope Images Indira P.*, Ganesh Babu T. R.**, Vidhya K.*** ABSTRACT Leukemia is a cancer of the blood and

More information

CHAPTER-1 INTRODUCTION

CHAPTER-1 INTRODUCTION CHAPTER-1 INTRODUCTION 1.1 Fuzzy concept, digital image processing and application in medicine With the advancement of digital computers, it has become easy to store large amount of data and carry out

More information

Association between pathology and texture features of multi parametric MRI of the prostate

Association between pathology and texture features of multi parametric MRI of the prostate Association between pathology and texture features of multi parametric MRI of the prostate 1,2 Peter Kuess, 3 D. Nilsson, 1,2 P. Andrzejewski, 2,4 P. Georg, 1 J. Knoth, 5 M. Susani, 3 J. Trygg, 2,6 T.

More information

Digital Volume Correlation for Materials Characterization

Digital Volume Correlation for Materials Characterization 19 th World Conference on Non-Destructive Testing 2016 Digital Volume Correlation for Materials Characterization Enrico QUINTANA, Phillip REU, Edward JIMENEZ, Kyle THOMPSON, Sharlotte KRAMER Sandia National

More information

Structural Health Monitoring Using Guided Ultrasonic Waves to Detect Damage in Composite Panels

Structural Health Monitoring Using Guided Ultrasonic Waves to Detect Damage in Composite Panels Structural Health Monitoring Using Guided Ultrasonic Waves to Detect Damage in Composite Panels Colleen Rosania December, Introduction In the aircraft industry safety, maintenance costs, and optimum weight

More information

Hardware Co-Simulation of Skin Burn Image Analysis

Hardware Co-Simulation of Skin Burn Image Analysis Hardware Co-Simulation of Skin Burn Image Analysis Deepak L 1, Joseph Antony 2, Dr. U C Niranjan 3 1 Student, Dept. of E&C, National Institute of Technology Karnataka, Surathkal 2 Asst. Professor, Dept.

More information

Review on Different Segmentation Techniques For Lung Cancer CT Images

Review on Different Segmentation Techniques For Lung Cancer CT Images Review on Different Segmentation Techniques For Lung Cancer CT Images Arathi 1, Anusha Shetty 1, Madhushree 1, Chandini Udyavar 1, Akhilraj.V.Gadagkar 2 1 UG student, Dept. Of CSE, Srinivas school of engineering,

More information

Wavelet-based Texture Classification of Tissues in Computed Tomography

Wavelet-based Texture Classification of Tissues in Computed Tomography Wavelet-based Texture Classification of Tissues in Computed Tomography Lindsay Semler, Lucia Dettori, Jacob Furst Intelligent Multimedia Processing Laboratory School of Computer Science, Telecommunications,

More information

Medical Image Retrieval Performance Comparison using Texture Features

Medical Image Retrieval Performance Comparison using Texture Features International Journal of Engineering Research and Development e-issn: 2278-067X, p-issn: 2278-800X, www.ijerd.com Volume 9, Issue 9 (January 2014), PP. 30-34 Medical Image Retrieval Performance Comparison

More information

Integration of thermographic data with the 3D object model by M. Kaczmarek*

Integration of thermographic data with the 3D object model by M. Kaczmarek* Integration of thermographic data with the 3D object model by M. Kaczmarek* * Gdansk Univ. of Technology,Gdansk, Narutowicza 11/12, 80-233,Poland, mariusz.kaczmarek@eti.pg.gda.pl Abstract The aim of the

More information

Volume 2, Issue 9, September 2014 ISSN

Volume 2, Issue 9, September 2014 ISSN Fingerprint Verification of the Digital Images by Using the Discrete Cosine Transformation, Run length Encoding, Fourier transformation and Correlation. Palvee Sharma 1, Dr. Rajeev Mahajan 2 1M.Tech Student

More information

Three Dimensional Texture Computation of Gray Level Co-occurrence Tensor in Hyperspectral Image Cubes

Three Dimensional Texture Computation of Gray Level Co-occurrence Tensor in Hyperspectral Image Cubes Three Dimensional Texture Computation of Gray Level Co-occurrence Tensor in Hyperspectral Image Cubes Jhe-Syuan Lai 1 and Fuan Tsai 2 Center for Space and Remote Sensing Research and Department of Civil

More information

Estimating the wavelength composition of scene illumination from image data is an

Estimating the wavelength composition of scene illumination from image data is an Chapter 3 The Principle and Improvement for AWB in DSC 3.1 Introduction Estimating the wavelength composition of scene illumination from image data is an important topics in color engineering. Solutions

More information

AN EFFICIENT SKULL STRIPPING ALGORITHM USING CONNECTED REGIONS AND MORPHOLOGICAL OPERATION

AN EFFICIENT SKULL STRIPPING ALGORITHM USING CONNECTED REGIONS AND MORPHOLOGICAL OPERATION AN EFFICIENT SKULL STRIPPING ALGORITHM USING CONNECTED REGIONS AND MORPHOLOGICAL OPERATION Shijin Kumar P. S. 1 and Dharun V. S. 2 1 Department of Electronics and Communication Engineering, Noorul Islam

More information

Detection and Identification of Lung Tissue Pattern in Interstitial Lung Diseases using Convolutional Neural Network

Detection and Identification of Lung Tissue Pattern in Interstitial Lung Diseases using Convolutional Neural Network Detection and Identification of Lung Tissue Pattern in Interstitial Lung Diseases using Convolutional Neural Network Namrata Bondfale 1, Asst. Prof. Dhiraj Bhagwat 2 1,2 E&TC, Indira College of Engineering

More information

CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR)

CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR) 63 CHAPTER 4 SEMANTIC REGION-BASED IMAGE RETRIEVAL (SRBIR) 4.1 INTRODUCTION The Semantic Region Based Image Retrieval (SRBIR) system automatically segments the dominant foreground region and retrieves

More information

UGviewer: a medical image viewer

UGviewer: a medical image viewer Appendix A UGviewer: a medical image viewer As a complement to this master s thesis, an own medical image viewer was programmed. This piece of software lets the user visualize and compare images. Designing

More information

Computer Aided Diagnosis Based on Medical Image Processing and Artificial Intelligence Methods

Computer Aided Diagnosis Based on Medical Image Processing and Artificial Intelligence Methods International Journal of Information and Computation Technology. ISSN 0974-2239 Volume 3, Number 9 (2013), pp. 887-892 International Research Publications House http://www. irphouse.com /ijict.htm Computer

More information

Feature Extraction and Texture Classification in MRI

Feature Extraction and Texture Classification in MRI Extraction and Texture Classification in MRI Jayashri Joshi, Mrs.A.C.Phadke. Marathwada Mitra Mandal s College of Engineering, Pune.. Maharashtra Institute of Technology, Pune. kjayashri@rediffmail.com.

More information

CHAPTER 6 PROPOSED HYBRID MEDICAL IMAGE RETRIEVAL SYSTEM USING SEMANTIC AND VISUAL FEATURES

CHAPTER 6 PROPOSED HYBRID MEDICAL IMAGE RETRIEVAL SYSTEM USING SEMANTIC AND VISUAL FEATURES 188 CHAPTER 6 PROPOSED HYBRID MEDICAL IMAGE RETRIEVAL SYSTEM USING SEMANTIC AND VISUAL FEATURES 6.1 INTRODUCTION Image representation schemes designed for image retrieval systems are categorized into two

More information

An Intelligent Clustering Algorithm for High Dimensional and Highly Overlapped Photo-Thermal Infrared Imaging Data

An Intelligent Clustering Algorithm for High Dimensional and Highly Overlapped Photo-Thermal Infrared Imaging Data An Intelligent Clustering Algorithm for High Dimensional and Highly Overlapped Photo-Thermal Infrared Imaging Data Nian Zhang and Lara Thompson Department of Electrical and Computer Engineering, University

More information

Parameter Optimization for Mammogram Image Classification with Support Vector Machine

Parameter Optimization for Mammogram Image Classification with Support Vector Machine , March 15-17, 2017, Hong Kong Parameter Optimization for Mammogram Image Classification with Support Vector Machine Keerachart Suksut, Ratiporn Chanklan, Nuntawut Kaoungku, Kedkard Chaiyakhan, Nittaya

More information

NAME :... Signature :... Desk no. :... Question Answer

NAME :... Signature :... Desk no. :... Question Answer Written test Tuesday 19th of December 2000. Aids allowed : All usual aids Weighting : All questions are equally weighted. NAME :................................................... Signature :...................................................

More information

MEDICAL IMAGE ANALYSIS

MEDICAL IMAGE ANALYSIS SECOND EDITION MEDICAL IMAGE ANALYSIS ATAM P. DHAWAN g, A B IEEE Engineering in Medicine and Biology Society, Sponsor IEEE Press Series in Biomedical Engineering Metin Akay, Series Editor +IEEE IEEE PRESS

More information

Three-dimensional nondestructive evaluation of cylindrical objects (pipe) using an infrared camera coupled to a 3D scanner

Three-dimensional nondestructive evaluation of cylindrical objects (pipe) using an infrared camera coupled to a 3D scanner Three-dimensional nondestructive evaluation of cylindrical objects (pipe) using an infrared camera coupled to a 3D scanner F. B. Djupkep Dizeu, S. Hesabi, D. Laurendeau, A. Bendada Computer Vision and

More information

Image Processing Techniques for Brain Tumor Extraction from MRI Images using SVM Classifier

Image Processing Techniques for Brain Tumor Extraction from MRI Images using SVM Classifier Image Processing Techniques for Brain Tumor Extraction from MRI Images using SVM Classifier Mr. Ajaj Khan M. Tech (CSE) Scholar Central India Institute of Technology Indore, India ajajkhan72@gmail.com

More information

3D VISUALIZATION OF SEGMENTED CRUCIATE LIGAMENTS 1. INTRODUCTION

3D VISUALIZATION OF SEGMENTED CRUCIATE LIGAMENTS 1. INTRODUCTION JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 10/006, ISSN 164-6037 Paweł BADURA * cruciate ligament, segmentation, fuzzy connectedness,3d visualization 3D VISUALIZATION OF SEGMENTED CRUCIATE LIGAMENTS

More information

Babu Madhav Institute of Information Technology Years Integrated M.Sc.(IT)(Semester - 7)

Babu Madhav Institute of Information Technology Years Integrated M.Sc.(IT)(Semester - 7) 5 Years Integrated M.Sc.(IT)(Semester - 7) 060010707 Digital Image Processing UNIT 1 Introduction to Image Processing Q: 1 Answer in short. 1. What is digital image? 1. Define pixel or picture element?

More information

LITERATURE SURVEY ON DETECTION OF LUMPS IN BRAIN

LITERATURE SURVEY ON DETECTION OF LUMPS IN BRAIN LITERATURE SURVEY ON DETECTION OF LUMPS IN BRAIN Pritam R. Dungarwal 1 and Prof. Dinesh D. Patil 2 1 M E.(CSE),Research Scholar, SSGBCOET,Bhusawal, pritam 2 HOD(CSE), SSGBCOET,Bhusawal Abstract: Broadly,

More information

Automatic Detection and Segmentation of Kidneys in Magnetic Resonance Images Using Image Processing Techniques

Automatic Detection and Segmentation of Kidneys in Magnetic Resonance Images Using Image Processing Techniques Biomedical Statistics and Informatics 2017; 2(1): 22-26 http://www.sciencepublishinggroup.com/j/bsi doi: 10.11648/j.bsi.20170201.15 Automatic Detection and Segmentation of Kidneys in Magnetic Resonance

More information

maximum likelihood estimates. The performance of

maximum likelihood estimates. The performance of International Journal of Computer Science and Telecommunications [Volume 2, Issue 6, September 2] 8 ISSN 247-3338 An Efficient Approach for Medical Image Segmentation Based on Truncated Skew Gaussian Mixture

More information

Color Local Texture Features Based Face Recognition

Color Local Texture Features Based Face Recognition Color Local Texture Features Based Face Recognition Priyanka V. Bankar Department of Electronics and Communication Engineering SKN Sinhgad College of Engineering, Korti, Pandharpur, Maharashtra, India

More information

Texture Analysis in Quantitative Osteoporosis Assessment

Texture Analysis in Quantitative Osteoporosis Assessment Texture Analysis in Quantitative Osteoporosis Assessment Characterizing Micro-architecture in High Resolution Peripheral Quantitative Computed Tomography Alexander Valentinitsch 1, Janina Patsch 1, Dirk

More information

A New GPU-Based Level Set Method for Medical Image Segmentation

A New GPU-Based Level Set Method for Medical Image Segmentation A New GPU-Based Level Set Method for Medical Image Segmentation Wenzhe Xue Research Assistant Radiology Department Mayo Clinic, Scottsdale, AZ Ph.D. Student Biomedical Informatics Arizona State University,

More information

Biomedical Image Processing for Human Elbow

Biomedical Image Processing for Human Elbow Biomedical Image Processing for Human Elbow Akshay Vishnoi, Sharad Mehta, Arpan Gupta Department of Mechanical Engineering Graphic Era University Dehradun, India akshaygeu001@gmail.com, sharadm158@gmail.com

More information

Time Stamp Detection and Recognition in Video Frames

Time Stamp Detection and Recognition in Video Frames Time Stamp Detection and Recognition in Video Frames Nongluk Covavisaruch and Chetsada Saengpanit Department of Computer Engineering, Chulalongkorn University, Bangkok 10330, Thailand E-mail: nongluk.c@chula.ac.th

More information

Abbie M. Diak, PhD Loyola University Medical Center Dept. of Radiation Oncology

Abbie M. Diak, PhD Loyola University Medical Center Dept. of Radiation Oncology Abbie M. Diak, PhD Loyola University Medical Center Dept. of Radiation Oncology Outline High Spectral and Spatial Resolution MR Imaging (HiSS) What it is How to do it Ways to use it HiSS for Radiation

More information

Image Registration. Prof. Dr. Lucas Ferrari de Oliveira UFPR Informatics Department

Image Registration. Prof. Dr. Lucas Ferrari de Oliveira UFPR Informatics Department Image Registration Prof. Dr. Lucas Ferrari de Oliveira UFPR Informatics Department Introduction Visualize objects inside the human body Advances in CS methods to diagnosis, treatment planning and medical

More information

Keywords Binary Linked Object, Binary silhouette, Fingertip Detection, Hand Gesture Recognition, k-nn algorithm.

Keywords Binary Linked Object, Binary silhouette, Fingertip Detection, Hand Gesture Recognition, k-nn algorithm. Volume 7, Issue 5, May 2017 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Hand Gestures Recognition

More information

Object Identification in Ultrasound Scans

Object Identification in Ultrasound Scans Object Identification in Ultrasound Scans Wits University Dec 05, 2012 Roadmap Introduction to the problem Motivation Related Work Our approach Expected Results Introduction Nowadays, imaging devices like

More information

Detection of Bone Fracture using Image Processing Methods

Detection of Bone Fracture using Image Processing Methods Detection of Bone Fracture using Image Processing Methods E Susmitha, M.Tech Student, Susmithasrinivas3@gmail.com Mr. K. Bhaskar Assistant Professor bhasi.adc@gmail.com MVR college of engineering and Technology

More information

Texture Segmentation by Windowed Projection

Texture Segmentation by Windowed Projection Texture Segmentation by Windowed Projection 1, 2 Fan-Chen Tseng, 2 Ching-Chi Hsu, 2 Chiou-Shann Fuh 1 Department of Electronic Engineering National I-Lan Institute of Technology e-mail : fctseng@ccmail.ilantech.edu.tw

More information

Available online Journal of Scientific and Engineering Research, 2019, 6(1): Research Article

Available online   Journal of Scientific and Engineering Research, 2019, 6(1): Research Article Available online www.jsaer.com, 2019, 6(1):193-197 Research Article ISSN: 2394-2630 CODEN(USA): JSERBR An Enhanced Application of Fuzzy C-Mean Algorithm in Image Segmentation Process BAAH Barida 1, ITUMA

More information

Automated segmentation methods for liver analysis in oncology applications

Automated segmentation methods for liver analysis in oncology applications University of Szeged Department of Image Processing and Computer Graphics Automated segmentation methods for liver analysis in oncology applications Ph. D. Thesis László Ruskó Thesis Advisor Dr. Antal

More information

A fast breast nonlinear elastography reconstruction technique using the Veronda-Westman model

A fast breast nonlinear elastography reconstruction technique using the Veronda-Westman model A fast breast nonlinear elastography reconstruction technique using the Veronda-Westman model Mohammadhosein Amooshahi a and Abbas Samani abc a Department of Electrical & Computer Engineering, University

More information

CHAPTER 2 TEXTURE CLASSIFICATION METHODS GRAY LEVEL CO-OCCURRENCE MATRIX AND TEXTURE UNIT

CHAPTER 2 TEXTURE CLASSIFICATION METHODS GRAY LEVEL CO-OCCURRENCE MATRIX AND TEXTURE UNIT CHAPTER 2 TEXTURE CLASSIFICATION METHODS GRAY LEVEL CO-OCCURRENCE MATRIX AND TEXTURE UNIT 2.1 BRIEF OUTLINE The classification of digital imagery is to extract useful thematic information which is one

More information

RADIOMICS: potential role in the clinics and challenges

RADIOMICS: potential role in the clinics and challenges 27 giugno 2018 Dipartimento di Fisica Università degli Studi di Milano RADIOMICS: potential role in the clinics and challenges Dr. Francesca Botta Medical Physicist Istituto Europeo di Oncologia (Milano)

More information

Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform

Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform Semi-Automatic Detection of Cervical Vertebrae in X-ray Images Using Generalized Hough Transform Mohamed Amine LARHMAM, Saïd MAHMOUDI and Mohammed BENJELLOUN Faculty of Engineering, University of Mons,

More information

A COMPARISON OF WAVELET-BASED AND RIDGELET- BASED TEXTURE CLASSIFICATION OF TISSUES IN COMPUTED TOMOGRAPHY

A COMPARISON OF WAVELET-BASED AND RIDGELET- BASED TEXTURE CLASSIFICATION OF TISSUES IN COMPUTED TOMOGRAPHY A COMPARISON OF WAVELET-BASED AND RIDGELET- BASED TEXTURE CLASSIFICATION OF TISSUES IN COMPUTED TOMOGRAPHY Lindsay Semler Lucia Dettori Intelligent Multimedia Processing Laboratory School of Computer Scienve,

More information

CHAPTER 6 DETECTION OF MASS USING NOVEL SEGMENTATION, GLCM AND NEURAL NETWORKS

CHAPTER 6 DETECTION OF MASS USING NOVEL SEGMENTATION, GLCM AND NEURAL NETWORKS 130 CHAPTER 6 DETECTION OF MASS USING NOVEL SEGMENTATION, GLCM AND NEURAL NETWORKS A mass is defined as a space-occupying lesion seen in more than one projection and it is described by its shapes and margin

More information

Classification Algorithm for Road Surface Condition

Classification Algorithm for Road Surface Condition IJCSNS International Journal of Computer Science and Network Security, VOL.4 No., January 04 Classification Algorithm for Road Surface Condition Hun-Jun Yang, Hyeok Jang, Jong-Wook Kang and Dong-Seok Jeong,

More information

Detection & Classification of Lung Nodules Using multi resolution MTANN in Chest Radiography Images

Detection & Classification of Lung Nodules Using multi resolution MTANN in Chest Radiography Images The International Journal Of Engineering And Science (IJES) ISSN (e): 2319 1813 ISSN (p): 2319 1805 Pages 98-104 March - 2015 Detection & Classification of Lung Nodules Using multi resolution MTANN in

More information

Volume 7, Issue 4, April 2017

Volume 7, Issue 4, April 2017 Volume 7, Issue 4, April 2017 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Brain Tumour Extraction

More information

Early Stage Oral Cavity Cancer Detection: Anisotropic Pre-Processing and Fuzzy C-Means Segmentation

Early Stage Oral Cavity Cancer Detection: Anisotropic Pre-Processing and Fuzzy C-Means Segmentation Early Stage Oral Cavity Cancer Detection: Anisotropic Pre-Processing and Fuzzy C-Means Segmentation Zhalong Hu 1 *, Abeer Alsadoon 1 *, Paul Manoranjan 2*, P.W.C. Prasad 1*, Salih Ali 3 * 1 School of Computing

More information

CHAPTER 3 TUMOR DETECTION BASED ON NEURO-FUZZY TECHNIQUE

CHAPTER 3 TUMOR DETECTION BASED ON NEURO-FUZZY TECHNIQUE 32 CHAPTER 3 TUMOR DETECTION BASED ON NEURO-FUZZY TECHNIQUE 3.1 INTRODUCTION In this chapter we present the real time implementation of an artificial neural network based on fuzzy segmentation process

More information

Face identification system using MATLAB

Face identification system using MATLAB Project Report ECE 09.341 Section #3: Final Project 15 December 2017 Face identification system using MATLAB Stephen Glass Electrical & Computer Engineering, Rowan University Table of Contents Introduction

More information

Volume Illumination and Segmentation

Volume Illumination and Segmentation Volume Illumination and Segmentation Computer Animation and Visualisation Lecture 13 Institute for Perception, Action & Behaviour School of Informatics Overview Volume illumination Segmentation Volume

More information

Statistical Evaluation of Law s Mask Texture Analysis for Osteoporosis Detection

Statistical Evaluation of Law s Mask Texture Analysis for Osteoporosis Detection Statistical Evaluation of Law s Mask Texture Analysis for Osteoporosis Detection GAN HONG SENG, HUM YAN CHAI, TAN TIAN SWEE Department of Biomechanics and Biomedical Materials Medical Implant Technology

More information

Computer Assisted Image Analysis TF 3p and MN1 5p Lecture 1, (GW 1, )

Computer Assisted Image Analysis TF 3p and MN1 5p Lecture 1, (GW 1, ) Centre for Image Analysis Computer Assisted Image Analysis TF p and MN 5p Lecture, 422 (GW, 2.-2.4) 2.4) 2 Why put the image into a computer? A digital image of a rat. A magnification of the rat s nose.

More information

An idea of continuous thermographic monitoring of machinery

An idea of continuous thermographic monitoring of machinery July 2-5, 2008, Krakow - Poland An idea of continuous thermographic monitoring of machinery *Department of Fundamentals of Machinery Design Silesian University of Technology, Gliwice, Poland Abstract M.

More information

Approaches For Automated Detection And Classification Of Masses In Mammograms

Approaches For Automated Detection And Classification Of Masses In Mammograms www.ijecs.in International Journal Of Engineering And Computer Science ISSN:2319-7242 Volume 3, Issue 11 November, 2014 Page No. 9097-9011 Approaches For Automated Detection And Classification Of Masses

More information

Uma Yadav Assistant Professor, Dept. of Computer Science and Engg., G.H. Raisoni College of Engineering, Nagpur(MS), India

Uma Yadav Assistant Professor, Dept. of Computer Science and Engg., G.H. Raisoni College of Engineering, Nagpur(MS), India Volume 7, Issue 4, April 2017 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Identification

More information

Carestream s 2 nd Generation Metal Artifact Reduction Software (CMAR 2)

Carestream s 2 nd Generation Metal Artifact Reduction Software (CMAR 2) Carestream s 2 nd Generation Metal Artifact Reduction Software (CMAR 2) Author: Levon Vogelsang Introduction Cone beam computed tomography (CBCT), or cone beam CT technology, offers considerable promise

More information

Digital Image Processing

Digital Image Processing Digital Image Processing Part 9: Representation and Description AASS Learning Systems Lab, Dep. Teknik Room T1209 (Fr, 11-12 o'clock) achim.lilienthal@oru.se Course Book Chapter 11 2011-05-17 Contents

More information

COMPUTER PROGRAM FOR IMAGE TEXTURE ANALYSIS IN PhD STUDENTS LABORATORY

COMPUTER PROGRAM FOR IMAGE TEXTURE ANALYSIS IN PhD STUDENTS LABORATORY P. Szczypiński, M. Kociołek, A. Materka, M. Strzelecki, Computer Program for Image Texture Analysis in PhD Students Laboratory, International Conference on Signals and Electronic Systems, Łódź-Poland 00,

More information

APREMISE to a supervised classifier is that the training

APREMISE to a supervised classifier is that the training A contextual classifier that only requires one prototype pixel for each class Gabriela Maletti, Bjarne Ersbøll and Knut Conradsen Abstract A three stage scheme for classification of multi-spectral images

More information