profile - knastik 2016 - fakultas teknologi informasi ukdw · pdf filesystem diagram block....
TRANSCRIPT
10/11/2016
1
[email protected]@ugm.ac.id
Intelligent Medical Imaging for Breast Cancer Detection and
Diabetic Retinopathy
Hanung Adi Nugroho
Inovasi E-Health and Biomedika untuk Indonesia
[email protected]@ugm.ac.id
Research and Development of Intelligent Medical Imaging
Profile
Dr. Ir. Hanung Adi Nugroho
Department of Electrical Engineering and Information TechnologyFaculty of Engineering, UNIVERSITAS GADJAH MADAJl. Grafika 2, Kampus UGM, Yogyakarta 55281, IndonesiaTelp./ fax. +62-274-552305Email: [email protected]; [email protected]
Research areas: Biomedical signal and image processing and analysis; computer vision; medical instrumentation; patternrecognition; data mining; statistical data analysis.
Bachelor of Engineering (S.T.) – Teknik Elektro, Universitas Gadjah Mada, Yogyakarta, Indonesia (2001)
Master of Engineering (M.E.) – School of Information Technology and Electrical Engineering, The University ofQueensland, St Lucia, Brisbane, Australia (2005)
Doctor of Philosophy (Ph.D.) – Electrical and Electronics Engineering Department, Universiti TeknologiPETRONAS, Seri Iskandar, Malaysia (2012)
10/11/2016
2
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research
Medical imaging - Overview
Currently medical imaging is limited to theacquisition of images of the human organs/ body
Medical imaging refers to the techniques andprocesses used to create images of the humanbody for clinical purposes (medical proceduresseeking to reveal, diagnose or examine disease).
Medical imaging can be seen as the solution ofmathematical inverse problems. This means thatcause (the properties of living tissue) is inferred fromeffect (the observed signal)
Analysis of the images obtained is performed clinically by experts
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research
Medical imaging - TechnologyGamma ray : positron emission tomography (PET)
X ray : computed tomography (CT)
a short-lived isotope, such as 18F, is incorporated into a substance used by the body such as glucose which is absorbed by the tumour of interest
Expose to x-ray radiation, repeated scans must be limited to avoid health effects
10/11/2016
3
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research
Magnetic resonance imaging (MRI)
uses powerful magnets to polarise and excite hydrogen nuclei (single proton) in water molecules in human tissue, producing a detectable signal which is spatially encoded resulting in images of the body
excellent soft-tissue contrast
no known long term effects of exposure to strong static fields
health risks associated with tissue heating from exposure to the RF field and the presence of implanted devices in the body, such as pace makers
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research
Medical imaging - TechnologyUltrasound : ultrasonography
Fundus cameraRetinal image
H-F sound, 2-10MHz, safe, 2D moving images
10/11/2016
4
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research
Issues, challenge and approach
Issues
• Harmful (radiation, contrast agent)
• Specialized device – difficult to use -highly trained operator needed
• Expensive (Initial cost, Maintenance)
• Image Acquisition only, little or no analysis for diagnostic purposes, subjective
Issues
• Harmful (radiation, contrast agent)
• Specialized device – difficult to use -highly trained operator needed
• Expensive (Initial cost, Maintenance)
• Image Acquisition only, little or no analysis for diagnostic purposes, subjective
Approach
From medical imaging (imageacquisition with enhancement) tomedical image analysis (featureextraction, classification, patternrecognition, measurements) resultingin intelligent imaging (decisionsupport systems)
Approach
From medical imaging (imageacquisition with enhancement) tomedical image analysis (featureextraction, classification, patternrecognition, measurements) resultingin intelligent imaging (decisionsupport systems)
Challenge
To develop intelligent medical imaging system which is objective in analysis that is safe to the patients.
Challenge
To develop intelligent medical imaging system which is objective in analysis that is safe to the patients.
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research
Current research in intelligent medical imaging system at DTETI-UGM
Ophthalmology (Diabetic retinopathy)Radiology (Breast cancer)
Diabetic retinopathy GlaucomaBreast cancer
10/11/2016
5
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Intelligent Medical Imaging Research in Breast Cancer
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerBreast Cancer
Breast cancer is a disease in which malignant(cancer) cells form in the tissues of the breast.
10/11/2016
6
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerBreast Cancer Detection
No Radiation
More Detail
Expensive
Limited availability
Low cost
Short acquisition time
No radiations
High availability
Convenient
more sensitive
Depend on operator
Radiologist s experience
Inconsistency of interpretation
Breast compression
Low-dose X-ray
Just for particular patient
Limited availabilityBreast Self Exam
Mammograms
USGMRI
• Elaborate the radiology knowledge into image processing and analysistechnology
• Assist radiologists to diagnose nodule
CAD
CAD : Computer Aided Diagnosis
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerResearch Objective
To develop a computer aided diagnosis (CAD)system for classifying breast nodule in ultrasound(US) images to distinguish benign and malignantnodules.
10/11/2016
7
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Diagnosis of Breast Cancer using Ultrasound
A breast ultrasound is a scan that uses penetrating sound waves thatdo not affect or damage the tissue and cannot be heard by humans.
Normal Abnormal
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Methodology
10/11/2016
8
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Image Acquisitions
Image Processing Analysis
Image Display
Radiologists
Computer Aided System
Diagnosis
USG Image
Scheme of CAD System
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
USG Images
RoI (1)
Noise and Marker
Reduction(3)
Segmentation (4)
Feature Selection(6)
Malignant / Benign
Preprocessing
GrayScale Conversion (2)
Feature Extraction (5)
• Moment based features
• Geometry Feature• Texture Feature
Birads based Classification (7) Diagnosis (8)
System Diagram Block
10/11/2016
9
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Nodule
Background
Segmented Area
Posterior Characteristic
Margin Characteristic
Echo Pattern Characteristic
Texture Features
Texture Analysis
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerGeometry Features
Geometric feature is constructed by a set of geometrical elements such as points, lines, curves or surfaces
����������� = ����
������ ����������
�������� =����� ���� �����
����
������� ���������� =
1� ∑ � � . exp (
�2���)�
����
�������
������ ����� =��� ��������
��� ��������
��������� =������ ���������
���������
�������� =������ ����
������ ����
����������� =4�. ����
����������
10/11/2016
10
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Geometry and Moment Based Features
Nodule
Background
Shape characteristics
Margin characteristics
Moment Based Analysis
Geometry Analysis
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerResearch Roadmap
2014
2015
Shape and Boundary
Echo Pattern
Prototype 1
2016Margin and Posterior Features
Prototype 2
Clinical TrialIntegrated
Modules
2018
10/11/2016
11
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Results
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Unmarked Hypoechoic or Hypoechoic
• Round - Oval
• Irregular
• Circumscribed
• Circumscribed
• Not Circumscribed
• Not Circumscribed
Benign
Malignant
Malignant
Malignant
Diagnosis Rules for i-Brids V.1
10/11/2016
12
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
ImageCapturing
ROI and FilteringSegmentation and Feature Extraction Diagnosis
i-Brids Prototype.1
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
0.00%10.00%20.00%30.00%40.00%50.00%60.00%70.00%80.00%90.00%
100.00%
Accuracy Sensitivity Specificity PPV NPVShape 96.20% 94.70% 97.90% 94.73% 97.91%
Margin 80.90% 79.50% 82.50% 78.50% 82.50%
Echo 91.23% 95.83% 87.88% 85.19% 96.67%
Performance Analysis of CAD System
10/11/2016
13
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
No Statistical AnalysisDiagnosis
Malignant Benign1 Number of Features Agreement 19 132 Number of Features due to Chance 12.5 6.53 Total Number of Subjects 384 Total Number of Agreement 32
5 Number of Agreement due to chance 19
6 Kappa 0.68
Statistical Analysis
Kappa statistics are commonly used to indicate the degree of agreement of nominalassessments made by multiple appraisers.A Kappa 0.68 is in the “substantial” agreement range between radiologists and CAD system.
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Unmarked Hypoechoic or Hypoechoic
• Circumscribed
• Not Circumscribed
• No Posterior Feature
• Enhancement
Benign/Malignant
Benign
• Shadowing Malignant
• No Posterior Feature
• Enhancement
Malignant
Malignant
• Shadowing Malignant
Diagnosis Rules for i-Brids V.2
10/11/2016
14
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
ImageCapturing
ROI and FilteringSegmentation and Feature Extraction Diagnosis
i-Brids Prototype 2
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerAccuracy of CAD System
76.00%78.00%80.00%82.00%84.00%86.00%88.00%90.00%92.00%94.00%96.00%98.00%
Margin Posterior DiagnosisRadiologist 1 89.47% 84.21% 97%
Radiologist 2 89.47% 86.84% 97%
10/11/2016
15
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
92%93%94%95%96%97%98%99%
100%
Sensitivity Specificity PPV NPVRadiologist 1 100% 94.74% 95% 100%
Radiologist 2 100% 94.74% 95% 100%
Performance Analysis of CAD System
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
No Statistical Analysis
Margin Posterior Diagnosis
Circumscribed Indistinct EnhancementNo
PosteriorShadow Malignant Benign
1 Number of Features Agreement 22 16 21 3 9 19 19
2 Number of Features due to Chance 12.74 6.74 11.6 0.79 3.47 9.5 9.5
3 Total Number of Subjects 38 38 38
4 Total Number of Agreement 38 33 38
5 Number of Agreement due to chance 19.47 19 15.87
6 Cohen's Kappa 1 0.774 1
Statistical Analysis
A Kappa 1 is in the “perfect” agreement range between two radiologistA Kappa 0.74 is in the “substantial” agreement range between two radiologist
10/11/2016
16
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerVideo of i-Brids
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerPotential Market
HealthLaboratories
Hospitals/Clinics Puskesmas
1380 1599
3451
Number of Health Care Fasilities in Indonesia
Total: 6430
10/11/2016
17
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast CancerRecognition
[1] H. A. Nugroho, N. Faisal, I. Soesanti, and L. Choridah, “Analysis of Computer Aided Diagnosis on Digital Mammogram Images,” in 2014 InternationalConference on Computer, Control, Informatics and Its Applications Analysis, 2014, pp. 25–29.
[2] A. Nugroho, H. A. Nugroho, and L. Choridah, “Active Contour Bilateral Filter for Breast Lesions Segmentation on Ultrasound Images,” in 2015International Conference on Science in Information Technology (ICSITech) Active, 2015, pp. 36–40.
[3] H. A. Nugroho, Y. Triyani, M. Rahmawaty, , I. Ardiyanto ,and L. Choridah, “Performance Analysis of Filtering Techniques for Speckle Reduction onBreast Ultrasound Images,” in 2016 International Electronics Symposium (IES), 2016, pp. 454–458.
[4] M. Rahmawaty, H. A. Nugroho, Y. Triyani, I. Ardiyanto, and I. Soesanti, “Classification of Breast Ultrasound Images based on Texture Analysis,” iniBioMed 2016, 2016, pp. 84–89.
[5] Y. Triyani, H. A. Nugroho, M. Rahmawaty, I. Ardiyanto, and L. Choridah, “Performance Analysis of Image Segmentation for Breast UltrasoundImages,” in ICITEE 2016, 2016, no. October, pp. 415–420.
[6] H. K. N. Yusufiyah, H. A. Nugroho, T. B. Adji, and A. Nugroho, “Feature Extraction for Classifying Lesion ’ s Shape of Breast Ultrasound Images,” 2ndInt. Conf. Inf. Technol. Comput. Electr. Eng., pp. 105–109, 2015.
[7] H. A. Nugroho, H. Khuzaimah, N. Yusufiyah, T. B. Adji, and A. Nugroho, “Zernike Moment Feature Extraction for Classifying Lesion ’ s Shape of BreastUltrasound Images,” in 7th International Conference on Information Technology and Electrical Engineering (ICITEE), 2015, pp. 458–463.
[8] H. A. Nugroho, N. Faisal, I. Soesanti, and L. Choridah, “Identification of Malignant Masses on Digital Mammogram Images based on Texture Featureand Correlation based Feature Selection Hanung,” in 6th International Conference on Information Technology and Electrical Engineering (ICITEE),2014.
[9] H.R. Fajrin, H. A. Nugroho, and I. Soesanti“Ekstraksi Ciri Berbasis Wavelet Dan Glcm Untuk Deteksi Dini Kanker Payudara Pada Citra Mammogram,”in SNST, 2015, pp. 47–52.
[10] M. Sahar, H. A. Nugroho, Tanur, I. Ardiyanto, and L. Choridah “Automated Detection of Breast Cancer Lesions Using Adaptive Thresholding andMorphological Operation,” in International Conference on Information Technology Systems and Innovation (ICITSI), 2016.
[11] Tianur, H. A. Nugroho, M. Sahar, R. Indrastuti, and L. Choridah, “Classification of Breast Ultrasound Images based on Posterior Feature,” inInternational Conference on Information Technology Systems and Innovation (ICITSI), 2016.
Breast Cancer :
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Breast Cancer
Team Members and CollaboratorsDepartment Electrical Engineering and Information TechnologyFaculty of EngineeringUniversitas Gadjah Mada
Department of Radiology Sardjito Hospital, Yogyakarta
• H A Nugroho • I Ardiyanto• M Rahmawaty • Y Triyani• M Sahar
• L Choridah• R. Indrastuti• A. Mardhiah
• Tianur• A Nugroho• D A Husna• H Khuzaimah• R L Buana
10/11/2016
18
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
What is diabetic retinopathy
TYPE 1 DIABETES: when the pancreasdoesn’t produce insulin
TYPE 1 DIABETES: when the pancreasdoesn’t produce enough insulin (or theinsulin cannot be processed)
GESTATIONAL DIABETES: when theinsulin is less effective during
pregnancy
your body needs insulin to transform glucose into energy
Types of diabetes:
10/11/2016
19
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
What is diabetic retinopathy
Diabetic Nephropathy Diabetic Neuropathy
Diabetic Cardiomyopathy
Diabetic Retinopathy(DR)
DR is retinopathy (damage to the retina) caused by complications of diabetes mellitus, which could
eventually lead to blindness.
Fact : - Nearly all patients of type-1 diabetes and 60% of
patients of type-2 diabetes indicate retinopathy.- DR is the leading cause of the blindness in
developing countries among adults aged 20-74 years.
Normal vision DR vision
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
Diabetes : fact and figures
Reported by International Diabetes Federation (IDF), 2015
“Worldwide”2015: 415 million people with diabetes2040: 642 million people with diabetes
10/11/2016
20
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
The pathologies of DR
new blood vessels
Haemorrhages
exudates
Micro aneurysms
Moderate NPDR
Mild NPDR
No DR
Proliferative DR
Severe NPDR
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
Issues, challenges and approachesIssues
Diabetes mellitus affect ~10% population (DR is a real concern -epidemic stage?)
Needs access to ophthalmologist with fundus camera equipment
Low contrast Fundus images requiring Fluorescein angiography -an invasive procedure
Challenges
1. Can we develop a screening & grading system to be made accessible to all diabetes patients?
2. Can we detect DR early even before patient have visual problems?
3. Can we make non-invasive procedure as effective?
Fundus camera technology+
Image Processing & Computer Vision
10/11/2016
21
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
Haemorrhages detection
EnhancementEnhancement Haemorrhages candidatesHaemorrhages candidates Detected HaemorrhagesDetected Haemorrhages
Pre-processing
Green and V band extraction
Histogram matching
Opening operation
Contrast enhancement Haemorrhages
candidate detection Post-processing
Retinal vessels detection
Retinal vessels elimination
Double length filtering
Masking operation
Two-dimensional matched filtering
Fundus image
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
Hard exudates detection
Fundus image Filtered imageHard Exudates
Detected Hard Exudates
Green channel extraction
Complement operation
Matched filter
Optic disc (OD) detection[1]
Removal OD and Morphological
operation
Detected ODCandidate Exudates
Removal OD andCandidate Hard Exudates
[1] H. A. Nugroho, K. W. Oktoeberza, T. B. Adji, and M. B. Sasongko, "Segmentation of exudates based on high pass filtering in retinal fundus images," in 2015 7th International Conference on Information Technology and Electrical Engineering (ICITEE), 2015, pp. 436-441.
10/11/2016
22
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
2015
2016
2017
2018
DR pathologies detection DR screening
system
DR monitoring and
grading system
Micro aneurysms detection
Optic disc detection
Macula detection
Analysis of DR pathologies
Haemorrhages and hard exudates detection
Clinical study
System evaluation
FAZ detection
Classification
Research roadmapGeneral : to develop a system to assist the ophthalmologists in monitoring and diagnosing
diabetic retinopathy disease.
First year: to develop algorithms in each module to detect structures and pathologies in DR retinal image.
Second year: to integrate the modules and develop an algorithm for screening DR system.
Third year: to test the system based on clinical study for monitoring and grading system.
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
Recognition International Conferences
[1] H. A. Nugroho, D. A. Dharmawan, I. Hidayah, and L. Listyalina, "Automated microaneurysms (MAs) detection in digital colour fundus images using matched filter," in Computer, Control, Informatics and its Applications (IC3INA), 2015 International Conference on, 2015, pp. 104-108.
[2] H. A. Nugroho, L. Listyalina, N. A. Setiawan, S. Wibirama, and D. A. Dharmawan, "Automated segmentation of optic disc area using mathematical morphology and active contour," in Computer, Control, Informatics and its Applications (IC3INA), 2015 International Conference on, 2015, pp. 18-22.
[3] H. A. Nugroho, D. Purnamasari, I. Soesanti, K. W. Oktoeberza, and D. A. Dharmawan, "Detection of foveal avascular zone in colour retinal fundus images," in 2015 International Conference on Science in Information Technology (ICSITech), 2015, pp. 225-230.
[4] H. A. Nugroho, K. W. Oktoeberza, T. B. Adji, and M. B. Sasongko, "Segmentation of exudates based on high pass filtering in retinal fundus images," in 2015 7th International Conference on Information Technology and Electrical Engineering (ICITEE), 2015, pp. 436-441.
[5] H.A. Nugroho, L. Listyalina, and D. A. Dharmawan, "A New Approach for Detection of Retinal Haemorrhages in ColourFundus Images," presented at the International Seminar on Sensors, Instrumentation, Measurement and Metrology, 2016.
[7] I. Ardiyanto, H.A. Nugroho, and R. L. B. Buana, "Maximum Entropy Principle for Exudates Segmentation in Retinal Fundus Images," presented at the International Seminar on Sensors, Instrumentation, Measurement and Metrology, 2016.
[8] H.A. Nugroho, W.KZ. Oktoeberza, I. Ardiyanto, R.L.B. Buana, and M. B. Sasongko, "Automated Segmentation of Hard Exudates Based on Matched Filtering," presented at the International Seminar on Sensors, Instrumentation, Measurement and Metrology, 2016.
10/11/2016
23
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
Recognition Journals
[1] H. A. Nugroho, K. W. Oktoeberza, T. B. Adji, and F. Najamuddin, "Detection of Exudates on Color Fundus Images using Texture Based Feature Extraction," International Journal of Technology, vol. 6, p. 04, 2015.
[2] H.A. Nugroho, D.A. Dharmawan, and L. Listyalina, "Automated Segmentation of Foveal Avascular Zone (FAZ) in Digital Colour Retinal Fundus Images," International journal of biomedical engineering and technology, 2016.
[email protected]@ugm.ac.id
Intelligent Medical Imaging Research in Diabetic Retinopathy
Team members and Collaborator
Rapid Assessment Diabetic Retinopathy and Intelligent System Research GroupsDepartment of Electrical Engineering and Information Technology, Faculty of Engineering
Universitas Gadjah Mada, Indonesia
(Hanung Adi Nugroho, Noor Akhmad Setiawan, Teguh Bharata Adji, Indriana Hidayah, Igi Ardiyanto, Ratna Lestari Budiani Buana, Dhimas Arief Dharmawan,
Latifah Listyalina, Dewi Purnamasari, Widhia Oktoeberza KZ)
Department of Ophthalmology, Sardjito Hospital, Yogyakarta, Indonesia
(dr. Muhammad Bayu Sasongko, dr. Kartika Dhani)