associate professor
play

Associate Professor Faculty of Engineering Multimedia University - PowerPoint PPT Presentation

Mohammad Faizal Ahmad Fauzi, Ph.D. Associate Professor Faculty of Engineering Multimedia University Imaging Informatics Imaging basics Imaging modalities PACS and its core functions DICOM 20 mm Nodule 4 mm Nodule 5 mm


  1. Mohammad Faizal Ahmad Fauzi, Ph.D. Associate Professor Faculty of Engineering Multimedia University

  2.  Imaging Informatics  Imaging basics  Imaging modalities  PACS and its core functions  DICOM

  3. 20 mm Nodule

  4. 4 mm Nodule

  5. 5 mm Nodule

  6. Reader 1 Reader 1

  7. Reader 2 Reader 2

  8. Reader 3 Reader 3

  9.  Fatigue  Distraction  Emotional stress  Variation in reader  Satisfaction of Search

  10.  Breast cancer is missed 10-30% …  by Expert Mammographers

  11.  Sensitivity of radiologists in detecting breast cancer on mammograms can be improved by 15% through double reading .

  12.  Computer-aided diagnosis: ◦ a diagnosis made by a physician using the output of a computerized system  Computerized system ◦ Automated image (or data) analysis

  13.  Breast Cancer  Lung Cancer  Brain Cancer  Colon Cancer

  14. Find Six Differences

  15. Find Six Differences

  16. • Solitary Pulmonary Nodules • Microcalcifications • Ground Glass Opacities • Masses

  17. Malignant Benign

  18. HR 2 (7/23/01) 5 10 15 20 25 30 35 40 5 10 15 20 25 30 35 40

  19. 1 2 3 4 5 6 7 8 9 10 11 12

  20. 10 20 30 40 50 60 10 20 30 40 50

  21.  Organ segmentation  Candidate detection/segmentation  Feature Extraction  Classification/clustering

  22.  Organ segmentation  Candidate detection/segmentation  Feature Extraction  Classification/clustering

  23.  Segment Lung Regions within the CT slice  Detect left and right lungs

  24.  Segmented lung region may exclude some nodules adjacent to pleura  Connect edge points of concave regions  Recover potential nodules adjacent to pleura

  25. d 2 d 1 P 1 d e P 2

  26.  Organ segmentation  Candidate detection/segmentation  Feature Extraction  Classification/clustering

  27. Mammogram Image Pre-screening Potential Signals CNN Classifier Potential TP Signals Clustering Microcalcification Clusters

  28. Mammogram Image Pre-screening Potential Signals CNN Classifier Potential TP Signals Clustering Microcalcification Clusters

  29.  Identify high density regions within segmented lung regions  Segmentation by k-means clustering with two classes: ◦ nodule candidates ◦ lung region

  30. Identification of Blood Vessels Thin long structure V-shaped True structure nodule

  31.  Organ segmentation  Candidate detection/segmentation  Feature Extraction  Classification/clustering

  32.  Thin long structures ◦ Major-to-minor axis ratio of a fitted ellipse  V-shaped structures ◦ Rectangularity

  33.  Thin long structures a R tl  b a b  V-shaped structures Area of rectangle  R v Area of object

  34.  Organ segmentation  Candidate detection/segmentation  Feature Extraction  Classification/clustering

  35. FP ROI TP ROI

  36. Mammogram Image Pre-screening Potential Signals CNN Classifier Potential TP Signals Clustering Microcalcification Clusters

  37. { 0: FP CNN Classifier 1: TP INPUT ROI

  38. Mammogram Image Pre-screening Potential Signals CNN Classifier Potential TP Signals Clustering Microcalcification Clusters

  39.  Image ◦ How to represent ◦ How to generate it  Imaging modalities ◦ How to integrate ◦ How to manage  Image Analysis ◦ Radiology ◦ Big picture

Recommend


More recommend