SlideShare uma empresa Scribd logo
1 de 49
Stereoscopic Display of Lung PET/
CT DICOM Scans using Perspective
     使用透視法於肺部 PET/CT DICOM 影像之三維立體顯示
                                                       Student:Yueh-Ju Chen
                                                    Advisor: Dr. Tang-Kai Yin
                   Institute of Computer Science and Information Engineering
                                            National University of Kaohsiung
•   Introduction

    •   Motivation

    •   Related Works

•   Proposed Approach

    •   DICOM Analysis

    •   Stereoscopic

•   Result

•   Conclusion and Future Work

                                 Institute of Computer Science and Information Engineering
                           2                              National University of Kaohsiung
Introduction



               Institute of Computer Science and Information Engineering
                                        National University of Kaohsiung
Background
•   Computed tomography:
    •   A medical imaging procedure
    •   Utilizing computer-processed
        X-rays to produce tomographic
        images or 'slices' of specific
        areas of the body
•   Stereoscopy:
    •   The illusion 3D depth from images on a 2D plane

                                          Institute of Computer Science and Information Engineering
                           4                                       National University of Kaohsiung
Motivation
•   3D effect get popular
•   Not a new technology
•   Medical diagnosis:
    •   Improve the efficiency of diagnosis
    •   Surgical simulation
    •   Education training

                                       Institute of Computer Science and Information Engineering
                             5                                  National University of Kaohsiung
Algorithm




            Institute of Computer Science and Information Engineering
                                     National University of Kaohsiung
Related Works



            Institute of Computer Science and Information Engineering
                                     National University of Kaohsiung
Medical Scans
•   DICOM file:

    •   File format
    •   DICOM Standards Committee
    •   Widely used by hospitals

•   Dividing into two parts:
    •   Image
    •   Header (metadata) files

                                    Institute of Computer Science and Information Engineering
                        8                                    National University of Kaohsiung
Maximum Intensity
         Projection (MIP)
•   Volume rendering method
•   Voxels with maximum intensity
•   Orthographic projection
    •   Cannot distinguish between left or right,
        front or back
•   Detection of lung nodules


                                        Institute of Computer Science and Information Engineering
                          9                                      National University of Kaohsiung
Standardized Uptake
        Value (SUV)
•   Distinguish between malignant lesions and
    benign tumor
•   Enhances the 3D nature of nodules
    •   Pulmonary bronchi and vasculature
•   Cut-off value for malignant lesion is 2.5


                                       Institute of Computer Science and Information Engineering
                         10                                     National University of Kaohsiung
Stereoscopic
•   Illusion of 3D depth from images on a 2D
    plane
•   3D viewer technology:
    •   Anaglyph
    •   Active shutter systems
    •   Polarization systems


                                  Institute of Computer Science and Information Engineering
                       11                                  National University of Kaohsiung
NVIDIA 3D Vision
•   Shutter glasses and driver software
•   Direct3D software
•   Mainstream consumers and PC gamers
•   Requirement:
    •   120 Hz LCD or CRT
        monitors, DLP-projectors
    •   NVIDIA graphics card

                                   Institute of Computer Science and Information Engineering
                      12                                    National University of Kaohsiung
Proposed Approach



              Institute of Computer Science and Information Engineering
                                       National University of Kaohsiung
DICOM Analysis



            Institute of Computer Science and Information Engineering
                                     National University of Kaohsiung
Calculation of SUV

•   Referred to as the dose uptake ratio
•   Main calculate source: PET DICOM
•   The related attributed tags:
    •   Rescale Slope tag
    •   Rescale Intercept tag


                                     Institute of Computer Science and Information Engineering
                            15                                National University of Kaohsiung
Step 1: Convert Pixel Value to
   Activity Concentration

•   Rescale Slope tag are vary for every image
    slice




                                     Institute of Computer Science and Information Engineering
                        16                                    National University of Kaohsiung
Step 2: Decay Calibration Factor




                        Institute of Computer Science and Information Engineering
               17                                National University of Kaohsiung
Step 3: Calculate SUV




                Institute of Computer Science and Information Engineering
          18                             National University of Kaohsiung
SUV




Number 147 and 195 slice (a)original PET (b)SUV (c) threshold with 2.5

                                                  Institute of Computer Science and Information Engineering
                                                                           National University of Kaohsiung
Non-body Pixels



                      Non-body
Original CT
                   pixels removed


                          Institute of Computer Science and Information Engineering
              20                                   National University of Kaohsiung
Body Mask




            Institute of Computer Science and Information Engineering
    21                               National University of Kaohsiung
Body Mask (cont.)




              Institute of Computer Science and Information Engineering
        22                             National University of Kaohsiung
Stereoscopic



           Institute of Computer Science and Information Engineering
                                    National University of Kaohsiung
Real 3D vs. Fake 3D
•   Fake 3D
    •   Converting 2D films into 3D
    •   Depth map
•   Real 3D
    •   Two views
    •   Two different cameras (or projections)

                                     Institute of Computer Science and Information Engineering
                       24                                     National University of Kaohsiung
Stereoscopic Principle

•   D: distance between the
    viewpoint and the screen

•   R: distance of stereo pair
    of images on the screen

•   S: distance between the
    perceived object and the
    screen



                                      Institute of Computer Science and Information Engineering
                                 25                            National University of Kaohsiung
Optical Angle
• Best viewing range:
    70~500cm

• Distance between the
    two eyes: 6.5~7cm




•
                             Institute of Computer Science and Information Engineering
                        26                            National University of Kaohsiung
Eye Separation
•   The most suitable for the 3D effect:
•   Distance: 140~210 cm
•   Optical angle: 2.86~1.91 degree




                                           Institute of Computer Science and Information Engineering
                              27                                    National University of Kaohsiung
Perspective




              Institute of Computer Science and Information Engineering
     28                                National University of Kaohsiung
Perspective




              Institute of Computer Science and Information Engineering
     29                                National University of Kaohsiung
Perspective




              Institute of Computer Science and Information Engineering
     30                                National University of Kaohsiung
Perspective




              Institute of Computer Science and Information Engineering
     31                                National University of Kaohsiung
Parallax




           Institute of Computer Science and Information Engineering
                                    National University of Kaohsiung
Positive and Zero
             Parallax
•   Positive Parallax
    •   Cross point of each eye sight with the
        screen
    •   Behind the screen
•   Zero Parallax
    •   Overlap on the screen
    •   No 3D effect

                                     Institute of Computer Science and Information Engineering
                        33                                    National University of Kaohsiung
Negative Parallax

•   Focus heating-point in front of the screen
•   Out of screen
•   The closer the screen is the smaller depth of
    field will be generated



                                      Institute of Computer Science and Information Engineering
                        34                                     National University of Kaohsiung
Parallax Adjustment




               Institute of Computer Science and Information Engineering
                                        National University of Kaohsiung
Result



         Institute of Computer Science and Information Engineering
                                  National University of Kaohsiung
NVIDIA 3D
  Vision
1. OpenGL QuadBuffer
      2. NVAPI
     3. 3D Video




                            Institute of Computer Science and Information Engineering
                       37                            National University of Kaohsiung
Experiment
   Environment
            ASUS G53J
      Platform: Win7 64bit
CPU: Intel i7-7400QM @1.73GHz
            RAM: 8GM
Graphic Card: NVIDIA GTX 460M
               1.5G



                                 Institute of Computer Science and Information Engineering
                            38                            National University of Kaohsiung
MIP


0 degree of MIP




100 degree of MIP
                    Institute of Computer Science and Information Engineering
      39                                     National University of Kaohsiung
MIP


240 degree of MIP




280 degree of MIP
                    Institute of Computer Science and Information Engineering
       40                                    National University of Kaohsiung
Perspective of Mean Volume
        Rendering



    0 degree of Perspective of Mean Volume Rendering




   100 degree of Perspective of Mean Volume Rendering
                                                Institute of Computer Science and Information Engineering
                                                                         National University of Kaohsiung
Perspective of Mean Volume
        Rendering



   240 degree of Perspective of Mean Volume Rendering




   280 degree of Perspective of Mean Volume Rendering
                                                Institute of Computer Science and Information Engineering
                                                                         National University of Kaohsiung
Perspective with Bilinear
     Interpolation



  0 degree of Perspective with Bilinear Interpolation




 100 degree of Perspective with Bilinear Interpolation
                                                 Institute of Computer Science and Information Engineering
                                                                          National University of Kaohsiung
Perspective with Bilinear
     Interpolation



 240 degree of Perspective with Bilinear Interpolation




 280 degree of Perspective with Bilinear Interpolation
                                                 Institute of Computer Science and Information Engineering
                                                                          National University of Kaohsiung
Conclusion
     &
Future Work

          Institute of Computer Science and Information Engineering
                                   National University of Kaohsiung
Conclusion
•   The stereoscopic image created by a perspective
    projection and applied with SUV calculation of PET
    scans in 3D shutter system.

•   Expending vision from 2D to 3D and the biggest
    difference between them is the depth information.

•   2D images cannot distinguish three points which is
    in the front or which is in the back, but after we
    applied the stereoscopic techniques it is more
    obvious and clear to distinguish points’ relation and
    distance between them

                                            Institute of Computer Science and Information Engineering
                            46                                       National University of Kaohsiung
Future Work

•   A medical analyze system with stereoscopic
    display
    •   More medical analyze functions
    •   Real time volume rendering
    •   Auto-stereoscopic


                                         Institute of Computer Science and Information Engineering
                         47                                       National University of Kaohsiung
Demo



       Institute of Computer Science and Information Engineering
                                National University of Kaohsiung
Q &A



       Institute of Computer Science and Information Engineering
                                National University of Kaohsiung

Mais conteúdo relacionado

Mais procurados

MULTI-LEVEL FEATURE FUSION BASED TRANSFER LEARNING FOR PERSON RE-IDENTIFICATION
MULTI-LEVEL FEATURE FUSION BASED TRANSFER LEARNING FOR PERSON RE-IDENTIFICATIONMULTI-LEVEL FEATURE FUSION BASED TRANSFER LEARNING FOR PERSON RE-IDENTIFICATION
MULTI-LEVEL FEATURE FUSION BASED TRANSFER LEARNING FOR PERSON RE-IDENTIFICATION
gerogepatton
 
Using Mask R CNN to Isolate PV Panels from Background Object in Images
Using Mask R CNN to Isolate PV Panels from Background Object in ImagesUsing Mask R CNN to Isolate PV Panels from Background Object in Images
Using Mask R CNN to Isolate PV Panels from Background Object in Images
ijtsrd
 
Image Classification using Deep Learning
Image Classification using Deep LearningImage Classification using Deep Learning
Image Classification using Deep Learning
ijtsrd
 
CV of gongpu lan 20150712
CV of gongpu lan 20150712CV of gongpu lan 20150712
CV of gongpu lan 20150712
Gongpu Lan
 

Mais procurados (19)

Purkinje imaging for crystalline lens density measurement
Purkinje imaging for crystalline lens density measurementPurkinje imaging for crystalline lens density measurement
Purkinje imaging for crystalline lens density measurement
 
Secure IoT Systems Monitor Framework using Probabilistic Image Encryption
Secure IoT Systems Monitor Framework using Probabilistic Image EncryptionSecure IoT Systems Monitor Framework using Probabilistic Image Encryption
Secure IoT Systems Monitor Framework using Probabilistic Image Encryption
 
MULTI-LEVEL FEATURE FUSION BASED TRANSFER LEARNING FOR PERSON RE-IDENTIFICATION
MULTI-LEVEL FEATURE FUSION BASED TRANSFER LEARNING FOR PERSON RE-IDENTIFICATIONMULTI-LEVEL FEATURE FUSION BASED TRANSFER LEARNING FOR PERSON RE-IDENTIFICATION
MULTI-LEVEL FEATURE FUSION BASED TRANSFER LEARNING FOR PERSON RE-IDENTIFICATION
 
Hyperspectral Retinal Imaging
Hyperspectral Retinal ImagingHyperspectral Retinal Imaging
Hyperspectral Retinal Imaging
 
Practical Considerations in the design of Embedded Ophthalmic Devices
Practical Considerations in the design of Embedded Ophthalmic DevicesPractical Considerations in the design of Embedded Ophthalmic Devices
Practical Considerations in the design of Embedded Ophthalmic Devices
 
Using Mask R CNN to Isolate PV Panels from Background Object in Images
Using Mask R CNN to Isolate PV Panels from Background Object in ImagesUsing Mask R CNN to Isolate PV Panels from Background Object in Images
Using Mask R CNN to Isolate PV Panels from Background Object in Images
 
Advanced Retinal Imaging
Advanced Retinal ImagingAdvanced Retinal Imaging
Advanced Retinal Imaging
 
Machine Learning for Medical Image Analysis: What, where and how?
Machine Learning for Medical Image Analysis:What, where and how?Machine Learning for Medical Image Analysis:What, where and how?
Machine Learning for Medical Image Analysis: What, where and how?
 
Data-driven Ophthalmology
Data-driven OphthalmologyData-driven Ophthalmology
Data-driven Ophthalmology
 
Raai 2019 clinical unmet needs and its solutions of deep learning in medicine3
Raai 2019 clinical unmet needs and its solutions of deep learning in medicine3Raai 2019 clinical unmet needs and its solutions of deep learning in medicine3
Raai 2019 clinical unmet needs and its solutions of deep learning in medicine3
 
인공지능 논문작성과 심사에관한요령
인공지능 논문작성과 심사에관한요령인공지능 논문작성과 심사에관한요령
인공지능 논문작성과 심사에관한요령
 
IFMIA 2019 Plenary Talk : Deep Learning in Medicine; Engineers' Perspectives
IFMIA 2019 Plenary Talk : Deep Learning in Medicine; Engineers' PerspectivesIFMIA 2019 Plenary Talk : Deep Learning in Medicine; Engineers' Perspectives
IFMIA 2019 Plenary Talk : Deep Learning in Medicine; Engineers' Perspectives
 
Ccids 2019 cutting edges of ai technology in medicine
Ccids 2019 cutting edges of ai technology in medicineCcids 2019 cutting edges of ai technology in medicine
Ccids 2019 cutting edges of ai technology in medicine
 
Image Classification using Deep Learning
Image Classification using Deep LearningImage Classification using Deep Learning
Image Classification using Deep Learning
 
Interpretability and informatics of deep learning in medical images3
Interpretability and informatics of deep learning in medical images3Interpretability and informatics of deep learning in medical images3
Interpretability and informatics of deep learning in medical images3
 
Time-resolved biomedical sensing through scattering medium
Time-resolved biomedical sensing through scattering mediumTime-resolved biomedical sensing through scattering medium
Time-resolved biomedical sensing through scattering medium
 
CV of gongpu lan 20150712
CV of gongpu lan 20150712CV of gongpu lan 20150712
CV of gongpu lan 20150712
 
Precision Physiotherapy & Sports Training: Part 1
Precision Physiotherapy & Sports Training: Part 1Precision Physiotherapy & Sports Training: Part 1
Precision Physiotherapy & Sports Training: Part 1
 
76201950
7620195076201950
76201950
 

Semelhante a Stereoscopic Display of Lung PET/CT DICOM Scans using Perspective

7-1 ARTIFICIAL INTELLIGENCE IN PATHOLOGY semiar 2.pptx
7-1 ARTIFICIAL INTELLIGENCE IN PATHOLOGY  semiar 2.pptx7-1 ARTIFICIAL INTELLIGENCE IN PATHOLOGY  semiar 2.pptx
7-1 ARTIFICIAL INTELLIGENCE IN PATHOLOGY semiar 2.pptx
HarishankarSharma27
 
ILT202411111111111111111111111111111.pdf
ILT202411111111111111111111111111111.pdfILT202411111111111111111111111111111.pdf
ILT202411111111111111111111111111111.pdf
w7823125
 
Region-based volumetric medical image retrieval
Region-based volumetric medical image retrievalRegion-based volumetric medical image retrieval
Region-based volumetric medical image retrieval
Institute of Information Systems (HES-SO)
 

Semelhante a Stereoscopic Display of Lung PET/CT DICOM Scans using Perspective (20)

module1.pptx
module1.pptxmodule1.pptx
module1.pptx
 
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting PneumoniaIRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
IRJET- A Survey on Medical Image Interpretation for Predicting Pneumonia
 
AI IN PATH final PPT.pptx
AI IN PATH final PPT.pptxAI IN PATH final PPT.pptx
AI IN PATH final PPT.pptx
 
Perception and Quality of Immersive Media
Perception and Quality of Immersive MediaPerception and Quality of Immersive Media
Perception and Quality of Immersive Media
 
7-1 ARTIFICIAL INTELLIGENCE IN PATHOLOGY semiar 2.pptx
7-1 ARTIFICIAL INTELLIGENCE IN PATHOLOGY  semiar 2.pptx7-1 ARTIFICIAL INTELLIGENCE IN PATHOLOGY  semiar 2.pptx
7-1 ARTIFICIAL INTELLIGENCE IN PATHOLOGY semiar 2.pptx
 
ILT202411111111111111111111111111111.pdf
ILT202411111111111111111111111111111.pdfILT202411111111111111111111111111111.pdf
ILT202411111111111111111111111111111.pdf
 
Deep High Resolution Representation Learning for Human Pose Estimation
Deep High Resolution Representation Learning for Human Pose EstimationDeep High Resolution Representation Learning for Human Pose Estimation
Deep High Resolution Representation Learning for Human Pose Estimation
 
Resume_updated_job
Resume_updated_jobResume_updated_job
Resume_updated_job
 
Recent advances in diagnosis and treatment planning1 /certified fixed orthod...
Recent advances in diagnosis and treatment  planning1 /certified fixed orthod...Recent advances in diagnosis and treatment  planning1 /certified fixed orthod...
Recent advances in diagnosis and treatment planning1 /certified fixed orthod...
 
Supercharging MD Simulations with GPUs
Supercharging MD Simulations with GPUsSupercharging MD Simulations with GPUs
Supercharging MD Simulations with GPUs
 
Recent advances in diagnosis and treatment planning1 /certified fixed orthod...
Recent advances in diagnosis and treatment  planning1 /certified fixed orthod...Recent advances in diagnosis and treatment  planning1 /certified fixed orthod...
Recent advances in diagnosis and treatment planning1 /certified fixed orthod...
 
Development of industrial ct system for 2 d 3d tomographic images of concrete...
Development of industrial ct system for 2 d 3d tomographic images of concrete...Development of industrial ct system for 2 d 3d tomographic images of concrete...
Development of industrial ct system for 2 d 3d tomographic images of concrete...
 
Dental digital radiography
Dental digital radiographyDental digital radiography
Dental digital radiography
 
Region-based volumetric medical image retrieval
Region-based volumetric medical image retrievalRegion-based volumetric medical image retrieval
Region-based volumetric medical image retrieval
 
Digital imaging
Digital imagingDigital imaging
Digital imaging
 
Yagaanddatascience
YagaanddatascienceYagaanddatascience
Yagaanddatascience
 
A vision-based uncut crop edge detection method for automated guidance of hea...
A vision-based uncut crop edge detection method for automated guidance of hea...A vision-based uncut crop edge detection method for automated guidance of hea...
A vision-based uncut crop edge detection method for automated guidance of hea...
 
Attentive-YOLO: On-Site Water Pipeline Inspection Using Efficient Channel Att...
Attentive-YOLO: On-Site Water Pipeline Inspection Using Efficient Channel Att...Attentive-YOLO: On-Site Water Pipeline Inspection Using Efficient Channel Att...
Attentive-YOLO: On-Site Water Pipeline Inspection Using Efficient Channel Att...
 
Detection of Macular Edema by using Various Techniques of Feature Extraction ...
Detection of Macular Edema by using Various Techniques of Feature Extraction ...Detection of Macular Edema by using Various Techniques of Feature Extraction ...
Detection of Macular Edema by using Various Techniques of Feature Extraction ...
 
Digital cephalometry
Digital cephalometryDigital cephalometry
Digital cephalometry
 

Último

The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
heathfieldcps1
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
ciinovamais
 

Último (20)

Interactive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communicationInteractive Powerpoint_How to Master effective communication
Interactive Powerpoint_How to Master effective communication
 
Paris 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activityParis 2024 Olympic Geographies - an activity
Paris 2024 Olympic Geographies - an activity
 
Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)Software Engineering Methodologies (overview)
Software Engineering Methodologies (overview)
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111Call Girls in Dwarka Mor Delhi Contact Us 9654467111
Call Girls in Dwarka Mor Delhi Contact Us 9654467111
 
Z Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot GraphZ Score,T Score, Percential Rank and Box Plot Graph
Z Score,T Score, Percential Rank and Box Plot Graph
 
A Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy ReformA Critique of the Proposed National Education Policy Reform
A Critique of the Proposed National Education Policy Reform
 
9548086042 for call girls in Indira Nagar with room service
9548086042  for call girls in Indira Nagar  with room service9548086042  for call girls in Indira Nagar  with room service
9548086042 for call girls in Indira Nagar with room service
 
Student login on Anyboli platform.helpin
Student login on Anyboli platform.helpinStudent login on Anyboli platform.helpin
Student login on Anyboli platform.helpin
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Advance Mobile Application Development class 07
Advance Mobile Application Development class 07Advance Mobile Application Development class 07
Advance Mobile Application Development class 07
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
fourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writingfourth grading exam for kindergarten in writing
fourth grading exam for kindergarten in writing
 
The basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptxThe basics of sentences session 2pptx copy.pptx
The basics of sentences session 2pptx copy.pptx
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..Sports & Fitness Value Added Course FY..
Sports & Fitness Value Added Course FY..
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
Grant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy ConsultingGrant Readiness 101 TechSoup and Remy Consulting
Grant Readiness 101 TechSoup and Remy Consulting
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 

Stereoscopic Display of Lung PET/CT DICOM Scans using Perspective

  • 1. Stereoscopic Display of Lung PET/ CT DICOM Scans using Perspective 使用透視法於肺部 PET/CT DICOM 影像之三維立體顯示 Student:Yueh-Ju Chen Advisor: Dr. Tang-Kai Yin Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 2. Introduction • Motivation • Related Works • Proposed Approach • DICOM Analysis • Stereoscopic • Result • Conclusion and Future Work Institute of Computer Science and Information Engineering 2 National University of Kaohsiung
  • 3. Introduction Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 4. Background • Computed tomography: • A medical imaging procedure • Utilizing computer-processed X-rays to produce tomographic images or 'slices' of specific areas of the body • Stereoscopy: • The illusion 3D depth from images on a 2D plane Institute of Computer Science and Information Engineering 4 National University of Kaohsiung
  • 5. Motivation • 3D effect get popular • Not a new technology • Medical diagnosis: • Improve the efficiency of diagnosis • Surgical simulation • Education training Institute of Computer Science and Information Engineering 5 National University of Kaohsiung
  • 6. Algorithm Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 7. Related Works Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 8. Medical Scans • DICOM file: • File format • DICOM Standards Committee • Widely used by hospitals • Dividing into two parts: • Image • Header (metadata) files Institute of Computer Science and Information Engineering 8 National University of Kaohsiung
  • 9. Maximum Intensity Projection (MIP) • Volume rendering method • Voxels with maximum intensity • Orthographic projection • Cannot distinguish between left or right, front or back • Detection of lung nodules Institute of Computer Science and Information Engineering 9 National University of Kaohsiung
  • 10. Standardized Uptake Value (SUV) • Distinguish between malignant lesions and benign tumor • Enhances the 3D nature of nodules • Pulmonary bronchi and vasculature • Cut-off value for malignant lesion is 2.5 Institute of Computer Science and Information Engineering 10 National University of Kaohsiung
  • 11. Stereoscopic • Illusion of 3D depth from images on a 2D plane • 3D viewer technology: • Anaglyph • Active shutter systems • Polarization systems Institute of Computer Science and Information Engineering 11 National University of Kaohsiung
  • 12. NVIDIA 3D Vision • Shutter glasses and driver software • Direct3D software • Mainstream consumers and PC gamers • Requirement: • 120 Hz LCD or CRT monitors, DLP-projectors • NVIDIA graphics card Institute of Computer Science and Information Engineering 12 National University of Kaohsiung
  • 13. Proposed Approach Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 14. DICOM Analysis Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 15. Calculation of SUV • Referred to as the dose uptake ratio • Main calculate source: PET DICOM • The related attributed tags: • Rescale Slope tag • Rescale Intercept tag Institute of Computer Science and Information Engineering 15 National University of Kaohsiung
  • 16. Step 1: Convert Pixel Value to Activity Concentration • Rescale Slope tag are vary for every image slice Institute of Computer Science and Information Engineering 16 National University of Kaohsiung
  • 17. Step 2: Decay Calibration Factor Institute of Computer Science and Information Engineering 17 National University of Kaohsiung
  • 18. Step 3: Calculate SUV Institute of Computer Science and Information Engineering 18 National University of Kaohsiung
  • 19. SUV Number 147 and 195 slice (a)original PET (b)SUV (c) threshold with 2.5 Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 20. Non-body Pixels Non-body Original CT pixels removed Institute of Computer Science and Information Engineering 20 National University of Kaohsiung
  • 21. Body Mask Institute of Computer Science and Information Engineering 21 National University of Kaohsiung
  • 22. Body Mask (cont.) Institute of Computer Science and Information Engineering 22 National University of Kaohsiung
  • 23. Stereoscopic Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 24. Real 3D vs. Fake 3D • Fake 3D • Converting 2D films into 3D • Depth map • Real 3D • Two views • Two different cameras (or projections) Institute of Computer Science and Information Engineering 24 National University of Kaohsiung
  • 25. Stereoscopic Principle • D: distance between the viewpoint and the screen • R: distance of stereo pair of images on the screen • S: distance between the perceived object and the screen Institute of Computer Science and Information Engineering 25 National University of Kaohsiung
  • 26. Optical Angle • Best viewing range: 70~500cm • Distance between the two eyes: 6.5~7cm • Institute of Computer Science and Information Engineering 26 National University of Kaohsiung
  • 27. Eye Separation • The most suitable for the 3D effect: • Distance: 140~210 cm • Optical angle: 2.86~1.91 degree Institute of Computer Science and Information Engineering 27 National University of Kaohsiung
  • 28. Perspective Institute of Computer Science and Information Engineering 28 National University of Kaohsiung
  • 29. Perspective Institute of Computer Science and Information Engineering 29 National University of Kaohsiung
  • 30. Perspective Institute of Computer Science and Information Engineering 30 National University of Kaohsiung
  • 31. Perspective Institute of Computer Science and Information Engineering 31 National University of Kaohsiung
  • 32. Parallax Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 33. Positive and Zero Parallax • Positive Parallax • Cross point of each eye sight with the screen • Behind the screen • Zero Parallax • Overlap on the screen • No 3D effect Institute of Computer Science and Information Engineering 33 National University of Kaohsiung
  • 34. Negative Parallax • Focus heating-point in front of the screen • Out of screen • The closer the screen is the smaller depth of field will be generated Institute of Computer Science and Information Engineering 34 National University of Kaohsiung
  • 35. Parallax Adjustment Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 36. Result Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 37. NVIDIA 3D Vision 1. OpenGL QuadBuffer 2. NVAPI 3. 3D Video Institute of Computer Science and Information Engineering 37 National University of Kaohsiung
  • 38. Experiment Environment ASUS G53J Platform: Win7 64bit CPU: Intel i7-7400QM @1.73GHz RAM: 8GM Graphic Card: NVIDIA GTX 460M 1.5G Institute of Computer Science and Information Engineering 38 National University of Kaohsiung
  • 39. MIP 0 degree of MIP 100 degree of MIP Institute of Computer Science and Information Engineering 39 National University of Kaohsiung
  • 40. MIP 240 degree of MIP 280 degree of MIP Institute of Computer Science and Information Engineering 40 National University of Kaohsiung
  • 41. Perspective of Mean Volume Rendering 0 degree of Perspective of Mean Volume Rendering 100 degree of Perspective of Mean Volume Rendering Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 42. Perspective of Mean Volume Rendering 240 degree of Perspective of Mean Volume Rendering 280 degree of Perspective of Mean Volume Rendering Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 43. Perspective with Bilinear Interpolation 0 degree of Perspective with Bilinear Interpolation 100 degree of Perspective with Bilinear Interpolation Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 44. Perspective with Bilinear Interpolation 240 degree of Perspective with Bilinear Interpolation 280 degree of Perspective with Bilinear Interpolation Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 45. Conclusion & Future Work Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 46. Conclusion • The stereoscopic image created by a perspective projection and applied with SUV calculation of PET scans in 3D shutter system. • Expending vision from 2D to 3D and the biggest difference between them is the depth information. • 2D images cannot distinguish three points which is in the front or which is in the back, but after we applied the stereoscopic techniques it is more obvious and clear to distinguish points’ relation and distance between them Institute of Computer Science and Information Engineering 46 National University of Kaohsiung
  • 47. Future Work • A medical analyze system with stereoscopic display • More medical analyze functions • Real time volume rendering • Auto-stereoscopic Institute of Computer Science and Information Engineering 47 National University of Kaohsiung
  • 48. Demo Institute of Computer Science and Information Engineering National University of Kaohsiung
  • 49. Q &A Institute of Computer Science and Information Engineering National University of Kaohsiung