Page 1
PortableRetinaEyeScanningDevice
1
EngineeringScienceDepartmentSonomaStateUniversityStudents:CristinFaria&DiegoA.EspinosaFacultyAdvisor:Dr.SudhirShresthaIndustryAdvisor:BenValvodinosClient:NorthBayVisionCenter
Website:http://diabeticretinopathyssu.weebly.comEmail:[email protected] @sonoma.edu
Page 2
1. ProblemandSolution2. GeneralSystemOverview3. SystemDescriptionandTechnicalComponents4. MarketingandEngineeringRequirements5. TestingandResults6. MaterialsandCosts7. Timeline8. Challenges9. LessonsLearned10. FutureWork11. Conclusion
2
Overview
Page 3
3
Problem
• Millionsofpeopleintheworldarediagnosedwithdiabeteseveryyear.
• Leadingtodiabeticretinopathy,adiseasefoundintheretinaoftheindividual.
• Oftenleadingtoblindnessifleftuntreated.
• Thisdiseaseisnoteasilydetected,andnormallynotreversiblewhenfoundinthepatient.
Page 4
4
PreviousWorksandourSolution
PeekVision:● Createdcamerasandsoftwareapplicationsonsmartphonestoscanpatients’retinas,butdoes
notutilizemachinelearningsorunsslowly.
Epipole:● Handheldretinalfunduscamera,mustbeconnectedtoWindowsorAndroidandtheInternet.
OurSolution:● AstandaloneproductthatisabletogiveinstantresultsbyutilizingMachineLearningand
ImageProcessing.● NoInternetconnectionnecessary.
Ourdeviceisadiagnostictool,andresultsgivenfromdeviceshouldbetakentoalicensedmedicalprofessional
Page 5
5
FinalProduct
● Imageofourfinalproduct.
● Howcomputer,raspberrypi,camera,LEDandbatteryareallconnected.
Page 6
Explainalltheparts– diagram
6
SystemOverview
● Systemoverviewthatlooksoverentiredeviceandshowshoweachpieceisconnected.
● Basicoverviewofhowoursystemworksandcanbeimplemented.
Page 7
7
HardwareDesign
● Visualrepresentationofallofthehardwarecomponentsweutilized.
● RaspberryPiisthecentralunit.
● Demonstrateshowallcomponentsinteractwitheachother.
Page 8
8
SoftwareDesign
● Thisflowchartgivesageneraldescriptionofwhatourprogramdoes.● Initializes,takesapicture,determineswhetherornottheretinaishealthyand
displaystheresultviaLED.● ThisprogramutilizesthemachinelearningtoolboxinMATLAB,RaspberryPi3
ModelB,andLEDtogiveaccurateresults.
Page 9
Requirements
MarketingRequirements● Thedevicewillbereliableindeterminingthe
healthstatusofapictureofapatient'sretina.● Thedevicewillnotbefullyautomated,butwill
besimpletouse.● Thedevicewillcapturepicturesofaretina
fundusimageswithhighresolution.● Thedevicewillbemarketedtowardtrained
physiciansandhealthpractitionersinvolvedintreatingpatientsinruralregionswithlimitedaccesstoophthalmologytestingtechnologythroughouttheworld.
9
EngineeringRequirements● Theaccuracyofthescanningmustbeover90%
inorderforthedevicetobereliableindeterminingthestatusofthepicture.
● Thedevicewillconsistoffourcomponents:RaspberryPi3ModelB,ArduCAM(camera),BatteryPack,andLEDboxlight.
● TheprojectrequiresinterfacingMATLABwiththedevicebut,minimalcommandsareusedtoexecutethedevice.
● Functionalityofthedevicewillbeaprecursortotakingascanofapatient’sretina,apracticedonebylicensedindividuals.
Foracompletelistofourrequirementsvisitourwebsite:http://diabeticretinopathyssu.weebly.com
Page 10
10
MachineLearningandtheConfusionMatrix
WhatisMachineLearning?● Itisatypeofcomputerprogrammingwhichusesdatatoperformatask.● Themoredata,orimagesyouaddtoaprogram,thebetteritperforms.
WhatistheConfusionMatrix?● Itisatablethatisusedtodescribetheperformanceofaclassifier(methodusedtoclassify
data)onasetoftestdatawherethetruevaluesareknown.● Inourprojectthemostimportantpartofthematrixlookedatthefalsenegativerateand
truepositiveratetodeterminetheoverallaccuracyofouralgorithm.
Page 11
11
MachineLearningandourProject
● Ourprojectutilizesmachinelearningandimageprocessinginordertorunthealgorithm,anddifferentiatebetweenimages.
● Inordertocheckbetweenhealthyretinaimagesanddiabeticretinaimagesouralgorithmlooksatbloodvessels,darkspots,damagetotheretinashapetounderstandthedifferencesbetweenthetwocategories.
Page 12
12
ClassifierTest
● Testusedtodeterminewhichtypeofclassifierwouldbebestsuitedtotestouralgorithmmostaccurately.
● Tested21differentclassifiersandfoundthat8hadsamebestaccuracyof60%.
● Thistestwascompletedbeforeweimprovedtheaverageaccuracyofouralgorithm.
● LookedatconfusionmatricesandconcludedthatLinearSupportVectorMachine(SVM)wouldgiveusthebestresult.
Page 13
13
AccuracyImprovementTest
● InitiallythebestaccuracyfortheLinearSupportVectorModelwas60%whichwas30%lowerthanourminimumgoalaccuracyof90%.
● ToincreaseouraccuracyfirstweeliminatedourGlaucomagroupfromourcode,thisincreasedouraverageaccuracyto83%.
● IncreasedthenumberofimagesinDiabeticRetinopathyfrom15to45,thisactionincreasedouraverageaccuracyto91.7%.
● OurFalsediscoveryrateforDiabeticRetinopathyis2%andis22%forhealthyretinas.
Page 14
14
AlgorithmAccuracyTest
● Testedtheaccuracyofthealgorithm,bytesting60images,30withdiabeticretinopathyand30healthyretinalimages.
● Imagestestedwerenotincludedinourtestingalgorithm,weretakenbyourcamera,andhadnotbeenpreviouslyseenbyouralgorithm.
● Wewereabletoconclude5healthyimagesweregivenaninaccurateresult,andonlyasingleimagewithdiabeticretinopathywasgivenaninaccurateresult.
● Givenanaverageaccuracyof90%,diabeticretinopathyaccuracyof97%,andhealthyaccuracyof83%.
● Diabeticretinopathyhadafalsediscoveryrateof3%andhealthyhadafalsediscoveryrateof17%.
Page 15
15
AutomationTest
● Automatedtakingpictures,savingthem,andtestingthem.
● Itautomaticallytakeimageswithanexternalcamera,savesthemtoaspecificlocation,andteststhemwithouralgorithm.
● Thisprogramworkswithasingleclickofamouse.
Page 16
16
HealthIndicatorTest
● TestedtoconfirmthattheLEDwascompatiblewithMATLABandwouldgiveusthecorrectresult.
● IftheLEDturnsonitmeanstheimagehasdiabeticretinopathy,ifnottheimageishealthy.
● TestedImageresultisDiabeticRetinopathy.
Page 17
17
MaterialsandCosts
● SpecialThankstoSOURCEwhogaveus$400tocompleteourproject.
● SpecialthankstoSharahmMarivaniforprovidingcomponents.
Page 18
18
Timeline
● TestingandDebuggingourprojecttooklongerduetocameraandRaspberryPiissues.
● Communicationledtosomedrawbacksandtimeconstraints.
● GettingMATLABtocommunicatecorrectlywithRaspberryPicauseddelays.
● Evenwiththeseissueswewerestillabletomakeacompletedproject.
Page 19
• WehadtochangetheideaofourprojectfromNVIDIAtoRaspberryPiduetolackofNVIDIAsupport.
• Utilizingmachinelearningandimageprocessing.
• GettingMATLABonRaspberryPi.
• Testingandupdatingouralgorithmtogetittoover90%accuracy.
19
Challenges
Page 20
● Progressisnotastraightpath,especiallywhenyouhaveaprojectthatismainlysoftwarebased.
● Thingsgowrong,andbythingswemeaneverything.
● Teamwork,anddedicationarevitalwhentakingonanewproject.
20
LessonsLearned
Page 21
21
FutureWork
● The next phase of our project will be to attach a retinal fundus camera to our device in order to take an image of a patient’s retina.
● Introducing, the product to doctors and health practitioners in regions that to do not have access to this technology, and make it so patients in these different regions have access to better medical care and are able to get treated faster.
Page 22
22
SpecialThanks
● We would like to thank our Professor Dr. Farid Farahamand, Faculty Advisor Dr. Sudhir Shrestha, Industry Advisor Ben Valvodinos, and Client North Bay Vision Center for giving us feedback, and helping us with the completion of our project.
● We would also like to thank our family and friends, for their encouragement and support throughout our senior design project, those actions and kind words did not go unnoticed.
Page 23
• https://www.aoa.org/patients-and-public/eye-and-vision-problems/glossary-of-eye-and-vision-conditions/diabetic-retinopathy
• http://www.diabetes.co.uk/news/2014/may/portable-eye-scanner-to-revolutionise-detection-of-diabetic-retinopathy-96133928.html
• http://www.who.int/mediacentre/news/releases/2003/pr86/en/• https://www.mathworks.com/discovery/machine-learning.html• https://www.sas.com/en_us/insights/analytics/machine-learning.html#• https://www.engineersgarage.com/articles/image-processing-tutorial-
applications• https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4463765/• http://onlinelibrary.wiley.com/doi/10.1046/j.1464-5491.2000.00333.x/full
23
References
Page 24
Questions/Comments
24
Questions
Page 25
25
ClassifierTestTable1
● Took 21 classifiers and looked at the average accuracy using the confusion matrix.
● Found that 8 different classifiers had same initial accuracy of 60%.
● These accuracies were our initial accuracies before adding anything to our algorithm.
Page 26
26
ClassifierTestTable2
● Looked at the True Positive Rate and False Negative Rate of top 8 classifiers.
● Was able to conclude from the test that Linear SVM gave us the best overall accuracy rating in each category.
● False Negative Rate was lower in all three categories and gave us a more well-rounded accuracy.
Page 27
27
AlgorithmImprovementTestMatrix1
● Single confusion matrix for Linear Support Vector Model.
● The top row specifies Diabetic Retinopathy, where 41 out of 45 images were correctly categorized, with an accuracy rating of 91%.
● Bottom row specifies the healthy category where 14 out of 15 were categorized correctly with an accuracy rating of 93%.
● Which gave an average accuracy of 92%.
Page 28
28
AlgorithmImprovementTestMatrix2
● Confusion matrix for Linear Support Vector Model, that shows true positive and false negative rates.
● For Diabetic retinopathy the true positive rate was 91% and false negative rate was 9%.
● For Healthy the true positive rate was 93% and false negative rate was 7%.
Page 29
29
AlgorithmAccuracyTestGraph
● BluebarisDiabeticRetinopathyandorangeisHealthy.
● Tested30imageswithDiabeticRetinopathy,andwasgiven29correctresults.
● Resultedina3%Falsenegativerate.
● Tested30HealthyImagesandwasgiven25correctresults.
● Resultedina17%Falsenegativerate.
Page 30
30
AutomationTest
● Codeusedinordertoautomateourprogram.
● WritteninMATLABandutilizesourmachinelearningalgorithm.