Statistical Methods in NeuroImage Analysis

 Time: Every Friday 1:00-4:00PM between September 2 to December 9.

 Place: Seoul National University Hosptial BLDG 001 ROOM 308.
 This is the first building you see from the gate near Hyewha subway

 station exit 3.

 Instructor:  Moo K. Chung

 Course webpage: http://brainimaging.waisman.wisc.edu/~chung/neuro.processing
 Office Hour: Friday 4:00-5:00PM or after class.
 Email: mkchung@wisc.edu

 Prerequisites:
 None. Need an acess to MATLAB. Learning curve will be steep.

 Target Audience:
 Anyone who is interested in analyzing brain images statistically.


 Course Evaluation:
 Students are required to submit an initial report containing
 preliminary proposal before the course drop deadline (10%), give 20-
 minute oral presentation (20%) and submit the final report (30%).

 There will be exams (40%).  In last two years, 16 students took

 similar courses and the grade distribution is as follows: 1 A, 8 A-, 5
 B+, 2 B, 1 C.

 Text book:
 Computational Neuroanatomy: The Methods. This is a preprint of book I
 am currently writing and it will be freely available to students.

 Course Outline:
 Various statistical issues in neuroimage processing and analysis will
 be addressed. The focus of the course is on the computational aspect
 of various statisical procedures used in neuroimages. MATLAB will be
 used as a language of instruction although students can do homework
 and project in any computer languages of their choice. The following
 topics will be covered:

 Week 1: Introduction to statistical computing in MATLAB, General
 linear models and random field theory.
 Week 2: Smoothness of fields, Type-I error. multiple comparision
 correction using random field theory.
 Week 3: Machine learning. Support vector machines (SVM).
 Week 4: Type-II error in correlated images. Sample size computation.
 Power analysis.
 Week 5-6: Hilbert space methods and Karhunen-Loeve expansion in random
 fields.

 Week 7-8: Linear models: general linaer models, mixed and fixed effect

 models.
 Week 9-10: More multiple comparisions using FDR and permutation tests.
 Nonparametric test procedures.
 Week 11: Time series analysis.
 Week 12-13: Multivariate analysis.
 Week 14: Student presentation.

 

 NOTE: I will be teaching a similar course in Madison in the spring of 2012.