Ph.D. Course: Topics in Biomedical Imaging

Responsible person for the course: Tulay Adali, Assoc. Prof., e-mail: adali@eivind.imm.dtu.dk

Course description: The objective of the course is to introduce the students two active areas of research in biomedical imaging: stochastic model based image analysis and its applications and medical image databases.

Course content: The course will provide a complete treatment of the biomedical image analysis problem in terms of imaging physics, statistical models for the pixel and context images and their justification, and segmentation of images, as well as study of key applications of image analysis, such as registration. Particular emphasis will be on magnetic resonance images but other modalities such as computed radiography and computed tomography will be discussed as well. Last part of the course will focus on design, management, and access technologies for medical image databases.

Prerequisites for the course: Random processes and statistical modeling/parameter estimation.

Institution: Technical University of Denmark

Danish name of institution: Danmarks Tekniske Universitet

Official abbreviation: DTU

Department: Department of Mathematical Modelling (IMM)

Dates: 22 to 26 May, 2000

Course arrangement: Lectures in the morning (9:00am-12:00pm), computer exercise/project in the afternoon (13:00pm-17:00pm)

Teaching arrangement: Lectures, exercises, and a project on biomedical image analysis

Language: English

Place: Lectures (9:00am-12:00pm): Building 305, Room 205 (22/5-25/5) and Building 321, Room 33 (26/5);
Computer Exercise/Project (13:00pm-17:00pm): Building 302, Room 43;
Technical University of Denmark, 2800 Lyngby

Number of participation hours: 35 hours

Number of actual working hours: Around 50 hours

Estimated part of obligatory 1/2 year courses: 10 % or 3 ECTS Points.

The course is part of the following Ph.D. program: Electrical Engineering

Course fee: Ph.D. students and Master students from DTU: None. Danish and foreign guest students: None. For students not attached to any University kr. 3.000,-

Registration: By e-mail to adali@eivind.imm.dtu.dk

Participant's obligation during the course: Attending the lectures, participation in the course, and a final project report.

For further information about the course: Please send e-mail to adali@eivind.imm.dtu.dk.

REFERENCES:

Main References:

Y. Wang and T. Adali, Stochastic Model Based Image Analysis, to appear in Signal Processing for Magnetic Resonance Imaging and Spectroscopy, (Chapter 14), Marcel Dekker, 2000. (Figures)
(and the postscript version and postscript version of figures ) )

T. K. Moon, ``The Expectation-Maximization Algorithm'', IEEE Signal Processing magazine, Nov, 1996, pp. 47-60.

Moriel NessAiver, Basic Nuclear Magnetic Resonance, Chapter 2, from ``All you really need to know about MRI physics''.

Y. Wang, T. Adali, S.-Y. Kung, and Z. Szabo, ``Quantification and segmentation of brain tissue from MR images: A probabilistic neural network approach,'' IEEE Trans. Image Processing, Special Issue on Applications of Neural Networks to Image Processing, vol. 7, no. 8, pp. 1165-1181, Aug. 1998.
(postscript version and postscript version of figures.)

Other References: (in case you need to refresh some of the basics and/or want additional reading material on the topics discussed in the class)

J. L. Marroquin and F. Girosi, ``Some extensions of the K-means algorithm for image segmentation and pattern classification,'' MIT Tech. Report, Jan. 1993. Processes,

R.C. Dubes et al., MRF Model Based Algorithms for Image Segmentation'', Proceedings. 10th International Conference on Pattern Recognition, 1990, p. 808-14 vol.1.

Y. Wang, T. Adali, and S. C. B. Lo, ``Automatic threshold selection for quantification,'' SPIE Journal of Biomedical Optics, vol. 2, no. 2, pp. 211-217, Apr. 1997.

R.M. Gray and L.D. Davisson, An Introduction to Statistical Signal Processing, 1995 and 1996 revision of Random Processes, Prentice Hall, by the same authors. (Current: Summer 1999 version).

Y. Wang, MR Imaging Statistics and Model-Based MR Image Analysis, Doctoral Dissertation, University of Maryland Baltimore County, Baltimore, MD, USA, May 1995. (postscript version)

Matlab References: (in case you need a quick reference)

MATLAB Users manual

MATLAB Image Processing Toolbox Users Manual

A MATLAB Primer (A short basic introduction to MATLAB. It is an old document but is always a good quick introduction/reminder material.) (postscript version)