Login
Course Information
Identification

CS 736: Medical Image Computing
 
Description

The course builds on fundamental theory in advanced data science, image processing, and machine learning for applications in medical image analysis.

1) Introduction to imaging modalities.
- Mathematical imaging models for physical signals, sampling, noise and artefact models. Signal modelling and model fitting.
- X ray, computed tomography (CT), positron emission tomography (PET), magnetic resonance imaging (MRI) (including diffusion MRI, functional MRI), microscopy, ultrasound, 2D and 3D imaging.

2) Visualization.
- Methods: sectioning, multimodal images, overlays, rendering surfaces and volumes, using glyphs.

3) Image reconstruction.
- Methods: mathematical models of image regularity, random fields, practical data sampling and acquisition schemes, problem formulations, optimization algorithms.
- Application domains: MRI, CT, PET, others.

4) Image restoration.
- Methods: degradation models for corrupted and missing data, Bayesian graphical modeling and inference, regression methods, learning based methods.
- Application domains: MRI, CT, PET, microscopy, ultrasound, others.

5) Image segmentation, object delineation, classification.
- Methods: clustering, graph partitioning, classification, mixture models, expectation maximization, hidden Markov random fields, multivariate Gaussian, kernel methods, variational methods using geometric and statistical modeling, abnormality detection, image categorization, computer aided diagnosis.
- Applications across biological structures and imaging modalities.

6) Statistical shape analysis.
- Methods: descriptors, shape spaces, learning shape models, learning shape mean and modes of variation.
- Application domains: organs and substructures, hypothesis testing, segmentation.

7) Image registration.
- Methods: similarity models, deformation models, energy functions, optimization algorithms.
- Applications: anatomical atlas generation, co-registration, motion correction.

8) Image retrieval.
- Methods: image descriptors, image similarity, searching, databases, hierarchical methods.
- Applications.

9) Machine learning methods in medical image computing.
 
References

Please see
https://www.cse.iitb.ac.in/~suyash/teaching/medical_image_computing.html
 
Home Page

https://www.cse.iitb.ac.in/~suyash/teaching/medical_image_computing.html
 
Prerequisites

Some course in image analysis / machine learning / data anlysis. OR Ask the instructor.
 
Other Details

Duration : Full Semester Total Credit : 6
Type : Theory
 
Autumn Semester 2019-20

Status : Not Offered Instructor : ---
 
Spring Semester 2019-20

Status : Offered Instructor : Prof. Suyash P. Awate




Last Modified Date: 15-Jul-2013

Webmail

Username:
Password:
Faculty CSE IT
Forgot Password
    [+] Sitemap     Feedback