20050831#lab conference#김진성
-
Upload
yonsei-university-college-of-medicine -
Category
Education
-
view
2.160 -
download
0
Transcript of 20050831#lab conference#김진성
![Page 1: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/1.jpg)
Computer-Aided Diagnosis System for Ground-Glass Opacity
using MDCT Images
2005. 8. 31 Jin Sung Kim
![Page 2: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/2.jpg)
2005 RDMI Lab Conference
Contents
• Introduction– Ground Glass Opacity– Purpose & Idea
• Methods– Concept of Algorithm– Image Processing Module– Texture Analysis– Support Vector Machine
• Further Study
![Page 3: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/3.jpg)
2005 RDMI Lab Conference
Ground Glass OpacityIntroduction
![Page 4: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/4.jpg)
2005 RDMI Lab Conference
Introduction
• Focal ground-glass opacity (GGO) is a finding of early adenocarcinoma or its precursor
• Ground-glass opacity (GGO) detection becomes more simple & efficient after extraction of vessels & solid nodules using 3DMM algorithm
• In this exhibition, I will describe our automated GGO nodule detection program that takes advantages of 3D volumetric data from multi-slice CT
• Japan-Korea Joint Symposium on Medical ImagingJapan-Korea Joint Symposium on Medical Imaging
2005. 9.21~22. 서울 고려대학교 구로병원
Introduction
![Page 5: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/5.jpg)
2005 RDMI Lab Conference
Purpose & Idea
• Previous research groups– General 2D slice CT image– Neural Networks (MLP)
• This Study– 3DMM algorithm – GGO Enhanced Image– Support Vector Machine
Introduction
![Page 6: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/6.jpg)
2005 RDMI Lab Conference
Material
• 10 patients have GGO nodule
• 120KVp, 120 effective mAs
• 3.2 mm slice thickness
• Average 126.9 images/patient
• Programming based on Matlab
• OSU LIBSVM in matlab
Materials & Methods
![Page 7: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/7.jpg)
2005 RDMI Lab Conference
Methods
Air Component
Soft TissuePulmonary VesselSolid nodules
GGO nodules
CT Noises
After soft tissue & air component extraction, GGO detection is more easier !!!!.
IntroductionMaterials & Methods
![Page 8: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/8.jpg)
2005 RDMI Lab Conference
Overall AlgorithmIntroductionMaterials & Methods
![Page 9: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/9.jpg)
2005 RDMI Lab Conference
3D Volume of segmented lung regionMethodsMaterials & Methods
![Page 10: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/10.jpg)
2005 RDMI Lab Conference
3D Image of Pulmonary Vessel extraction using 3DMM algorithm
MethodsMaterials & Methods
![Page 11: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/11.jpg)
The GGO was not include in vessel
We can find a GGO in right lung region
Original CT Image – Soft Tissue Image Using thresholding, GGO can be found
![Page 12: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/12.jpg)
2005 RDMI Lab Conference
ROI matrix, texture analysis
• 32x32 matrix
• Texture– Mean– Standard
deviation– Skewness– Kurtosis– Area– Compactness– Eccentricity– Etc…
Materials & Methods
![Page 13: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/13.jpg)
2005 RDMI Lab Conference
1. Final Extraction Image
![Page 14: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/14.jpg)
2005 RDMI Lab Conference
2. GGO Enhanced Image
![Page 15: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/15.jpg)
2005 RDMI Lab Conference
2. GGO Enhanced Image
![Page 16: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/16.jpg)
2005 RDMI Lab Conference
3. Original CT Image
![Page 17: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/17.jpg)
2005 RDMI Lab Conference
3. Original CT Image
![Page 18: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/18.jpg)
2005 RDMI Lab Conference
Texture AnalysisMaterials & Methods
![Page 19: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/19.jpg)
2005 RDMI Lab Conference
Support Vector Machine
• 11 parameters, 29 cases• Using OSU LIBSVM in matlab• Kernel Type– Polynomial, degree:5
• [AlphaY, SVs, Bias, Parameters, nSV, nLabel]= u_PolySVC(T_Samples, T_Labels, Degree);
• [Labels, DecisionValue]= SVMClass(T_Test, AlphaY, SVs, Bias, Parameters, nSV, nLabel);
• Result– Label : [0 0 1 1]– DecisionValue
Materials & Methods
![Page 20: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/20.jpg)
2005 RDMI Lab Conference
Results
• Image processing
• Texture analysis
completed!
• SVM classification
진행중 ...
• Final Results
![Page 21: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/21.jpg)
2005 RDMI Lab Conference
Further Study
• SVM Training, Testing– 많은 Case, – Training set 과는 다른 Test set 적용
• 통계처리– Sensitivity, Specificity, – ROC curve analysis
• GUI development
![Page 22: 20050831#lab conference#김진성](https://reader031.fdocument.pub/reader031/viewer/2022031518/5a64a6ac7f8b9a5d568b4fd5/html5/thumbnails/22.jpg)
Thank you!!!