Modeling and Prediction of Abdominal Tumor Motion Haobing Wang Department of Computer Science May 9 th, 2003.

Slides:



Advertisements
Similar presentations
Pattern Recognition and Machine Learning
Advertisements

DETC ASME Computers and Information in Engineering Conference ONE AND TWO DIMENSIONAL DATA ANALYSIS USING BEZIER FUNCTIONS P.Venkataraman Rochester.
Problems 2.1, 2.2 and 2.3 pages How Fitting! – The Least Squares Line and How Fitting! – The Least Squares Exponential Fitting Models to Data.
Polynomial Curve Fitting BITS C464/BITS F464 Navneet Goyal Department of Computer Science, BITS-Pilani, Pilani Campus, India.
Copyright © 2006 The McGraw-Hill Companies, Inc. Permission required for reproduction or display. 1 ~ Curve Fitting ~ Least Squares Regression Chapter.
March 1, 2009Dr. Muhammed Al-Mulhem1 ICS 415 Computer Graphics Hermite Splines Dr. Muhammed Al-Mulhem March 1, 2009 Dr. Muhammed Al-Mulhem March 1, 2009.
Pattern Recognition and Machine Learning
Data Modeling and Parameter Estimation Nov 9, 2005 PSCI 702.
Toward Automatic Music Audio Summary Generation from Signal Analysis Seminar „Communications Engineering“ 11. December 2007 Patricia Signé.
Regression Analysis Module 3. Regression Regression is the attempt to explain the variation in a dependent variable using the variation in independent.
 Coefficient of Determination Section 4.3 Alan Craig
Silhouette Lookup for Automatic Pose Tracking N ICK H OWE.
Basis Expansion and Regularization Presenter: Hongliang Fei Brian Quanz Brian Quanz Date: July 03, 2008.
Shape and Dynamics in Human Movement Analysis Ashok Veeraraghavan.
HMM-BASED PATTERN DETECTION. Outline  Markov Process  Hidden Markov Models Elements Basic Problems Evaluation Optimization Training Implementation 2-D.
Video Coding with Linear Compensation (VCLC) Arif Mahmood, Zartash Afzal Uzmi, Sohaib A Khan Department of Computer.
Least Square Regression
Optical Flow Methods 2007/8/9.
Curve-Fitting Regression
ECIV 301 Programming & Graphics Numerical Methods for Engineers Lecture 26 Regression Analysis-Chapter 17.
Real-time tumor tracking with preprogrammed dynamic MLC motion and adaptive dose-rate regulation B.Y Yi, S. Han-Oh, F. Lerma, B. Berman, C. Yu.
Least Square Regression
ECIV 301 Programming & Graphics Numerical Methods for Engineers Lecture 25 Regression Analysis-Chapter 17.
The Islamic University of Gaza Faculty of Engineering Civil Engineering Department Numerical Analysis ECIV 3306 Chapter 17 Least Square Regression.
Topics: Regression Simple Linear Regression: one dependent variable and one independent variable Multiple Regression: one dependent variable and two or.
Copyright © 2006 The McGraw-Hill Companies, Inc. Permission required for reproduction or display. by Lale Yurttas, Texas A&M University Chapter 171 CURVE.
Energy-efficient Self-adapting Online Linear Forecasting for Wireless Sensor Network Applications Jai-Jin Lim and Kang G. Shin Real-Time Computing Laboratory,
Regression Analysis Regression analysis is a statistical technique that is very useful for exploring the relationships between two or more variables (one.
PATTERN RECOGNITION AND MACHINE LEARNING
Copyright © The McGraw-Hill Companies, Inc. Permission required for reproduction or display. 1 Part 4 Curve Fitting.
Managerial Economics Demand Estimation. Scatter Diagram Regression Analysis.
Linear Regression James H. Steiger. Regression – The General Setup You have a set of data on two variables, X and Y, represented in a scatter plot. You.
© 2008 Pearson Addison-Wesley. All rights reserved Chapter 1 Section 13-6 Regression and Correlation.
Regression Maarten Buis Outline Recap Estimation Goodness of Fit Goodness of Fit versus Effect Size transformation of variables and effect.
Linear Regression Least Squares Method: the Meaning of r 2.
Chapter 8 Curve Fitting.
PATTERN RECOGNITION AND MACHINE LEARNING CHAPTER 3: LINEAR MODELS FOR REGRESSION.
Curve-Fitting Regression
Lesson 5.1 Forecasting Moving Averages Exponential Smoothing.
Approximation on Finite Elements Bruce A. Finlayson Rehnberg Professor of Chemical Engineering.
Lecture 16 - Approximation Methods CVEN 302 July 15, 2002.
Radiation Detection and Measurement, JU, 1st Semester, (Saed Dababneh). 1 Radioactive decay is a random process. Fluctuations. Characterization.
1 Data Analysis Linear Regression Data Analysis Linear Regression Ernesto A. Diaz Department of Mathematics Redwood High School.
AAM based Face Tracking with Temporal Matching and Face Segmentation Mingcai Zhou 1 、 Lin Liang 2 、 Jian Sun 2 、 Yangsheng Wang 1 1 Institute of Automation.
Linear Prediction Correlation can be used to make predictions – Values on X can be used to predict values on Y – Stronger relationships between X and Y.
 Present by 陳群元.  Introduction  Previous work  Predicting motion patterns  Spatio-temporal transition distribution  Discerning pedestrians  Experimental.
Curve Fitting Pertemuan 10 Matakuliah: S0262-Analisis Numerik Tahun: 2010.
Principles of Extrapolation
Lecture 17 - Approximation Methods CVEN 302 July 17, 2002.
Copyright © 2006 The McGraw-Hill Companies, Inc. Permission required for reproduction or display. 1 ~ Curve Fitting ~ Least Squares Regression.
CSE 5331/7331 F'07© Prentice Hall1 CSE 5331/7331 Fall 2007 Regression Margaret H. Dunham Department of Computer Science and Engineering Southern Methodist.
Rigid Needles, Steerable Needles, and Optimal Beam Algorithms Ovidiu Daescu Bio-Medical Computing Laboratory Department of Computer Science University.
Martin J Murphy PhD Department of Radiation Oncology
Department of Mathematics
Part 5 - Chapter
Part 5 - Chapter 17.
CSE 4705 Artificial Intelligence
Particle Filtering for Geometric Active Contours
Special Topics In Scientific Computing
Chapter 12 Curve Fitting : Fitting a Straight Line Gab-Byung Chae
Part 5 - Chapter 17.
MATH 2140 Numerical Methods
Warm Up If there are 2000 students total in the school, what percentage of the students are in each region?
The Science of Predicting Outcome
Least Squares Method: the Meaning of r2
Contact: Machine Learning – (Linear) Regression Wilson Mckerrow (Fenyo lab postdoc) Contact:
Least-Squares Regression
Least Square Regression
Regression and Correlation of Data
CISE-301: Numerical Methods Topic 1: Introduction to Numerical Methods and Taylor Series Lectures 1-4: KFUPM CISE301_Topic1.
Presentation transcript:

Modeling and Prediction of Abdominal Tumor Motion Haobing Wang Department of Computer Science May 9 th, 2003

Project Outline Topic and Goal Background and Motivation Methods Experiments Analysis Future Work

Topic and Goal Facilitate real-time tracking of the tumor motion during radiotherapy and allow for for precise delivery of radiation dose to mobile tumors. Find methods to model and predict abdominal tumor motion.

Background and Motivation Tumor position is modeled by tracking surgically implanted clips surrounding the tumor. The radiation beam has mechanical latency.

Template Matching Using DHMM DHMM: Deformable Hidden Markov Model Given a pattern template, recognizing the pattern in a new time series, allowing flexible deformation of time.

Template Matching Using DHMM Generalize the standard constant model and allow each state to generate data in the form of a regression curve. K-state segmental HMM each state of which corresponds to one segment in the piecewise linear representation of the template.

Template Matching Using DHMM Use a sinusoid as template The DHMM automatically find the period whose shape is similar to a sinusoid. Then the sequence is found is used as the prediction of the next breathing period.

Experiments of DHMM Method

Prediction of 100 frames

Analysis of DHMM Method Average error and error variance is greater than 1 millimeter. Although the computation time for each clip is around 5 minutes, it’s still cannot be done on-line.

Prediction by Curve Fitting A least square method to fit the data points to a third order polynomial function: f(x) = b 0 + b 1 x + b 2 x 2 + b 3 x 3. The set of coefficients [b n ] can be found by minimizing the sum:

Examples of Curve Fitting

Prediction by Curve Fitting Suppose S is the shape function which describes the trajectory of a single breathing period, and  (t) is a weighing function. I use  as a decay factor. So S(t) can be computed by: S k = f(t) + (1-  t  S k-1

Experiments of Curve Fitting Bob (clip 2)

Experiments of Curve Fitting Gary (clip 0)

Experiments of Curve Fitting Results of predicting approximately 550 frames on average

Experiments of Curve Fitting Results of predicting 100 frames

Comparison of Four Methods Predicting 100 frames

Analysis of Curve Fitting Gives better result. Average error is the best among the four methods, and error variation is the second to the best. Computation is fast. Can be done on-line.

Future Work Adjustment of duration of each breathing period. Improvement of the performance of the clip tracker and patients’ breathing pattern.

Future Work