1 / 39

Medical Imaging & Visualization

Medical Imaging & Visualization. A Presentation by Shruti Vangari Under the guidance of Dr. Xiao. Outline of this project. Aim : To help doctors diagnose cancer faster Data used : Collection of brain samples of patients detected with cancer

kaz
Download Presentation

Medical Imaging & Visualization

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Medical Imaging & Visualization A Presentation byShruti VangariUnder the guidance ofDr. Xiao

  2. Outline of this project • Aim: To help doctors diagnose cancer faster • Data used : Collection of brain samples of patients detected with cancer • Idea : Filtering of edges of these medical images can help fasten the process of detecting tumor • Algorithm: Canny Edge Detection

  3. Terminology • Medical Imaging: • Process to create images of the human body for clinical purposes • Visualization: • Representing information as Computer Graphics • VTK(Visualization toolkit) and ITK(Insight Segmentation and Registration Toolkit) : • Computer graphics, image processing & visualization

  4. Medical Terminology • Nuclear Medicine (NM): • Application of radioactive elements – radiopharmaceuticals in the diagnosis and treatment of disease • Medical Resonance Imaging (MR): • Medical technique used in radiology to visualize internal structures of the body

  5. Medical Topology

  6. Steps followed – Step 1 • Step 1 – Collect Samples • MR and NM samples of the following time periods: • Baseline • Baseline + 2 months • Baseline + 4 months • Baseline + 7 months • Baseline + 10 months • Baseline + 12 months • Baseline + 15 months • Baseline + 17 months • Baseline + 21 months • Baseline + 25 months

  7. Steps followed – Step 2 • Step 2 – Setup the system and software • Download Cmake • Download VTK • Download VTK data • Download ITK Insight Applications • Download ITK Insight Toolkit • Build all the software as per the steps • Write a sample program to build the binaries

  8. Steps Followed – Step 3 • Step 3 - Canny Edge detection Algorithm • Gaussian filter – to smoothen image & reduce noise • Gradient Magnitudes – Gradient vector of an image • Non-Max suppression – Sets to 0 if pixel is not a peak • Canny Output Edges – Got after thresholding and linking the edges

  9. Steps followed – Step 4 Step 4 – Canny Edge Detection in VTK "vtkSmartPointer.h" "vtkDICOMImageReader.h" "vtkImageGaussianSmooth.h" "vtkImageActor.h" "vtkRenderer.h" "vtkRenderWindow.h" "vtkRenderWindowInteractor.h" "vtkImageGradient.h" "vtkImageMagnitude.h" vtkImageNonMaximumSuppression.h" "vtkImageConstantPad.h" "vtkImageToStructuredPoints.h" "vtkLinkEdgels.h" "vtkThreshold.h" "vtkGeometryFilter.h" "vtkSubPixelPositionEdgels.h" "vtkStripper.h" "vtkPolyDataMapper.h" "vtkJPEGReader.h" "vtkTextProperty.h" "vtkTextActor.h"

  10. Input Data Used MR Data Saggital Axial Coronal

  11. Canny Edge Detection - Output Gaussian Smoothed Canny Edges Gradient Magnitudes Non-Max Suppression

  12. Results - Final Output

  13. Other image filtering - NM NM Data Input NM Data Canny Edges

  14. Comparison of the outputs • The outputs were compared from the baseline period till baseline + 25 months • The results showed a dramatic improvement – base on the medication

  15. Baseline – when the cancer was detected

  16. Baseline + 2 months

  17. Baseline + 4 months

  18. Baseline + 7 months

  19. Baseline + 10 months

  20. Baseline + 12 months

  21. Baseline + 15 months

  22. Baseline + 17 months

  23. Baseline + 21 months

  24. Baseline + 25 months

  25. ITK Output - Baseline

  26. ITK Output - Baseline + 2 months

  27. ITK Output - Baseline + 4 months

  28. ITK Output - Baseline + 7 months

  29. ITK Output - Baseline + 10 months

  30. ITK Output - Baseline + 12 months

  31. ITK Output - Baseline + 15 months

  32. ITK Output - Baseline + 17 months

  33. ITK Output - Baseline + 21 months

  34. ITK Output - Baseline + 25 months

  35. Conclusion • The Canny Edge Detection algorithm uses a multi-stage algorithm to detect edges in images. • It finds “optimal” edges implying • Good Detection • Good Localization • Minimal Response • Hence, one gets accurate results. The same was proved in his paper as well – cited in the references

  36. Future Work • Use the concept of FUSION – MR + NM • Detect edges for the fused image – faster and more accurate results • To find edges for all the data collected : Baseline to Baseline + 25 months.

  37. References • Visualization slides prepared by Dr. Xiao http://cs.uakron.edu/~xiao/ • Wikipedia, the free encyclopedia http://www.wikipedia.org/ • VTK Kitwarehttp://www.vtk.org/ • ITK Kitwarehttp://www.itk.org/ • CmakeKitwarehttp://www.cmake.org/ • Cancer data samples collected from https://public.cancerimagingarchive.net/ncia/home.jsf

  38. References (2) • Canny Edge Detection http://www.cse.iitd.ernet.in/~pkalra/csl783/canny.pdf • Image Processing Algorithms • J Canny. 1986. A Computational Approach to Edge Detection. IEEE Trans. Pattern Anal. Mach. Intell. 8, 6 (June 1986), 679-698. DOI=10.1109/TPAMI.1986.4767851 http://dx.doi.org/10.1109/TPAMI.1986.4767851

  39. Thank You

More Related