Lung cancer detection using digital image processing

April 2, 2018 | Author: pandi | Category: Matlab, Data Compression, Ct Scan, Image Segmentation, Graphical User Interfaces


Comments



Description

ABSTRACTDetection of lung cancer is the most interesting research area of researcher's in early stages. The proposed system is designed to detect lung cancer in premature stage in two stages. The proposed system consists of many steps such as image acquisition, preprocessing, binarization, thresholding, segmentation, feature extraction, and neural network detection. At first Input lung CT images to the system and then passed through the image preprocessing stage by using some image processing techniques. In first stage, Binarization technique is used to convert binary image and then compare it with threshold value to detect lung cancer. In second stage, segmentation is performed to segment the lung CT image and a strong feature extraction method has been introduced to extract the some important feature of segmented images. Extracted features are used to train the neural network and finally the system is tested any cancerous and noncancerous images. The performance of proposed system shows satisfactory results and proposed method gives 96.67% accuracy. 1 CHAPTER I INTRODUCTION 1.1 GENERAL The term digital image refers to processing of a two dimensional picture by a digital computer. In a broader context, it implies digital processing of any two dimensional data. A digital image is an array of real or complex numbers represented by a finite number of bits. An image given in the form of a transparency, slide, photograph or an X-ray is first digitized and stored as a matrix of binary digits in computer memory. This digitized image can then be processed and/or displayed on a high-resolution television monitor. For display, the image is stored in a rapid-access buffer memory, which refreshes the monitor at a rate of 25 frames per second to produce a visually continuous display. 1.1.1 THE IMAGE PROCESSING SYSTEM Digitizer Mass Storage Image Digital Operator Processor Computer Console Hard Copy Device Display FIG 1.1 BLOCK DIAGRAM FOR IMAGE PROCESSING SYSTEM 2 DIGITIZER: A digitizer converts an image into a numerical representation suitable for input into a digital computer. Some common digitizers are 1. Microdensitometer 2. Flying spot scanner 3. Image dissector 4. Videocon camera 5. Photosensitive solid- state arrays. IMAGE PROCESSOR: An image processor does the functions of image acquisition, storage, preprocessing, segmentation, representation, recognition and interpretation and finally displays or records the resulting image. The following block diagram gives the fundamental sequence involved in an image processing system. Problem Image Representation & Segmentation Domain Acquisition Description n Knowledge Result Preprocessing Recognition & interpretation Base FIG 1.2 BLOCK DIAGRAM OF FUNDAMENTAL SEQUENCE INVOLVED IN AN IMAGE PROCESSING SYSTEM 3 As detailed in the diagram, the first step in the process is image acquisition by an imaging sensor in conjunction with a digitizer to digitize the image. The next step is the preprocessing step where the image is improved being fed as an input to the other processes. Preprocessing typically deals with enhancing, removing noise, isolating regions, etc. Segmentation partitions an image into its constituent parts or objects. The output of segmentation is usually raw pixel data, which consists of either the boundary of the region or the pixels in the region themselves. Representation is the process of transforming the raw pixel data into a form useful for subsequent processing by the computer. Description deals with extracting features that are basic in differentiating one class of objects from another. Recognition assigns a label to an object based on the information provided by its descriptors. Interpretation involves assigning meaning to an ensemble of recognized objects. The knowledge about a problem domain is incorporated into the knowledge base. The knowledge base guides the operation of each processing module and also controls the interaction between the modules. Not all modules need be necessarily present for a specific function. The composition of the image processing system depends on its application. The frame rate of the image processor is normally around 25 frames per second. DIGITAL COMPUTER: Mathematical processing of the digitized image such as convolution, averaging, addition, subtraction, etc. are done by the computer. MASS STORAGE: The secondary storage devices normally used are floppy disks, CD ROMs etc. HARD COPY DEVICE: The hard copy device is used to produce a permanent copy of the image and for the storage of the software involved. 4 IMAGE PROCESSING TECHNIQUES: This section gives various image processing techniques. Then these images are processed by the five fundamental processes. not necessarily all of them. 1. The operator is also capable of checking for any resulting errors and for the entry of requisite data. The digitalization process includes sampling.2 IMAGE PROCESSING FUNDAMENTAL: Digital image processing refers processing of the image in digital form. at least any one of them.1. They are captured by video cameras and digitalized. quantization. Image Enhancement Image Restoration IP Image Analysis Image Compression Image Synthesis 5 . Modern cameras may directly take the image in digital form but generally images are originated in optical form.OPERATOR CONSOLE: The operator console consists of equipment and arrangements for verification of intermediate results and for alterations in the software as and when require. or degradations of the original image. IMAGE COMPRESSION: Image compression and decompression reduce the data content necessary to describe the image. It is used to correct images for known degradations.3: IMAGE PROCESSING TECHNIQUES MAGE ENHANCEMENT: Image enhancement operations improve the qualities of an image like improving the image’s contrast and brightness characteristics. improper focus. They depend on the image statistics. and object classification. Image restorations are used to restore images with problems such as geometric distortion. so efficiently stored or 6 . and camera motion. This just enhances the image and reveals the same information in more understandable image. measured. automated measurements. IMAGE RESTORATION: Image restoration like enhancement improves the qualities of image but all the operations are mainly based on known. IMAGE ANALYSIS: Image analysis operations produce numerical or graphical information based on characteristics of the original image. Most of the images contain lot of redundant information. Common operations are extraction and description of scene and image features. Because of the compression the size is reduced. compression removes all the redundancies. It does not add any information to it. Image analyze are mainly used in machine vision applications. reducing its noise content. or sharpen the details. repetitive noise. They break into objects and then classify them. FIG1. and 7 . The compressed image is decompressed when displayed. medical processing. radar. but Lossy compression does not represent the original image but provide excellent compression. sonar and acoustic image processing. geographical mapping. IMAGE SYNTHESIS: Image synthesis operations create images from other images or non-image data. cineangiograms. image transmission and storage for business applications. prediction of agricultural crops. one is concerned with processing of chest X-rays. SATELLITE IMAGING: Images acquired by satellites are useful in tracking of earth resources. nuclear magnetic resonance (NMR) and ultrasonic scanning. Lossless compression preserves the exact data in the original image. Image synthesis operations generally create images that are either physically impossible or impractical to acquire. APPLICATIONS OF DIGITAL IMAGE PROCESSING: Digital image processing has a broad spectrum of applications. MEDICAL APPLICATIONS: In medical applications. projection images of transaxial tomography and other medical images that occur in radiology.transported. flood and fire control. urban growth and weather. robotics and automated inspection of industrial parts. These images may be used for patient screening and monitoring or for detection of tumors’ or other disease in patients. such as remote sensing via satellites and other spacecrafts. closed-circuit television based security monitoring systems and in military communications. and transmission for converting paper documents to a digital image form. compressing the image. It is also used in document reading for automatically detecting and recognizing printed characteristics. teleconferencing. COMMUNICATION: Image transmission and storage applications occur in broadcast television. and storing it on magnetic tape. Space image applications include recognition and analysis of objects contained in image obtained from deep space-probe missions.many other environmental applications. communication of computer networks. DEFENSE/INTELLIGENCE: It is used in reconnaissance photo-interpretation for automatic interpretation of earth satellite imagery to look for sensitive targets or military threats and target acquisition and guidance for recognizing and tracking targets in real-time smart-bomb and missile-guidance systems. RADAR IMAGING SYSTEMS: Radar and sonar images are used for detection and recognition of various types of targets or in guidance and maneuvering of aircraft or missile systems. and transmission of facsimile images for office automation. SCOPE OF THE PROJECT: 8 . DOCUMENT PROCESSING: It is used in scanning. Michelle S. hundreds of such thin-sectional CT images are generated for each patient and are evaluated by a radiologist in the traditional sense of looking at each image in the axial mode. Information about nodules such as size and compact shape are then incorporated into the algorithm to reduce the detected nodule candidates which are not likely to be nodules. Higher density structures including nodules scattered throughout the lungs can be identified by using a local density maximum algorithm. Schwartz-2003 Increasingly. 9 . In this paper. we present a computerized method for automated identification of small lung nodules on multi slice CT (MSCT) images. on average. Binsheng Zhao*. The preliminary results demonstrate the potential of this technique for assisting the detection of small nodules from chest MSCT images. Gordon Gamsu. This results in the potential to miss small nodules and thus potentially miss a cancer. Ginsberg. computed tomography (CT) offers higher resolution and faster acquisition times. LITERATURE SURVEY: 1. in the current clinical practice. Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm. a supervised classifier was designed through combining level-nodule probability and level context probability. In this paper. Li Jiang. and ~iii! reduction of false-positives among the detected nodule candidates. A three-dimensional lung mask can be extracted by analyzing density histogram of volumetric chest images followed by a morphological operation. The results from the experiments on the ELCAP dataset showed promising performance of our method. The method was applied to the detection of computer simulated small lung nodules (2 to 7 mm in diameter) and achieved a sensitivity of 84. The method consists of three steps: (i) separation of the lungs from the other anatomic structures. However.2% with. We also suggest that the proposed method can be generally applicable to other medical or general imaging domains. which may represent lung cancers at earlier and potentially more curable stages. This has resulted in the opportunity to detect small lung nodules. and Lawrence H. (ii) detection of nodule candidates in the extracted lungs. five false-positive results per scan. we devise an approach to estimate the gray level intensity distribution (Hounsfield Units) and a figure of merit of the size of appropriate templates.. Salwa Elshazly and Robert Falk*. The performance of the new nodule templates will be evaluated during the detection step and compared with the use of parametric templates and another non-parametric Active Appearance model to explain the advantages and/or disadvantages of using parametric vs. Salwa A. Farag. Elhabian. The paper presents an extensive study of the sensitivity and specificity of the nodule detection step.2007 Lung nodule modeling quality defines the success of lung nodule detection. in which the quality of the nodule model is the driving factor. Overall. Quantification of Nodule Detection in Chest CT: A Clinical Investigation Based on the ELCAP Study Amal A. Elshazly and Aly A. non-parametric models as well as which variation of nonparametric template design.e. Farag. The paper also shows that isotropic templates do not provide adequate detection rate (in terms of sensitivity and specificity) of vascularized nodules. Parametric and Non-Parametric Nodule Models: Design and Evaluation Amal A. Farag– 2008 This paper examines the detection step in automatic detection and classification of lung nodules from low-dose CT (LDCT) scans. validation of the detection approach on labeled clinical dataset from the Early Lung Cancer Action Project (ELCAP) screening study is conducted. Aly A. specified by radiologists. From an ensemble of nodules. and the effect of these models on the detection process. This paper presents a novel method for generating lung nodules using variational level sets to obtain the shape properties of real nodules to form an average model template per nodule type.2. Farag. Finally. which can be used to automatically select the template size. a data-driven approach is used to design the templates. The nodule models in this paper can be used in various machine learning approaches for automatic nodule detection and classification. 3. Two issues are studied in detail: nodule modeling and simulation. shape based or shape-texture based yields better results in the overall detection process. this paper shows a relationship between the spatial support of the nodule templates and the resolution of the LDCT. Shireen Y. There are two main categories that lung nodule models fall within. i. James Graham. parametric and non-parametric. 10 . The texture information used for filling the nodules is based on a devised approach that uses the probability density of the radial distance of each nodule to obtain the maximum and minimum Hounsfield density (HU). Hence. which are then used to detect candidate nodules based on optimum similarity measured by the normalized cross-correlation (NCC). These thin- slice chest scans have become indispensable in thoracic radiology. Automating the analysis of such data is. using active appearance models (AAM). Computer Analysis of Computed Tomography Scans of the Lung: a Survey Ingrid Sluimer. salwa elshazly and robert falk*– 2011 This paper examines the effectiveness of geometric feature descriptors. 5. research trends and challenges are identified and directions for future research are discussed. Mathias Prokop. In addition. classification and quantification of chest abnormalities. james graham. but have also substantially increased the data load for radiologists. Current computed tomography (CT) technology allows for near isotropic. and applications aimed at detection. evaluation of geometric feature descriptors for detection and classification of lung nodules in low dose ct scans of the chest amal farag. A data-driven lung nodule modeling approach creates templates for common nodule types. therefore. and Bram van Ginneken *. a necessity and this has created a rapidly developing research area in medical imaging. common in computer vision. 11 . This paper presents a review of the literature on computer analysis of the lungs in CT scans and addresses segmentation of various pulmonary structures. Member. Results on the clinical ELCAP database showed that the descriptors provide 2% enhancements in the specificity of the detected nodule above the NCC results when used in a k-NN classifier. Geometric feature descriptors (e. registration of chest scans. Thus quantitative measures of enhancements of the performance of CAD models based on LDCT are now possible and are entirely model-based most importantly. IEEE– 2005 In this paper.4. asem ali.. in order to extract features from the nodule candidates. sub millimeter resolution acquisition of the complete chest in a single breath hold. for false positive reduction and for classification of lung nodules in low dose CT (LDCT) scans. for further enhancement of output and possible reduction of false positives. aly farag. Arnold Schilham.g. SIFT. LBP and SURF) are applied to the output of the detection step. our approach is applicable for classification of nodules into categories and pathologies. and are capable of analyzing the large number of small nodules identified by CT scans. CHAPTER 2 INTRODUCTION: LUNG cancer is a major cause of cancer-related deaths in humans worldwide. interpretation of CT images is challenging for radiologists due to the large number of cases. At present. the identification of potentially malignant lung nodules is essential for the screening and diagnosis of lung cancer. and are usually spherical. and pleural-tail (P) with the nodule near the pleural surface connected by a thin tail. however. vascularized (V) with the nodule located centrally in the lung but closely connected to neighboring vessels. is the most popular approach and it divides nodules into four types: well-circumscribed (W) with the nodule located centrally in the lung without any connection to vasculature. they can be distorted by surrounding anatomical structures. which may represent lung cancers at earlier and potentially more curable stages. Lung nodules are small masses in the human lung. such as vessels and the adjacent pleura. juxta-pleural (J) with a large portion of the nodule connected to the pleural surface. Intraparenchymal lung nodules are more likely to be malignant than those connected with the surrounding structures. CADs provide depiction by automatically computing quantitative measures. computed tomography (CT) offers higher resolution and faster acquisition times. Computer-aided diagnosis (CAD) systems would be helpful for radiologists by offering initial screening or second opinions to classify lung nodules. In this 12 . In current clinical practice. the classification from Diciotti et al. Computed tomography (CT) is the most accurate imaging modality to obtain anatomical information about lung nodules and the surrounding structures. however. This has resulted in the opportunity to detect small lung nodules. This results in the potential to miss small nodules and thus potentially miss a cancer. therefore. and thus lung nodules are divided into different types according to their relative positions. hundreds of such thin-sectional CT images are generated for each patient and are evaluated by a radiologist in the traditional sense of looking at each image in the axial mode. Approximately 20% of cases with lung nodules represent lung cancers. However. This manual reading can be error-prone and the reader may miss nodules and thus a potential cancer. Increasingly. in the current clinical practice. The system has been collected total 300 Lung CT images that are cancer and normal image of lung from the Internet and Hospital. Computed tomography is an imaging procedure. The system used Lung CT images that are jpeg file format. 13 .paper. we present a computerized method for automated identification of small lung nodules on multislice images DATAFLOW DIAGRAM: A. Image Acquisition Normally a special type of digital X-Ray machine is used to acquire detailed pictures or scans of areas inside the body called computerized tomography (CT). the system use the Matlab function im2bw. Image Preprocessing After Image Acquisition. medfilt2. Fig.e. A median filter is more effective than convolution when the goal IS to simultaneously reduce noise and preserve edges. 1) Gray Scale Conversion RGB image converted into gray scale image by using the Matlab function rgb2gray. 14 . 2) Normalization Normalize the acquired image by using the Matlab function imresize.B. 3) Noise Reduction To remove the noise the system used median filter i. that is an image with pixels O's (white) and I 's (black). 2 shows the block diagram of image preprocessing steps. 4) Binary Image Noise free gray scale image is converted to binary image. Medfilt2 is 2-D median filter. The system uses imresize function with the value of 150 x 140 pixels and 200 x 250 pixels. images are passed through the image preprocessing steps. It converts RGB image or color image to grayscale by eliminating the hue and saturation information while retaining the luminance. To convert gray scale image into binary image. Median filtering is a nonlinear operation often used in image processing to reduce "salt and pepper" noise. This size gives enough information of the image when the processing time is low. E.5) Remove unwanted portion of the image Converting into binary image. Thresholding Method Thresholding method is based on a threshold value to turn a gray-scale image into a binary image. The goal of segmentation is to simplify and/or change the representation of an image into more meaningful and easier to analyze. D. In the proposed system.) in images. we have to remove the unnecessary pixels (0) from original image. curves. Recently. if the percentage of white pixels is greater than the Thresh2 and Thresh3. In binary CT image. etc. then the right lung and left lung respectively is affected. is the process of partitioning a digital image into multiple segments. This is done because we need to develop size independent algorithm. image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics. Threshlo Threshz. The key idea of this method is to select the threshold value (or values when multiple levels are selected). and Thresh3. Image segmentation is typically used to locate objects and boundaries (lines. 15 . The proposed system used three types of threshold value i. segmentation processes consists of different steps. methods have been developed for thresholding computed tomography (CT) images. if the percentage of white pixels is greater than the Thresh).e. More precisely. Segmentation Image Segmentation in computer vision system. In segmented binary image. then full lung is affected. The simplest method of image segmentation is called the thresholding method. 16 . these features are passed through the neural network to train up the system for classification purpose or detection purpose. Feature Extraction The system has been used a rotation and size independent feature extraction method to extract the feature of the lung cancer and finally obtain 33 features for each type of lung cancer CT images. rest of the Lung Cancer Detection System uses neural network which is very efficient and reliable.Image Acquisition. G. Neural Network Classification. Neural Network Detection After the Thresholding method.F. Feature Extraction. Image Preprocessing. After the feature extraction process. The whole proposed training system of lung cancer detection consist of the following steps. Segmentation. 14 Version MATLAB MATLAB is a high-performance language for technical computing. It integrates computation. Multichannel images are created using co-registered multimodality images of the same subject to utilize information across modalities comprehensively. the proposed method uses feature-level information fusion method to spatio-adaptively combine the complementary information from different modalities that characterize different tissue types.1 GENERAL This paper proposes a novel non rigid inter-subject multichannel image registration method which combines information from different modalities/channels to produce a unified joint registration. through Gabor wavelets transformation and Independent Component Analysis (ICA). to produce a robust inter-subject registration. and programming in an easy-to-use environment where problems and solutions are expressed in familiar mathematical notation. Contrary to the existing methods which combine the information at the image/intensity level. visualization. 3. CHAPTER 3 SOFTWARE SPECIFICATION 3.2 SOFTWARE REQUIREMENTS  MATLAB 7. Typical uses include:  Math and computation 17 . Developed by Math Works. and Fortran. plotting of functions and data.  Algorithm development  Modeling.3 INTRODUCTION MATLAB (matrix laboratory) is a numerical computing environment and fourth-generation programming language. and visualization  Scientific and engineering graphics. Simulink. MATLAB allows matrix manipulations. implementation of algorithms. This allows you to solve many technical computing problems. and prototyping  Data analysis. adds graphical multi-domain simulation and Model-Based Design for dynamic and embedded systems. an optional toolbox uses the MuPADsymbolic engine. Java. allowing access to symbolic computing capabilities. 18 . including C. Although MATLAB is intended primarily for numerical computing. including Graphical User Interface building MATLAB is an interactive system whose basic data element is an array that does not require dimensioning. and interfacing with programs written in other languages. simulation. in a fraction of the time it would take to write a program in a scalar non-interactive language such as C or FORTRAN 3. exploration. An additional package. especially those with matrix and vector formulations. C++. creation of user interfaces.  Application development. 4 FEATURES OF MATLAB  High-level language for technical computing. and distribute your MATLAB algorithms and applications. extending the commands available. MATLAB users come from various backgrounds of engineering. MATLAB provides a number of features for documenting and sharing your work. MATLAB is widely used in academic and research institutions as well as industrial enterprises. design. 3. and is popular amongst scientists involved in image processing. as a script or encapsulated into a function. You can integrate your MATLAB code with other languages and applications. typically using the MATLAB Editor. In 2004.  Interactive tools for iterative exploration. which is one of the elements of the MATLAB Desktop. When code is entered in the Command Window. The simplest way to execute MATLAB code is to type it in the Command Window. science. MATLAB can be used as an interactive mathematical shell. MATLAB was first adopted by researchers and practitioners in control engineering. in particular the teaching of linear algebra and numerical analysis. Sequences of commands can be saved in a text file. but quickly spread to many other domains. and data. and economics. 19 . and problem solving. The MATLAB application is built around the MATLAB language. Little's specialty. MATLAB had around one million users across industry and academia. It is now also used in education.  Development environment for managing code. files. filtering. the fundamental operators (e. MATLAB is used in vast area.  Tools for building custom graphical user interfaces. optimization. including the Cheaha compute cluster.g. including signal and image processing. C++. COM. Fourier analysis.  2-D and 3-D graphics functions for visualizing data. Fortran. multiplication) are programmed to deal with matrices when required. including for-loop unrolling. Since so many of the procedures required for Macro- Investment Analysis involves matrices. 20 .  Mathematical functions for linear algebra. such as C.  Functions for integrating MATLAB based algorithms with external applications and languages.MATLAB is one of a few languages in which each variable is a matrix (broadly construed) and "knows" how big it is. And the MATLAB environment handles much of the bothersome housekeeping that makes all this possible. With the addition of the Parallel Computing Toolbox. financial modeling and analysis. communications. and computational. statistics. Java™. Moreover. and numerical integration. Add-on toolboxes (collections of special-purpose MATLAB functions) extend the MATLAB environment to solve particular classes of problems in these application areas. test and measurement. MATLAB proves to be an extremely efficient language for both communication and implementation. addition. Additionally this toolbox supports offloading computationally intensive workloads to Cheaha the campus compute cluster. and Microsoft Excel. MATLAB can be used on personal computers and powerful server systems. control design. the language can be extended with parallel implementations for common computational functions. As alternatives to the MuPAD based Symbolic Math Toolbox available from Math Works. Calling MATLAB from Java is more complicated.  Spreadsheet Import Tool that provides more options for selecting and loading mixed textual and numeric data.NET can be directly called from MATLAB and many MATLAB libraries (for example XML or SQL support) are implemented as wrappers around Java or ActiveX libraries. which should not be confused with the unrelated Java that is also called JMI. MATLAB can be connected to Maple or Mathematical. or using an undocumented mechanism called JMI (Java-to-Mat lab Interface). Libraries written in Java. and for network installations. The dynamically loadable object files created by compiling such functions are termed "MEX-files" (for MATLAB executable). which is sold separately by Math Works.4.1 INTERFACING WITH OTHER LANGUAGES MATLAB can call functions and subroutines written in the C programming language or FORTRAN. 21 .  Development Environment  Startup Accelerator for faster MATLAB startup on Windows. ActiveX or . but can be done with MATLAB extension. A wrapper function is created allowing MATLAB data types to be passed and returned. Libraries also exist to import and export MathML.3. especially on Windows XP. enabling you to quickly iterate to the optimal solution. such as declaring variables. flow control. object-oriented programming (OOP). and allocating memory. In many cases. data types.  Developing Algorithms and Applications MATLAB provides a high-level language and development tools that let you quickly develop and analyze your algorithms and applications. specifying data types.  Automatic variable and function renaming in the MATLAB Editor. For fast execution of heavy matrix and vector computations. As a result. MATLAB lets you execute commands or groups of commands one at a time. without compiling and linking. At the same time. including arithmetic operators.  The MATLAB Language The MATLAB language supports the vector and matrix operations that are fundamental to engineering and scientific problems. data structures. MATLAB eliminates the need for ‘for’ loops. one line of MATLAB code can often replace several lines of C or C++ code. It enables fast development and execution. you can program and develop algorithms faster than with traditional languages because you do not need to perform low-level administrative tasks.  Readability and navigation improvements to warning and error messages in the MATLAB command window. and debugging features. 22 . MATLAB provides all the features of a traditional programming language. With the MATLAB language.  Development Tools MATLAB includes development tools that help you implement your algorithm efficiently. This technology. MATLAB generates machine-code instructions using its JIT (Just-In-Time) compilation technology. For general-purpose scalar computations. such as setting breakpoints and single stepping CODE ANALYZER Checks your code for problems and recommends modifications to maximize performance and maintainability MATLAB PROFILER Records the time spent executing each line of code 23 . provides execution speeds that rival those of traditional programming languages. These include the following: MATLAB Editor Provides standard editing and debugging features. MATLAB uses processor-optimized libraries. which is available on most platforms. and browsers for viewing help. Many of these tools are graphical user interfaces. and edit user interfaces. Alternatively. This is the set of tools and facilities that help you use MATLAB functions and files. and sliders. 24 . as well as MATLAB plots and Microsoft ActiveX® controls. design.  The MATLAB Mathematical Function Library. and code coverage DESIGNING GRAPHICAL USER INTERFACES By using the interactive tool GUIDE (Graphical User Interface Development Environment) to layout. file dependencies. and the search path. you can create GUIs programmatically using MATLAB functions. files. the workspace. pull-down menus. 3. GUIDE lets you include list boxes.5 THE MATLAB SYSTEM The MATLAB system consists of five main parts:  Development Environment. radio buttons. push buttons. It includes the MATLAB desktop and Command Window. a command history. DIRECTORY REPORTS Scan all the files in a directory and report on code efficiency. file differences. functions. It include facilities for calling routines from 25 . This is a vast collection of computational algorithms ranging from elementary functions like sum. It allows both "programming in the small" to rapidly create quick and dirty throw-away programs.  Handle Graphics. to more sophisticated functions like matrix inverse. image processing. and fast Fourier transforms. and presentation graphics. input/output. It includes high-level commands for two-dimensional and three-dimensional data visualization. animation. and complex arithmetic. data structures. cosine. It also includes low- level commands that allow you to fully customize the appearance of graphics as well as to build complete graphical user interfaces on your MATLAB applications.  The MATLAB Language. This is a library that allows you to write C and FORTRAN programs that interact with MATLAB. This is a high-level matrix/array language with control flow statements. matrix eigenvalues. and "programming in the large" to create complete large and complex application programs. and object-oriented programming features. This is the MATLAB graphics system. sine.  The MATLAB Application Program Interface (API). Bessel functions. calling MATLAB as a computational engine. 3.5. and for reading and writing MAT-files.MATLAB (dynamic linking). The tools are:  Current Directory Browser  Workspace Browser  Array Editor  Editor/Debugger  Command Window  Command History  Launch Pad  Help Browser Command Window 26 .1 DESKTOP TOOLS This section provides an introduction to MATLAB's desktop tools. You can also use MATLAB functions to perform most of the features found in the desktop tools. The exclamation point character! is a shell escape and indicates 27 . To save the input and output from a MATLAB session to a file.  Running External Programs You can run external programs from the MATLAB Command Window. use the diary function. In the Command History. and copy and execute selected lines. Use the Command Window to enter variables and run functions and M-files. you can view previously used functions.  Command History Lines you enter in the Command Window are logged in the Command History window. that the rest of the input line is a command to the operating system. On Linux.  Help Navigator Use to Help Navigator to find information.m. click the help button in the toolbar. or type helpbrowser in the Command Window. where you view the information. and the display pane. It includes: 28 . When you quit the external program.m invokes an editor called emacs for a file named magik. the Help Navigator. The Help browser consists of two panes. To open the Help browser.  Help Browser Use the Help browser to search and view documentation for all your Math Works products. and documentation. which you use to find information. The Help browser is a Web browser integrated into the MATLAB desktop that displays HTML documents. the operating system returns control to MATLAB. This is useful for invoking utilities or running other programs without quitting MATLAB.!emacs magik. for example. demos.  Launch Pad MATLAB's Launch Pad provides easy access to tools.  Product filter Set the filter to show documentation only for the products you specify.  Contents tab View the titles and tables of contents of documentation for your products. While viewing the documentation.  Index tab Find specific index entries (selected keywords) in the MathWorks documentation for your products. To get help for a specific function.  Favorites tab View a list of documents you previously designated as favorites. view it in the display pane. set the Search type to Function Name.  Search tab Look for a specific phrase in the documentation. you can:  Browse to other pages 29 .  Display Pane After finding documentation using the Help Navigator.  Find a term in the page Type a term in the Find in page field in the toolbar and click Go. evaluating a selection.  Bookmark pages Click the Add to Favorites button in the toolbar. or use the back and forward buttons in the toolbar.  Print pages Click the print button in the toolbar. Current Directory Browser 30 . Use the arrows at the tops and bottoms of the pages. Other features available in the display pane are: copying information. and viewing Web pages. MATLAB file operations use the current directory and the search path as reference points. Any file you want to run must either be in the current directory or on the search path. Search Path To determine how to execute functions you call. MATLAB uses a search path to find M-files and other MATLAB-related files. which are organized in directories on your file system. Any file you want to run in MATLAB must reside in the current directory or in a directory that is on the 31 . use the Workspace browser.search path. use the clear function. select Save Workspace As from the File menu. The workspace is not maintained after you end the MATLAB session. You add variables to the workspace by using functions. or use the load function. or use the functions who and whos. There are options for saving to different formats. By default.  Array Editor Double-click on a variable in the Workspace browser to see it in the Array Editor.  Workspace Browser The MATLAB workspace consists of the set of variables (named arrays) built up during a MATLAB session and stored in memory. the files supplied with MATLAB and MathWorks toolboxes are included in the search path. To read in a MAT-file.mat extension. To view the workspace and information about each variable. Use the Array Editor to view and edit a visual 32 . select Import Data from the File menu. which has a . and loading saved workspaces. This saves the workspace to a binary file called a MAT-file. or use the save function. To save the workspace to a file that can be read during a later MATLAB session. To delete variables from the workspace. Alternatively. select the variable and select Delete from the Edit menu. running M-files.  Editor/Debugger Use the Editor/Debugger to create and debug M-files. to producing presentation-quality output. or you can use debugging functions. The Editor/Debugger provides a graphical user interface for basic textediting. and numerical analysis. as well as for M-file debugging. through preprocessing. which sets a breakpoint. If you just need to view the contents of an M-file. and cell arrays of strings that are in the workspace.2 ANALYZING AND ACCESSING DATA MATLAB supports the entire data analysis process. 3. such as Emacs. If you use another editor. visualization. such as dbstop. strings. which are programs you write to run MATLAB functions.representation of one.  DATA ANALYSIS MATLAB provides interactive tools and command-line functions for data analysis operations. you can display it in the Command Window by using the type function. and can use preferences (accessible from the desktop File menu) to specify that editor as the default. from acquiring data from external devices and databases. including:  Interpolating and decimating 33 . you can still use the MATLAB Editor/Debugger for debugging. You can use any text editor to create M-files.5.or two-dimensional numeric arrays. databases. changing line colors and markers. such as HDF and HDF5. Latex equations. and video files. VISUALIZING DATA All the graphics features that are required to visualize engineering and scientific data are available in MATLAB. and drawing shapes. such as Microsoft Excel. These include 2-D and 3-D plotting functions. valley. You can customize plots by adding multiple axes. and scientific files. and averaging  Thresholding and smoothing  Correlation. and zero finding  Basic statistics and curve fitting  Matrix analysis DATA ACCESS MATLAB is an efficient platform for accessing data from files. other applications. scaling. sound. and legends. tools for interactively creating plots. 2-D PLOTTING 34 . and filtering  1-D peak. Low-level binary file I/O functions let you work with data files in any format. and the ability to export results to all popular graphics formats. adding annotation. You can read data from popular file formats. image. 3-D volume visualization functions. Fourier analysis.  Extracting sections of data. and external devices. Additional functions let you read data from Web pages and XML. ASCII text or binary files. multidimensional data. bar. Specifying plot characteristics. and engineering functions to support all common engineering and science operations.  Histograms. contour. statistical. 35 . such as camera viewing angle. 3-D scalar. 3-D PLOTTING AND VOLUME VISUALIZATION MATLAB provides functions for visualizing 2-D matrices.  Polygons and surfaces. lighting effect. often complex. slice. 3-D plotting functions include:  Surface.  Animations. area.3 PERFORMING NUMERIC COMPUTATION MATLAB contains mathematical. Visualizing vectors of data with 2-D plotting functions that create:  Line. and transparency. and isosurface. perspective.  Scatter/bubble plots. You can use these functions to visualize and understand large.5. These functions.  Cone. and pie charts. 3. light source locations. and 3-D vector data.  Image plots. and mesh. stream.  Direction and velocity plots. Because these processor-dependent libraries are optimized to the different platforms that MATLAB supports.  Fourier analysis and filtering. including doubles.  Data analysis and statistics. The core math functions use the LAPACK and BLAS linear algebra subroutine libraries and the FFTW Discrete Fourier Transform library. MATLAB provides the following types of functions for performing mathematical operations and analyzing data:  Matrix manipulation and linear algebra.  Ordinary differential equations (ODEs). and integers.  Partial differential equations (PDEs). are the foundation of the MATLAB language.developed by experts in mathematics. singles. they execute faster than the equivalent C or C++ code.  Sparse matrix operations. MATLAB can perform arithmetic on a wide range of data types. 36 .  Polynomials and interpolation.  Optimization and numerical integration. At the end of the system can say that the system achieve its desired expectation. But the detection of lung cancer is most difficult task. and then these features are used to train up the neural network and test the neural network.67% which meet the expectation of system. and then feature extraction. In future this technique can be used in the detection of brain tumor. so it is necessary to detect early stages. From the literature review many techniques are used for the detection of lung cancer but they have some limitations. breast cancer etc. The proposed system successfully detects the lung cancer from CT scan images. The proposed system test 150 types of lung CT images and obtains the result where overall success rate of the system is 96. In our proposed method pursue approaches in which first step is binary thresholding. CONCLUSION Lung cancer is one kind of dangerous diseases. 37 . Zhao. "Identifying Lung Cancer Using Image Processing Techniques. transactions on medical imaging. Viergever. 115. Prasad. R. pp. 4. "Lung Cancer Detection Using Image Processing Techniques ". Ginsberg. M. 2. Bhat. vol.. "Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm. 38 . vol. Nalini. "Detection and Classification of Lung Cancer Using Artificial Neural Network. Biradar . Farag. G. I. 2012. 2002. L. [7] D."detection. [2] A.120. 12. K. A. L. R. and R. [6] B. Schwartz.C3). Jiang and L. Gamsu.V. IEEE. [5] A. 20. V. Saptalkar. M. 2011. vol." Information Conference on Biomedical Engineering. Path an. Falk. and identification of lung abnormalities in chest spiral CT scans: phase I. vol. Sharma and G. I Issue. vol. "Artificial Neural Network based Cancer Cell Classification (ANN . Rocco. 3 Issue 1 September 2013. visualization. Ginneken. Romeny and M. Vol." International Journal on Advanced Computer Engineering and Communication Technology. 2002. Vaman. Lin and C. no. [4] B. B." IEEE. Jindal. S. [8] D. "Computer-aided diagnosis in chest radiography: a survey.200l. S. ISSN 2278-5140. International Journal of Latest Trends in Engineering and Technology (lJIl'ET). G. Egypt. [3] D. EI-Baz." journal of applied clinical medical physics. REFERENCES [I] G. "Lung nodules identification rules extraction with neural fuzzy network ".2003." Computer Engineering and Intelligent Systems. H. A. Van. Neural Information Processing. 4. H. no. B. 3." International Conference on Computational Techniques and ArtifiCial Intelligence (ICCTAf'2011). no.[9] A. vol. A. A. "Lung Cancer detection and Classification by using Machine Learning and Multinomial Bayesian. " Lung Cancer Detection using Curvelet Transform and Neural Network. Feb. [13] C. pp. Singh. 39 . September. 2014." International Journal of Latest Trends in Engineering and Technology (IJLTET). Chaudhary and S.1359. Vaman. S. Prasad. Tiwari. vol. Feb. Jan. P. June. 3. vol. pp. Niranjana. R. vol. 86 . vol. Mr. 6. 2014. Borse and Mr. 182-186. Priya. A. Dhananandhini. no. 385-383. 1. pp. Gupta and S. 2014. Dhivya. Jan. J. Rajeswari. [14] Mr. M. [16] G. A. 2014. [15] A. 2013. vol." International Journal of Application or Innovation in Engineering and Management (IJAIEM).l. Jan." International Journal of Soft Computing and Engineering (IJSCE). "Automatic Detection of Lung Cancer in CT Images. Yametkar. no. pp. 52-54." IJRET: International Journal of Research in Engineering and Technology. S. [12] B. no. "Lung Cancer Detection Using Digital Image Processing. K. "Lung Cancer Detection Using Image Processing Techniques. M. 3. May. 2012 . vol. [10] Ada and R. Yametkar and R. I. Dwivedi. 2. pp. 372-378. 2014. 3. 2 .7. Patane. no. M.7-13. no. 6. Suhasini and R. pp. pp.pp. R. "A New Approaches of Lung Segmentation Using Neuro-Fuzzy Network. 2. "Lung Cancer Detection and Classification by Using Bayesian Classifier. "Early Detection and Prediction of Lung Cancer Survival using Neural Network Classifier." Proceedings of IRF International Conference. 1351. Kaur. 9. [II] D. 15-17. 69-75. Vijaya. no." International Journal of Research in Engineering and Applied Sciences (IJREAS)." International Journal of Computer Applications. 2013 ." IOSR Journal of Electronics and Communication Engineering (IOSR-JECE). D. [18] N. Prabakaran. "Size Estimation of Lung Cancer Using Image Segmentation and Back Propagation. [19] K. 2014. "Gray Coefficient Mass Estimation Based Image Segmentation Technique For Lung Cancer Detection Using Gabor Filters. 40 . M." International Journal of Latest Scientific Research and Technology. no. Sankar and DR. no. Aug. Kaur and H. Jul.[17] G. pp. 2. Aug. 638-644. vol.95-98. no. 9. vol." Journal of Theoretical and Applied Information Technology. 1. 1. pp. 2014." International Journal for Research in Technological Studies. 14-17. pp. 2014. Sharma and Sheenam. Singh. "Lung Cancer Detection Using BPNN and SVM. 2. vol. 66 .
Copyright © 2024 DOKUMEN.SITE Inc.