Presentation on theme: "Analysis of Dental Images using Artificial Immune Systems Zhou Ji 1, Dipankar Dasgupta 1, Zhiling Yang 2 & Hongmei Teng 1 1: The University of Memphis."— Presentation transcript:
Analysis of Dental Images using Artificial Immune Systems Zhou Ji 1, Dipankar Dasgupta 1, Zhiling Yang 2 & Hongmei Teng 1 1: The University of Memphis 2: Yinchuan Stomatological Hospital, China CEC 2006. Vancouver, BC, Canada. July 17, 2006.
outline Application background AIS method Data preprocessing Preliminary results
Application background Occlusion: alignment of teeth/jaw Malocclusion Abnormal occlusion Diagnosis using X-ray
malocclusion Different types: I (normal bite), II (overbite), and III (underbite) Mild or severe (functional)
lateral view skull X-ray Normal case Example of malocclusion
conventional diagnosis method Angles classification: angle ANB (3 in the picture) N A B
AIS method Negative selection algorithms A detector set is generated from normal samples and used to detect abnormal cases. One-class classification: classification between two classes using samples from one class to train the system anomaly detection
V-detector A new negative selection algorithm Maximized detection size of detectors Coverage estimate
Data preprocessing method -feature extraction Using brightness distribution instead of traditional feature extraction (identification of entities or anatomical parts) Binarization at multiple thresholds Description of each binary image with four real numbers
choose thresholds T 0 = V max, T 1 = V max (V max V min )/n,..., T n-1 = V max (n 1)(V max Vmin )/n, Thresholds are decided by the actual values of the image.
decide reference point Binarized at the highest threshold
extract four features at each threshold (or for each binary image) 1. Horizontal displacement x = x white x 0, (x white is the mean of x of white pixels) 1. Vertical displacement y = y white y 0, (y white is the mean of y of white pixels) 1. Displacement distance r = mean of distances between white pixels to (x 0, y 0 ) 1. Area mass A = total number of white pixel/width · height
Steps to represent an image as a real-valued vector A grayscale image n binary images Each binary image 4 real values 1. Clean up 2. Binarization 3. Calculate 4 features 4. Normalization Result: a grayscale image is represented by a 4n- dimensional vector over [0,1] 4n
Using half of normal data to train SVM result V-detector result
Summary V-detector shows some potentials. A novel feature extraction is proposed. Key idea: general shapes instead of anatomical part Issues: Other possible feature representations more normal data are desired.