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 Nodule
Reader 1 Reader 1
Reader 2 Reader 2
Reader 3 Reader 3
Fatigue Distraction Emotional stress Variation in reader Satisfaction of Search
Breast cancer is missed 10-30% … by Expert Mammographers
Sensitivity of radiologists in detecting breast cancer on mammograms can be improved by 15% through double reading .
Computer-aided diagnosis: ◦ a diagnosis made by a physician using the output of a computerized system Computerized system ◦ Automated image (or data) analysis
Breast Cancer Lung Cancer Brain Cancer Colon Cancer
Find Six Differences
Find Six Differences
• Solitary Pulmonary Nodules • Microcalcifications • Ground Glass Opacities • Masses
Malignant Benign
HR 2 (7/23/01) 5 10 15 20 25 30 35 40 5 10 15 20 25 30 35 40
1 2 3 4 5 6 7 8 9 10 11 12
10 20 30 40 50 60 10 20 30 40 50
Organ segmentation Candidate detection/segmentation Feature Extraction Classification/clustering
Organ segmentation Candidate detection/segmentation Feature Extraction Classification/clustering
Segment Lung Regions within the CT slice Detect left and right lungs
Segmented lung region may exclude some nodules adjacent to pleura Connect edge points of concave regions Recover potential nodules adjacent to pleura
d 2 d 1 P 1 d e P 2
Organ segmentation Candidate detection/segmentation Feature Extraction Classification/clustering
Mammogram Image Pre-screening Potential Signals CNN Classifier Potential TP Signals Clustering Microcalcification Clusters
Mammogram Image Pre-screening Potential Signals CNN Classifier Potential TP Signals Clustering Microcalcification Clusters
Identify high density regions within segmented lung regions Segmentation by k-means clustering with two classes: ◦ nodule candidates ◦ lung region
Identification of Blood Vessels Thin long structure V-shaped True structure nodule
Organ segmentation Candidate detection/segmentation Feature Extraction Classification/clustering
Thin long structures ◦ Major-to-minor axis ratio of a fitted ellipse V-shaped structures ◦ Rectangularity
Thin long structures a R tl b a b V-shaped structures Area of rectangle R v Area of object
Organ segmentation Candidate detection/segmentation Feature Extraction Classification/clustering
FP ROI TP ROI
Mammogram Image Pre-screening Potential Signals CNN Classifier Potential TP Signals Clustering Microcalcification Clusters
{ 0: FP CNN Classifier 1: TP INPUT ROI
Mammogram Image Pre-screening Potential Signals CNN Classifier Potential TP Signals Clustering Microcalcification Clusters
Image ◦ How to represent ◦ How to generate it Imaging modalities ◦ How to integrate ◦ How to manage Image Analysis ◦ Radiology ◦ Big picture
Recommend
More recommend