SUPPLEMENTARY PNEUMONIA DETECTION VIA X-RAY IMAGES THROUGH MATLAB
A thesis presented to the College of Engineering of FEU Institute of Technology Technology
In partial fulfillment of requirements for the degree of Bachelor of Science in Electronics and Communications Engineering
by Cordova !ar" #oseph !$ %an Ben&amin Fran"lin 'elos (eyes #ayson )$ !ateo *a+rence (ay !aupoy #hon ,aul C$
Engr$ *uigi Carlo 'e #esus Adviser
Engr$ ,ocholo #ames !$ *oresco,ECE Faculty-in-Charge
Chapter 1 Intro!"t#on .$. Bac"ground Bac"ground of the Study Study Essential chec"ing for our +ell-being is important in order for us to "eep trac" of our health status$ This study entitled Supplementary ,neumonia 'etection via /-ray Images Images throug through h !AT !AT*AB is design designed ed to provid providesp especia ecialis lists ts a more more effect effective ive and convenient +ay of detecting pneumonia$ Based from the data gathered by the researchers radiologists are having a hard time on detecting pneumonia accurately due to the lac" of proper equipments +hich leads to misdiagnosing of disease$ 0ith the help of the advancement of computer technology medical medical e1perts e1perts incorp incorpora orate te the use of image image proces processin sing g to delive deliverr concret concretee result resultss through chest /-ray$ Image processing techniques are +idely used in several medical fiel fields ds for for imag imagee enha enhanc ncem emen entt in earl earlie ierr dete detect ctio ion n and and trea treatm tmen entt stag stages es of the the patients$2o+ever the traditional manual procedure of chest /-ray is still not enough to produce a high accurate result because of image quality illumination$ From the stated facts above the proponents came up +ith the idea of incorporating the used of matri1 laboratory 3!AT*AB4$ The proposed system is a supplementary device that +ill capture chest /-ray films and digiti5ed the image to be transferred to !AT*AB soft+are$ It +ill employ lung segmentation e1traction and selection$ The proposed system +ill have a constant database stoc"piling that +ill store pictures for further investigation of the result$
.$6 Statement Statement of the ,roblem ,roblem According to 'r$ !ario E$ Sarmenta and 'r$ Socorro Ferias from the (adiology 7ffice in the ,hilippines Children8s !edical Center one of their most common problem they encounter during pneumonia detection is +hen a part of chest /-ray is undere1posed or overe1posed$ An undere1posed chest /-ray result has a lo+ density number and is +hite or lighter +ithout enough image details +hile an overe1posed chest /-ray result means the image is too dar" to be read and some image details are lost due to being burned out to radiation that leads to misdiagnosis of disease$ In addit additio ion n accor accordi ding ng to 'r$ 'r$ Sarme Sarment ntaa anot anothe herr probl problem em they they encou encount nter er that that contributes to misdiagnosing of disease is theiroutdatedequipment that may have an inaccurate inaccurate result$ Aside Aside from that the s"ill of the radiologistis radiologistis also another factor to be consider$ The ability of the radiologist is also important in order to avoid any errors during test diagnosis$ 2e also mentioned that another issue they are encountering in the (adiol (adiology ogy 'epart 'epartmen mentt +as it ta"es ta"es days days before before they they can determ determine ine the patien patientt to havepneumonia because in some cases there are procedures that +ere need to revie+ regarding +ith the related pathology especially difficult cases$They also consider the history of each patient before they can diagnose it +ith pneumonia$ This study Supple Supplement mentary ary Pneumo Pneumonia nia Detect Detection ion System System via X-ray X-ray Images Images through MATLAB MATLAB +ill attempt to solve the follo+ing problems9 •
Scarcity of spare parts
•
The misdiagnosis of disease due overe1posed and undere1posed images
•
The longer time duration of releasing the results
.$: 7b&ectives 7b&ectives of the Study The general ob&ective of this study is to design and implement a supplementary pneumonia detection system via /-ray through !AT !AT*AB$ .$:$ .$:$. .
Spec Specif ific ic 7b&e 7b&ect ctiv ivee •
To develop a system that +ill aid radiologists to produce an reliable chest /-ray result
•
To develop a program that can be able to employ lung segmentation feature e1traction and feature classification of a chest /-ray image through !AT*AB$
•
To provide radiologists in obtaining faster result in detecting pneumonia using /-ray images from patients
•
To lessen lessen time consume and errors by performing statistical analysis of the pro&ect
.$; Scope and and *imitati *imitations ons The main scope of this study is to identify and characteri5e pneumonia patterns b y analy5ing the input /-ray image then use the pattern to compare on an actual chest /-ray of the patient$ The system is designed to determine +hether the chest /-ray of the patient is infected +ith pneumonia based on the pattern and characteri5ation gathered from severa severall chest chest /-ray /-ray images images that that contai contains ns actual actual pneumo pneumonia nia$$ By using using the propos proposed ed system misdiagnosis of the disease +ill be reduce and the accuracy of the chest /-ray result +ill be enhance$
The proposed system is capable of capturing images from a chest /-ray +hich includes bu55er to detect +hether the /-ray is properly attached to the hard+are and ready to be captured$ The suggested dimension of the input +ill be .;1< inches +hich +ill also be used on the testing of the hard+are$ The system +ill also ma"e use of Arduino Uno board +ith AT!E%A :=: microcontroller that +ill control and send the capture images to the computer$ The image format that the proposed system +ill produce +ill have an e1tension of #,E% or #,% format so it +ill be supported by !AT*AB8s formats for import and e1port$ The operating system that +ill be used in this pro&ect shall not be lo+er than 0indo+s < +ith an Intel or A!' 1=> processor supporting SSE6 instruction set$ The recommended (A! should at least be 6?;=!B and the 2ard 'rive space should be .%B for !AT*AB only and : to ;%B free space is needed for !AT*AB installation$ The !AT*AB version that +ill be used +ill not be lo+er than version <$.?$?$;@@ 3(6?.?a4$ The proposed system is limited only on detecting patterns of pneumonia and does not include other diseases$ If the chest /-ray of the patient does not have any signs of pneumonia it +ill be categori5ed as healthy or if the system determines other patterns that is not the same +ith pneumonia it +ill be categori5ed +ith other disease$ .$ Significance of the Study This study is designed to provide a pneumonia detection system via /-ray images through !AT*AB$ It +ill be very beneficial for doctors and lab technicians as it can be used to diagnose patients+ith pneumonia faster and accurately to produce reliable results$ This study is also relevant for students especially for medical students in order for them to gain more "no+ledge about pneumonia and also about the field of radiology$
They can used this study as a reference or research material to further investigate the methods of detecting pneumonia$ The study +ill also be significant for future researchers +ho +ill also attempt to conduct future study about pneumonia detection as it +ill serve as a good reference for the development of their study$ .$> 'efinition of Terms Conventional is based on or in accordance +ith +hat is generally done or believed$ Database is a structured set of data held in a computer especially one that is accessible in various +ays$ Digitie! is to put data 3images etc$4 into digital form$ "mploy is to use something to +or" to ma"e use of$ "#traction is the action of ta"ing out something especially using effort or force$ Image Processing is the analysis and manipulation of a digiti5ed image especially in order to improve its quality$ MATLAB $Matri# Laboratory% is a multi-paradigm numerical computing environment and fourth-generation programming language developed by !ath0or"s$ Mis!iagnosis is an incorrect diagnosis due to some medical malpractice and or errors$ &a!iation is the emission of energy as electromagnetic +aves or as moving subatomic particles especially high-energy particles that cause ioni5ation$ &a!iologist are medical doctors +ho speciali5e in diagnosing and treating diseases and in&uries using medical imaging techniques such as 1-rays computed
tomography 3CT4 magnetic resonance imaging 3!(I4 nuclear medicine positron emission tomography 3,ET4 and ultrasound$ Segmentation is the process of dividing something into parts or segments$ Stoc'piling is the act of storing for future use usually carefully accrued and maintained$ Supplementary is something added to complete a thing ma"e up for a deficiency or e1tend or strengthen the +hole$ System is a set of connected things or parts forming a comple1 +hole in particular$ A set of principles or procedures according to +hich something is done an organi5ed scheme or method$
Chapter $ Re%#e& o' Re(ate )or*+ an L#terat!re 6$. Foreign *iterature 6$.$. 2I(A-TA9 A real-time ,C(-based System for the (apid Identification of Causative Agents in ,neumonia Ta"ashi 2irama Shohei !ine5a"i 36?.:4$ (I&A-TA)* A real-time PC&-base! system +or the rapi! i!enti+ication o+ causative agents in pne umonia 7daiba #apan$ According to this article +ritten by !r$ Ta"ahashi 2irama and !r$ Shohei !ine5a"i the case of pneumonia is increasing the past centuries and +as notably the main cause of deaths by many$ 'ifferent medical tests such as antigen tests and paired antibody titers etc$ all failed to "no+ and identify the reason of the causative pathogens of the disease$ According to them in order to effectively identify the causative pathogens of pneumonia a quic" identification using the 2I(A-TA system +ill allo+ the medical e1perts to come up for the selection of solutions for pneumonia$ The identification of pneumonia using the 2I(A-TA system really helps the medical e1perts in various +ays such as for the selection of antibiotics a quic" scans and in producing accurate results$
6$.$6 'etection of ,neumonia in chest /-ray Images Shabnam Dannan 36?..4$ Detection o+ Pneumonia in Chest X-ray Images India$ According to this article based from the survey conducted by medical e1perts around the +orld pneumonia is a type of infection that is very common to people +ho has poor lifestyle$ It is also stated that the disease li"e pneumonia is also common for
children +ho has +ea" immune system$ This type of infection quic"ly spreads in the lung area of the body$ To diagnose pneumonia medical e1perts uses the po+er of image processing technology li"e the chest /-ray$ Using the chest /-ray images the doctors can effectively identify pneumonia by loo"ing at the pattern in the chest /-ray result from the patients$ Because of its effectiveness in identifying difficult illnesses chest /-ray +as then used to detect several diseases not only pneumonia$ The researchers also added that using feature e1tractions li"e 0,T 0FT and '0T can also be used in detecting the disease$ This method according to them produces more accurate result than the rest of the "no+n methods of pneumonia detection$
6$.$: ,neumonia 'iagnosis 'r$ Shirley !cfield 36?.64$ Pneumonia Diagnosis USA This article is about pneumonia diagnosis$ According to this article pneumonia diagnosis is done using some physical health e1amination based from the findings of the doctors$ The article also stated that further investigations are being done by the e1perts to confirm their diagnosis$ The data gathered from the chest /-rays and blood tests are very helpful in order to them to thoroughly identify the case of the patient$ The researcher also stated that the chest /-ray method for pneumonia detection is +idely commonly used by many hospitals and medical clinics no+ because of its reliable and convenient results$ 2o+ever according to some study conducted by medical e1perts there are still areas that uses the traditional +ay of detecting pneumonia$ They diagnosed diseases based from the symptoms and health e1aminations only$ The researcher also cited that diagnosing can also be difficult in some patient especially to those +ho also have other
disease$ To distinguish pneumonia from other illnesses of the patient medical e1perts ma"e use of the chest CT scan or by the use of other tests that also ma"e use of image processing techniques$ The author also stated that chest /-ray is a very helpful test for identifying pneumonia +hen it comes to difficult scenarios during diagnosis$ Chest /-ray helps in e1posing pneumonia patterns to be able to identify clearly by medical e1perts$
6$.$; 0hat is ,neumonia Its types and ho+ to detect it Bree ormandin 36?.64$ ,hat is Pneumonia It.s Types an! ho/ to !etect it0 USA$ Bree ormandin conducted a study about pneumonia and ho+ to detect it$ According to his study pneumonia is a some sort of infection that occurs in human lungs$ Fungi bacteria and other viruses are the number one cause of pneumonia that brings people in the pinch of pains$ This paper further reveals that pneumonia also causes inflammation in lung8s air sacs "no+n as the alveoliG$ The inflammation brings pains to patients that causes serious effect +hen not immediately ta"en care of because the alveoliG ma"es breathing difficult$ ,neumonia8s symptoms according to the study of medical e1perts can starts from mild to a high level life threatening one$ ,neumonia is a top leading disease that causes more deaths than any other illness +orld+ide$ The seriousness of the disease depends on the cause of its inflammation or either the type of virus that caused the infection$ The types of pneumonia based from this article are9 bacterial pneumonia this type of pneumonia according to the author can affect anyone$ 7n the other hand viral pneumonia is a type pneumonia +hich can be dangerous to
pregnant +omen$ 0hile mycoplasma pneumonia is a type of pneumonia that produces mild cases of pneumonia$ ,neumonia detection can be done by the help of chest /-rayG and other image processing techniques a noninvasive tests that sho+s the structures of +hat the inside of the human chest and produces images out of it$ oninvasive means that no surgery +ill be done and no medical instruments +ill be inserted into the patient8s body$
6$.$ ,reliminary Study of ,neumonia Symptoms 'etection !ethod Using Cellular eural et+or" Abdullah A$A$ 36?.;4$ Preliminary Stu!y o+ Pneumonia Symptoms Detection Metho! 1sing Cellular )eural )et/or'0 !alaysia ,erlis Arau !alaysia$ According to this paper it is said that medical diagnosis is one of the most important process +herein image processing technique is being applied$ This paper proposes a pneumonia symptoms detection method based on cellular neural net+or"s technology that +as developed to help users to detect early symptoms of any disease$ The main technology used in this study is the cellular neural net+or"s +hich is represented by a virtual pattern e1pansion obtained from different operations done by the researchers$ The C +as based from : by : patterns of linear space invariant$ The main aim of this paper is to be able to detect pneumonia symptoms +ithin the short period of time$ The main function of the cellular neural net+or"s is by allo+ing the connections bet+een the ad&acent units only in order to avoid any net+or" traffics$ There are also mandatory rules that has to be implemented in designing the patterns to be used for instance9 the state output boundary equations and also their respective values$ In order to
create the most effective algorithm for pneumonia symptoms detection the developer combined all the patterns that +ere acquired during the development phase$ Furthermore during the soft+are testing and debugging the developer ma"e use of the candy soft+are as a simulator for the cellular neural net+or"s in detecting pneumonia symptoms$ The soft+are +as tested using the 6: amounts of chest /-rays samples +ith grayscales +hich is an indication of symptoms of pneumonia$
6$6 *ocal *iterature 6$6$. 'etection of ,otential ,neumonia H Causing Bacteria Found in ebuli5ers in Iligan City 2ospitals9 Some Implications on Infection Control Blaisel !ae $ Baguio Aimee %race %emelo 36?.64$ Detection o+ Potential Pneumonia 2 Causing Bacteria 3oun! in )ebuliers in Iligan City (ospitals* Some Implications on In+ection Control Baguio ,hilippines$ This article +ritten by Blaisel et al$ discusses the survey conducted in Iligan City 2ospitals$ Based from the data gathered by the researchers about the most commonly acquired infection by patients from hospitals pneumonia is on its third place +hich means that almost .;J of deaths in the +orld is caused by pneumonia infection from the said place$ It +as estimated that up to
in reducing significant problems in the lungs$ It is also +idely used by manymedical doctors across countries$ The main purpose of the study is to conduct an assessment on pneumonia detection using nebuli5er in Iligan City hospitals$
6$6$6 Incidence and (is" Factors of Childhood ,neumonia-*i"e Episodes in Biliran Island ,hilippines 'elmiro Fernande5 H (eyes 36?.4$ Inci!ence an! &is' 3actors o+ Chil!hoo! Pneumonia-Li'e "piso!es in Biliran Islan!0 Philippines0 Tarlac University$ ,hilippines$ In this article the discussion is about the study of the researcher conducted in Biliran Island$ The study is about the factor of ris" of pneumoniaamong patients in the said area$ According to 'elmiro the main cause of deaths among babies and young adults is none other than pneumoniaG$ According to the information gathered by the researcherin some developing countries such as the ,hilippines and !alaysia pneumonia is a disease feared by many because of its severity that easily leads to death$ 2o+ever the scarce amount of data obtained by the researcher are still not enough to support this study$ This paper aims to calculate the tragics and rates in death of pneumonia in Biliran Island$ !oreover the study also aims to evaluate the ris" factors of pneumonia and the health threats among the residence$ Based from previous studies that +ere found parental smo"ing the type of coo"ing fuel type of toilet facility etc$ are all contributes to the ris" factors of having pneumonia$ All the aforementioned studies +ere conducted in the hospitals and that data gathered +ere all from the different researchers +ho also conducted the same topic$
According to the research done by the e1perts in the said area +hen the children develops pneumonia some parents do not ta"e them to hospitals because of various reasons this is due to financial problems and the lac" of "no+ledge$ In conclusion a stable and good connection to medical institutes is significant in order to prevent pneumonia earlier$
6$6$: ,reventing ,neumonia in the Elderly The ,hilippine Star 36?.;4$ Preventing Pneumonia in the "l!erly0 !anila ,hilippines$ According to the ,hilippine Star e+spaper community-acquired pneumonia in adults +ith an aged of > above can be prevented based from the results gathered form landmar" clinical trial test that +as conducted by evaluating the ,fi5er8s effectiveness using its pneumococcal vaccine$ The vaccine +ere tested on several adults +ho are identified positive +ith pneumonia and the result has an average percent to prevent the spread of pneumonia$ Also according to this article community-acquired pneumonia is public8s most health concern and the main cause of deaths in adults around the +orld$ The article also reveals based from the ,hilippines 'epartment of 2ealth the data of mortality of adults in the country$ It +as revealed that pneumonia is currently on its th ran" in the top leading causes of mortality among adults$ In addition to this the total number of Filipinos >? years and older +ere at :$< million during the year .@@ +hich represents $;J total of the population$And by the year 6??? to present the total record has increased to ;$= million or almost >J of the total population today$
2o+ever despite of the success of the trial the researchers stated that there are still +or"s to be done$
6$6$; ,hilippines Clinical ,ractice %uidelines on the 'iagnosis Empiric !anagement and ,revention of Community-acquired ,neumonia 3CA,4 in Immunocompetent Adults !arissa !$ Ale&andria 36?.;4$ Philippines Clinical Practice 4ui!elines on the Diagnosis0 "mpiric Management0 an! Prevention o+ Community-ac5uire! Pneumonia $CAP% in Immunocompetent A!ults0 ,hilippine College of (adiology ,hilippines$ This article is about the study of the researchers about the clinical practices on the diagnosis empiric management and prevention of community-acquired pneumonia for immunocompetent adults in the ,hilippines$According to this study conducted by the researchers pneumonia is the third leading cause of death in the ,hilippines based from the data obtained from the ,hilippine 2ealth Statistics 7ffice$ From year .@@= to 6??. the rate of death caused by pneumonia +as the highest among other neighboring countries$ Community-acquired pneumonia or CA, for short is typically "no+n as an acute infection that usually target young children and or aged adults$ ,neumonia infection8s symptoms includes acute illness pains and accompanied by an abnormal chest /-ray findings$ 2o+ever those people +ho acquired the infection from long term facilities are not included$ These clinical practice guidelines about community-acquired pneumonia or CA, for short +as conducted only for empiric therapy of those immunocompetent patientsKadults$ This study +as drafted in order to provide e1perts +ith a more practical
approach in the resolution of the important issues in diagnosis management and prevention of community-acquired pneumonia of adult patients$
6$6$ (espiratory Liruses from 2ospitali5ed Children +ith Severe ,neumonia in the ,hilippines 2a5el B$ %alang 36?.64$ &espiratory 6iruses +rom (ospitalie! Chil!ren /ith Severe Pneumonia in the Philippines0 Tacloban City ,hilippines$ In this article the study of the researcher revolves a round investigating respiratory viruses from hospitali5ed children +ith severe pneumonia$ According to this article over the past 6? years pneumonia is still the main cause of deaths by young patients$ It +as because the symptoms from pneumonia cases remains undefined by e1perts due to the lac" of proper equipment until no+$ In Eastern Lisayas (egional !edical Center in Tacloban City is the place +here this study is conducted$ The researcher has a target population of =.@ patients +ho +ere involved in this study$ The goal of this study is to be able to identify the nature of pneumonia by investigating the patients +ho have a symptoms of pneumonia$ To begin the research process the researcher uses samples +hich is composed of children +ith ages @ days to . years old +ho +ere transferred into the ,ediatrics 'epartment$ These children are positive +ith severe pneumonia viruses and are voluntarily enrolled themselves to be part of the research being conducted by the researcher$ After the admission of the patients the researcher performed the polymerase reaction by using some blood samples$ The detection of these respiratory viruses and bacteria helps
the researcher to identify the severity stages of the symptoms of pneumonia from patients +ho are infected by pneumonia viruses$ According to the researcher pneumonia viruses and symptoms are very common to the young adults in the ,hilippines$ So a quic" and effective pneumonia detection system is very necessary to aid the patients$ 6$: Foreign Studies 6$:$. Computer-Aided Tuberculosis 'etection in Chest (adiographs9 A Survey yeinaing 2ti"e Dhan Shafie 36?.;4$Computer-Ai!e! Tuberculosis Detection in Chest &a!iographs* A Survey0 Duala *umpur !alaysia$ In this study the researchers conducted a study about the investigation of a ,C supported conclusion frame+or" for computeri5ed e1amination of mid-section 1-beam for recogni5able proof of pneumonic tuberculosis$ The study stresses to give the progressions of tuberculosis order from 1-beam pictures for e1ample H preprocessing$ The principal goal of the picture preprocessing is not &ust to enhance the nature of the picture additionally to lessen the undesired segment from the foundation of the pictures$ The vast ma&ority of pre-handling strategy connected the force estimation of neighborhood pi1el for getting the brilliance po+er estimation of the information pictures$
6$:$6 To+ards the 'etection of Abnormal Chest (adiographs the 0ay (adiologists 'o It Al5ubaidi ,atel ,anchanathan Blac" 36?.?4$ To/ar!s the !etection o+ abnormal chest ra!iographs the /ay ra!iologists !o it0Ari5ona State University Tempe Ari5ona USA$
In this study they utili5e ,C Supported Identification 3CA'e4 and ,C 2elped 'iagnosis 3CA'14 to utili5e highlight e1traction design ac"no+ledgment and machine learning calculations to help radiologists in recogni5ing and diagnosing variations from the norm in therapeutic pictures$ The e1aminations endeavors to utili5e base up preparing to give up ,C Supported Analysis of typical versus anomalous elements they propose to utili5e it to give ,C 2elped 'iscovery of typical components$ They also propose to determine gray scale overlay map that sho+s ho+ ordinary basic radiography substance is in the nearby area around that pi1el$
6$:$: 'iagnosis of ,neumonia +ith an Electronic ose9 Correlation of Lapor Signature +ith Chest Computed Tomography Scan Findings 2oc"stein Thaler Torigian !iller #r$ 'effenderfer 2anson 36??;4$ Diagnosis o+ Pneumonia /ith an "lectronic )ose* Correlation o+ 6apor Signature /ith Chest Compute! Tomography Scan 3in!ings0 !assachusetts USA$ Electronic nose innovation is conceivably valuable in clinical drug in light of the fact that the gadgets are convenient trying is not invasive and the outcome are fast$ In the conclusion of pneumonia the system can be usedto test lapsed gasses$ 7n the off chance that the gadget can be prepared to perceive the electronic pattern of the patient8s breath +ho is positive +ith pneumonia it +ill be very useful in the facilitating of patients accepting ventilation po+ered by mechanical machines$ As of no+ no highest quality level in the conclusion of the said disease$ Frame+or" scoring pneumonia radiography in
mid-section and bronchoscope are all considered$ In real life use conclusion ta"ing into account the flo+ of accessible information and clinical tests and e1periments$ 'uring emergency unit tests basically sic" patients frequently e1perience midsection registered tomography filtering to help in analysis$ ,ast medical tests had sho+n the ability of proposed electronic nose to recogni5epatients +ho +ere in danger of pneumonia ventilating-related stuffs and the capacity of the proposed electronic nose to distinguish respiratory pathogens in vitro =@$ According to this study it is +as assumed that the proposed electronic nose is failed to detectbreathed out unpredictable atoms from patient8s breaths$
6$:$; 'etection of ,neumonia using Free-Te1t (adiology (eports in the Bio Sense System Asatryan A$ 36?.?4$ Detection o+ Pneumonia using 3ree-Te#t &a!iology &eports in the Bio Sense System0 Science Applications International Corporation USA$ The study is about the development of the real-time disease detection system using the electronic data sources$ According to the study the cases of patients +ho are positive +ith symptoms of pneumonia are getting bigger and alarming each year$ A rapid pneumonia detection system is needed in order to provide radiologists a faster +ay to diagnosis and detect the symptoms of pneumonia$ The proposed study aims to develop a system that can be used to send te1t radiology reports to medical e1perts for quic"er detection of pneumonia$
In order to test the reliability of the proposed system the researcher tested the program using the electronic radiology to send te1t reports$ A computer algorithm +as used that searches for selected programmed "ey+ords$
6$:$ Innovative Chest /-ray Solutions Supporting TB ,revalence Studies 'r$ 0essel Ei&"man and 'r$ Fran" Lan 'oren 36??@4$ Innovative Chest X-ray Solutions Supporting TB Prevalence Stu!ies0 USA$ 'r$ 0essel Ei&"man and 'r$ Fran" Lan 'oren conducted a study entitled Innovative Chest /-ray Solutions Supporting TB ,revalence Studies$ According to their study chest /-rays is a very useful image processing technique as it visually sho+s the patterns of symptoms of a disease &ust li"e symptoms of pneumonia and or TB$ Chest 1-ray according to them not only helps radiologists in obtaining accurate results but also helps in shortening the delays of diagnosis of doctors$ They also cited that avoiding films by using digiti5ed chest /-rays is more appropriate because the digital technology has a more tendency to solve most chest /-ray problems$ Furthermore the researchers believes that by using the direct digital chest /-ray +ill definitely improve the chances in obtaining accurate and rapid results$ The direct digital /-ray +ill another advantage is that it is an eco-friendly system that also decimates cost per image +hile providing balance support to the ecosystem by eliminating the chemical +aste issues as +ell as revolutioni5ing the case detection of pneumonia and TB in countries +ith insufficient sources$
6$; *ocal Studies 6$;$. Breast Cancer 3'uctal Carinoma4 'etection and Classification Soft+are using Fu55y ,attern (ecognition *oren5o !ontalban (eal So 36??<4$ Breast Cancer $Ductal Carinoma% Detection an! Classi+ication So+t/are using 3uy Pattern &ecognition0'e *a Salle University ,hilippines$ In this study the researchers deals on detection and classification of breast carcinoma particularly ductal carcinoma$ The study ta"es on the characteristics and definitions seen in the microscope analy5ed and evaluated +ith t+o modules +hich is image processing and the fu55y pattern recognition$ The first module analy5es the Terminal 'uct *obular Unit 3T'*U4 by implementing a number of image processing techniques such as uclei E1traction Filtering and Feature e1traction to name a fe+$ The second module uses fu55y membership functions to evaluate the degree and the level at +hich the image is an Invasive Carcinoma 3malignant4 or on-invasive 3benign4$ And if invasive +ould it be invasive ductal carcinoma ST 3no specific type4 or of a different type$ The researchers overall accuracy on performing the study is about @J$
6$;$6 ,addy 'isease 'etection System Using Image ,rocessing Devin B$ Buenaventura et al$ 36?.64$ Pa!!y Disease Detection System 1sing Image Processing0 'ominican CollegeSta$ (osa *aguna ,hilippines$ In 'ominican College of Sta$ (osa *aguna a study about ,addy 'isease 'etection System using Image ,rocessing +as amended$ The main ob&ectives of the
study is to develop a system that can be used to detect paddy diseases such as the ,addy Blast Bro+n Spot and arro+ Bro+n 'isease$ The study focuses on the image processing techniques used in enhancing image qualitiesand the techniques of neural net+or"s to identify the paddy disease$ The system development methodology used by the researchers during the image processing includes pre-processing segmentation and classification$ The researchers put the paddy samples through the (%B till proceeding to the binary conversion$ After having identified all the paddy samples as normal or +ith patterns of paddy disease the segmented paddy disease sample then converted by the researchers into binary data$ In order to recogni5e the paddy diseases +ith passing accuracy rates employing neural technique is necessary$
Chapter , Re+ear"h Methoo(o. :$. 7vervie+ The proposed system is designed to provide radiologists a supplementary pneumonia detection system via /-ray images through !AT*AB$ The system aims to help specialists to produce accurate results in detecting pn eumonia$ The graphical user interface of the proposed system is composed of si1 buttons9 the Scan Image button Start ,rocessing button Lie+ Test (esult button (eset button 2elp button and the E1it button$ The ideal set up of the proposed system +ill be discussed in the succeeding parts of this chapter$ :$6 Conceptual Frame+or" I,UT
/-ray scan image !AT*AB capture image *E'-light indicator ,(7CESS I$ II$
The 1-ray scan image +ill be placed on the device !AT*AB +ill process the 1-ray scan image
III$
!AT*AB +ill segment select and e1tract the image$
IL$
*E' light indicator signifies that the image is already captured
L$
*C' display +ill sho+ off if the patient is healthy possible positive of pneumonia or possible of other disease$
LI$
The result +ill be printed out on a paper$
7UT,UT
(esult +ith diagnosis *C' display Figure .$ Conceptual Frame+or" Figure . presents the conceptual frame+or" of the proposed system$ The figure sho+s the input-process-output of the pro&ect$ The system input includes the user and the patient8s chest /-ray that +ill be employed into the machine$ In the process stage is +here the captured image +ill be processed by !AT*AB to perform image enhancement$ The system output is +here the result +ill be display in the graphical user interface of the system that has the option to store image into the database that can be used for future reference$ :$: Bloc" 'iagram
Chest /-ray Image 3'igiti5ed Ima e
!AT*AB 3Image ,rocessing4
Segmentation
E1traction
Selection
,rocessed Image 3(esult4
Figure 6$ Functional Bloc" 'iagram of the ,roposed System
Figure :$:$. sho+s the functional bloc" diagram of the supplementary pneumonia detection system via /-ray images through !AT*AB$ The figure sho+s the principal functions of the systems +hich are represented by the bloc"s$ According to this diagram the chest /-ray +ill be digiti5ed and +ill be placed into the !AT*AB machine$ The chest /-ray +ill then undergo image processing to be able to scan the /-ray image thoroughly by performing image segmentation e1traction and selection$
,/0 S"heat#" D#ara
Figure :$ Schematic 'iagram of the ,roposed System
Figure ;$ Schematic 'iagram of !icrocontroller 3AT!E%A:6=4 "#planation :$ Algorithm START DISPLAY POSSIBLE POSITIVE OF PNEUMONIA WITH OTHER DESEASE
CAPTURE IMAGE
PRE PROCESS OF THE
Y WITH OTER DESEASE
PROCESS LUNG SEGMENTATION
FEATURE FEATURE FEATURE EXTRACTION SEECTION FIND MATCH
PNEUMONIA HEALTHY?
Y N
N Y
DISPLAY POSSIBLE POSITIVE OF DISPLAY DISPLAYOF PNEUMONIA POSSIBLE OF OTHER HEALTHY ILLNESS
END
Figure :$$.9 Soft+are 'esign Flo+ Chart
Figure :$$. sho+s the soft+are diagram of the proposed system$ First digiti5ed chest /-ray image +ill be uploaded to the system and prepares for processing$ e1t pre processing stage +ill be performed +herein the image +ill undergo +ith image enhancement$ After the pre-processing stage the image +ill undergo +ith lung
segmentation$ Then the segmented lungs +ill undergo to feature selection +herein target areas in the lungs +ill be selected$ After feature selection it +ill undergo to feature classification to determine if the targeted areas in the lungs are classified as healthy positive +ith pneumonia positive of pneumonia +ith other disease and positive of other illness$ 7nce feature classification is done the output +ill be displayed in the graphical user interface of the system$
F*70C2A(T START
X- RAY IMAGE PLATE
INPUT DATA RECEIVED
CAPTURE IMAGE
X-RAY FILM CONVERTED TO DIGITAL IMAGE
IMAGE TRANSMITTED TO COMPUTER FOR PROCESSING
PROCESSED IMAGE RESULT (The Output
END
Figure :$$69 %eneral 2ard+are 'esign Flo+ Chart Figure :$$6 sho+s the hard+are diagram of the proposed system$ First the /-ray image template +ill be used as input$ Then the /-ray image plate input +ill be scanned
through a scanner to digiti5e the input image$ The digiti5ed chest /-ray image +ill no+ be imported into the system and store the digiti5ed /-ray image to start processing$ ,/2 Te+t Pro"e!re+
Step .9 The proponents +ill place the 1-ray film on the Illuminator Step 69 The camera +ill ta"e a picture of the 1-ray film Step :9 The proponent +ill chec" +hether the image is received by the database Step ;9 The proponent +ill chec" the output that +ill be sho+n by the %UI Step 9 The output +ill serve as the input on the proposed pro&ect8s output Step >9 (epeat Steps . to until the number of trials are reached ,/3 Iea( Set!p
3a4
3b4
Figure :$<$. Ideal Setup (epresentation of the ,ro&ect
Figure :$<$. sho+s ho+ the prototype +ill +or" and ho+ it +ill function during the operations$ 1-ray films +ill be placed on the illuminator and then an image capturing device +ill be present at +hich its output +ill be placed directly to the soft+are device and perform the algorithms necessary to analy5e the image for further investigation$ ,/4 Har&are Coponent+
Figure :$<$.9 The Arduino Uno Board
Figure :$=$. sho+s the Arduino Uno Board that +ill be used by the proposed system$ It is a microcontroller board based on the Atmel8s AT!E%A:6= microcontroller$ It is the latest in a series of USB 3Universal Serial Bus4 Arduino board$ It has .>!25 ceramic resonator a USB connection a po+er &ac" an ICS, header a reset button > analogs inputs and .; digital inputKoutput pins of +hich > pin can be used as ,0!
outputs$ It uses AT!E%A.>U6 programmed as USB-to-serial converter instead of FT'I USB-to-serial driver chip +hich +as used in all the preceding board$ It has a :6"b flash memory of +hich ?$"b is used by boot loader 6"b of S(A! ."b of EE,(7! and .> !25 cloc" speed$
Figure :$=$69 (epresentation of AT!E%A:6=
Figure :$=$6 sho+s the microcontroller unit that +ill be used on the proposed system$ The microcontroller unit consists of ;DK=D bytes of in-system programmable flash +ith read-+hile-+rite capabilities 6>K;.6 bytes EE,(7! along +ith the .6K.DK6D bytes of S(A!$ It has 6: general purpose inputKoutput :6 general +or"ing registers : fle1ible timerKcounters +ith compare models internal and e1ternal interrupts and a serial program USA(T$ It has a byte-oriented 6-+ire serial interface an S,I serial port a >-channel .? bit A'C a programmable +atch-dog timer +ith an internal oscillator and soft+are-selectable po+er saving mode$
Figure :$=$:9 (epresentation of USB to Serial Bridge Co ntroller ,*6:?:
Figure :$=$: sho+s the presentation of USB to serial bridge controller ,*6:?: +hich +ill be used by the proponent that can operate as a bridge bet+een one USB port and one standard (S6:6 serial port$ It comprises of @ ports input signal ports output signal @ po+erKground connection and ports bi-directional signals$
Figure :$=$;9 (epresentation of ,:??>*E Transistor
Figure :$=$; represents an -channel !7SFET transistor that +ill be used by the proponents$
Figure :$=$ *C' SC(EE !7'U*E
A *iquid Crystal 'isplay 3*C'4 is a flat as sho+n in figure .? thin display device consisting of any number of pi1els aligned in front of a reflector or source of light$ The group +ill be using a ,hilips 6 by .> *C' to be able to display if the patient has possible pneumonia or possible of other illness +hich +ere displayed on the *C'$
*E' 3*ight indicator4
Figure :$=$> *E' *I%2T I'ICAT7( A light-emitting diode 3*E'4 is a t+o-lead semiconductor light source$ I t i s a pHn &unction diode +hich emits light +hen activated$0hen a suitable voltage is applied to the leads electrons are able to recombine +ith electron holes +ithin the device releasing energy in the form of photons$ This effect is called electroluminescence and the color of the light 3corresponding to the energy of the photon4 is determined by the energy band gap of the semiconductor$ It is used as a light indicator of the device +hen capturing image$
,/5 So't&are Con+#erat#on
Figure :$@$.9 !AT*AB 3!atri1 *aboratory4
!atri1 *aboratory 3!AT*AB4 is a high-performance language for technical computing$ It integrates computation visuali5ation and programming in an easy-to-use
environment +here problems and solutions are e1pressed in familiar mathematical notation$ A typical use of this soft+are includes Algorithm development scientific and engineering graphic data analysis e1ploration and visuali5ation and application development +hich include %raphical User Interface building$ The advantages of !AT*AB over other programming languages for image processing are it has a huge database of inherent calculation for image processing and ,C vision application$ It permits you to test calculations instantly +ithout recompilation +here you can sort something at the order line or e1ecute an area in the supervisor and promptly see the outcome$ Their des"top surroundings +hich permit you to +or" intelligently +ith your information help you to stay informed concerning documents and variables and disentangle normal programming or investigating assignments$ It has a capacity to pursue in a +ide mi1ture of both basic and space particular picture designs furthermore its capacity to auto-produce C code utili5ing !AT*AB Coder for an e1pansive and developing subset if image processing and other specific functions +hich you could then use in different situations such as for installed frame+or"s or as a segment in other programming$
,/16 )or*#n Theor#e+
The performance of algorithm used in processing the chest /-ray image is usually quantified in terms of accuracy of the soft+are$ Algorithm +ith higher accuracy requires more processing time +hich is undesirable for most system application$ 2o+ever it is important to ta"e note that the proposed system +ill focus on the accuracy of the system that can be used for other studies$
,/16/1 Pre-pro"e++#n Stae
In this stage in order to achieve enhanced image result for further analysis the input chest /-ray image must be readable$ The proposed system depends on the quality of the input image$ This stage involves processes of grayscale conversion binari5ation and noise reduction$
,/16/$ L!n Seentat#on
The first algorithm to be implemented is by obtaining the inner lung details along +ith border refinement +hich involves separating the bac"ground and foreground pi1els$ Also the lung fields have to be grouped together and surrounding areas needs to be removed$ Also the blood vessels are segmented to be obtaining better orientation of the blood stream +ithin the lung area$ Segmenting blood vessels in the lung areas as +ell may have a better resemblance to pneumonia patterns$
,/16/, 7eat!re Se(e"t#on
For the algorithm of the feature selection a covariance matri1 of each feature +ill be categori5ed bet+een the three classes +hich are healthy +ith pneumonia and other disease$ It gives difference bet+een the corresponding feature values of various classes$ A threshold +ill be set after the trial and error +hich selects a set of feature that helps distinguish the various classes better$
,/16/0 7eat!re C(a++#'#"at#on
The classification algorithm used in this process is by getting each region for the image along +ith the set of features that has been selected is computed$ The data +ill be served as a training set for the classifier$ The classes are assigned to each region of the data$ The input image +ill be classified based on the nearest neighbor algorithm the features that closely resemble to the data$
,/16/8 7eat!re E9tra"t#on
From the segmented lungs of the image regions in the lungs are mar"ed and each of these gray level co-occurrence matri1es is constructed$ It is an nMn matri1 +here n is the number of distinct intensity values +hich sho+s the relationship bet+een various intensities$ This +ill give idea of spatial relationship bet+een intensities$
,/16/2 E9pe"te Re+!(t
The follo+ing series of images sho+ +hat is e1pected to occur during processing$
3a4
3b4
3c4
3d4
Figure :$.?$>$.9 Image ,rogress using the ,roposed System The figures above sho+s the development of the chest /-ray image during image processing using the proposed system +here 3a4 is the 7riginal Image 3b4 Binari5ed Image 3c4 the Segmented *ungs 3d4 is for Feature E1traction of the *ungs$
,/11 Stat#+t#"a( Ana(.+#+ o' Data
To be able to determine the reliability of the proposed pro&ect several tests +ill be performed by the proponents$ The suitable fit to determine the reliability of the proposed pro&ect is by using Cohen8s Dappa coefficient +hich measures inter-rater agreement of categorical output$
,/11/1 Cohen:+ ;appa Te+t#n
Cohen8s Dappa 3Cohen .@>?4 +as presented as a measure of agreement +hich maintains a strategic distance from the issue depicted by ad&usting the observed proportional agreement to ta"e account of the measure of understanding +hich +ould be e1pected by chance$ Sample si5e estimation using an inter-rater reliability study the proponents must resolve ho+ many sub&ects should be selected and ho+ many raters should rate them$ Flac" et al$ 3.@==4 have recommended a method of calculating the optimal number of sub&ects for Cohen8s "appa coefficient +hen the quantity of raters is constrained to t+o$ The ideal number of sub&ects for a given inter-rater reliability coefficient is characteri5ed as the quantity of sub&ect that minimi5ed standard error connected +ith the percent
agreement bet+een t+o discretionary raters$ The variance agreement
,v
is
defined as v
=
( − Pa )
Pa 1
n
0here9 Pa
N percent agreement
n =¿ (equired number of sub&ects
The @J error margin connected +ith the percent agreement is 2 √ v
and if the proponent +ant it to remain belo+ a desired value
E then this goal +ill be accomplished by any number of sub&ect
n
that e1ceeds the desired value$ Since the smaller the number of sub&ects the better the optimal sub&ect is given by n
=
1 E
2
0here9 E=¿ 'esired error margin
Cohen8s Dappa 3Cohen .@>?4 illustrates the minimum number of sub&ect required on accomplishing the desired @J error margin$ It ta"es after that the evaluated percent agreement to fall +ithin J of its trueG error-free value the collected data of ;?? sub&ects is required$ 2ence
n =400 sample ¿ ¿
After determining the required sample si5e +ith a J desired error margin the proponents +ill be able to start determining the Cohen8s Dappa value given by the equation Pa− Pe k = 1− Pe
0here9 k =¿ Cohen8s Dappa value Pa
=¿ (elative observed agreement
Pe
N 2ypothetical probability of chance agreement
Computing for the relative observed agreement
Pa and the
Pe the normal numbers
hypothetical probability of chance agreement
concurring are found as in chi-squared test by ro+ total times column divided by grand total$ %enerally a Dappa has a range of ? to .$?? values +ith larger values indicating better reliability$ Benchmar"ing the result is essential for communicating the results reliability$ And also provides guidelines to assist practitioners +ith the use of agreement statistics$ *andis and Doch 3 .@<<4 proposed an e1tend agreement that can be qualified as ,oorG SlightG FairG !oderateG SubstantialG and Almost ,erfectG depending on the magnitude of Dappa$ A "appa value of ;?J to >?J indicates a moderate agreement level >?J to =?J and =?J to .??J indicates substantial and almost perfect agreement levels respectively$
Sample no$
.
6
:
;
$$$
;??
(ater . (ater 6 Table . Sample data for identifying the agreement bet+een doctorOs output and proposed pro&ectOs output
The proponents are required to chec" that each samples +ill identify +hether the /-ray films contains a disease or it is classified as healthy$ T+o raters +ill identify the disease (ater . as the doctors output and rater 6 defined as the proposed pro&ect8s output$ The samples output +ill be abbreviated as follo+s9
pG N pneumonia hG N healthy poG N pneumonia +ith other disease oG N other disease
(ater .
(ater 6
pG
hG
(o+ Totals poG
pG hG poG oG Column Total Table 6 Contingency table for the proposed output
oG
