Ghassan Hamarneh
 Professor
 School of Computing Science
 Faculty of Applied Science
 Simon Fraser University

 ACM & IEEE Senior Member
 BRC RAMP NeuroDevNet NeuroScience
 CDIRE BIONF MICCAI

 
Medical Image Analysis Lab

Home home Email [replace (at) with @]email  Contactcontact

 

News | Bio | Research | Publications Teaching | Students | Software | Funding

CMPT 419: Biomedical Image Computing -- Special Topics in AI
Cross listed with
CMPT 829: Biomedical Image Computing -- Special Topics in Bioinformatics

Next offering: Fall 2013.
course outline
Course homepage


Note to non-SFU graduate students
For non-SFU undergraduate students, inquire about attending CMPT419 by emailing csugrad@sfu.ca


  • General objectives of the course: This course is designed to give students the knowledge needed to understand, develop,  and use software and algorithms on medical image data, to extract useful clinical information. It may be viewed as a course in image processing and computer vision  adapted to 3D (volumetric) and more complex medical images (such as MRI or CAT scans), with health-related application.
  • In this course you will:
    • learn about medical imaging modalities such as MRI, CT, and ultrasound, and recent advances such as functional and molecular imaging, diffusion tensor imaging, and time-varying medical images.


    Examples of several types of medical image (modalities) of the brain.
     

    • appreciate the need for developing automated, accurate, robust, and fast, techniques for extracting information from medical imaging for a variety of health applications.
    • learn how biomedical image computing involves understanding, adapting and applying a variety of computational, mathematical and engineering techniques which include: signal/image processing, optimization, AI, machine learning, graph theory, mathematical modeling, differential equations, multi-variate statistics,  geometrical modeling, matrix/tensor algebra, etc.


    High-level overview

  •  learn about biomedical image file format (including DICOM, Analyze, MINC),  and how they are different from images you capture with your digital camera.


Example information related to a DICOM medical image file.

  • learn about different approaches for processing, and enhancing (reducing noise) in medical images  (including spatial, frequency-domain, and morphological filtering).


Enhancing an MRI image of a mouse kidney.


Reducing noise in a heart image.

  • learn how to model variability in anatomical shapes and how can this translate into improved healthcare. You can calculate the mean and variance of some numbers, but how do you find the "mean and variance" of heart ventricles?


(left) ventricle of the heart in an ultrasound image. (middle) Some acceptable and implausible ventricular shapes. (right) average ventricle shape and allowable variations.

  • learn what biomedical image segmentation is, different approaches (including clustering, deformable models, region-based and level-set approaches), and why is it important for medicine.


A PDE-based optimization method is used to move the red contour in a brain image and identify the corpus callosum (bridge connecting left and right brain hemispheres).


 Schematic diagram of a graph-theoretic approach for identifying objects in a medical image.

  • understand what medical biomedical image registration is,  its applications in health care, and what its basic building blocks.


Before  (top) and after (bottom) registration of radioactivity (orange)  to anatomy from CT image (gray).


Registering an extended knee to a flexed knee.

  • learn how to use 3D and medical imaging software to view and process your data. Think of these as Photoshop-like tools for 3D  and more complicated images.


Example software screenshots and applications.

  • Project: The course involves working on a biomedical image computing project. A wide range of projects related to the above topics is possible. The project topic can be either initiated by the student or recommended by the instructor. The project may  be very clinical application oriented or may deal with a theoretical aspect of  computational/mathematical techniques for medical image analysis, or a combination of both (see some example projects at our Medical Image Analysis Lab).
  • Advantages: there are many other advantages to studying topics at the interface between computing and medicine, including: wider career opportunities, graduate studies and funding, working with state-of-the-art software and hardware, collaborating with doctors and accessing valuable medical data... more are mentioned here.
  • More details about the course are available in the formal course outline

  
(left) vasculature in 3D brain MR angiography (head seen from above, nose in lower right corner)   (right) spinal cord detection in MRI

 
rotator cuff muscle in the shoulder

 
 
back 2003-2012 G. Hamarneh Contact Email [replace (at) with @] Home  Last update: 21-Sep-2012top