CODE | ICS5118 | |||||||||
TITLE | Intelligent Image Analytics | |||||||||
UM LEVEL | 05 - Postgraduate Modular Diploma or Degree Course | |||||||||
MQF LEVEL | 7 | |||||||||
ECTS CREDITS | 5 | |||||||||
DEPARTMENT | Artificial Intelligence | |||||||||
DESCRIPTION | The study-unit will provide the participants with an up-to-date background in current state-of- the-art in advanced digital image analysis. The aim of the study-unit is to show how to extract, model, and analyze information from images with a focus on medical image applications, which can be used for the diagnosis, and monitoring of diseases. The main topics include: - Image modalities; - Segmentation algorithms (e.g. snakes, watershed, region-growing, max-tree, ...); - Delineation of vessel-like structure (e.g. Frangi and B-COSFIRE filtering); - Registration; - Feature detection (e.g. detection of vessel bifurcations in retinal fundus images); - Shape and texture analysis; - Deformable shape model; - Hough transformation. Study-unit Aims: The aims of this study unit are to: - Introduce students to state-of-the-art techniques in the field of advanced image analysis; - Expose students to different types of medical images, including retinal fundus images, x-rays, mammograms, and MRI, among others; - Teach students appropriate evaluation methods for medical image analysis. The effect of false negatives in medical image analysis may lead to dramatic consequences; - Provide hands-on experience with popular tools, such as Matlab, Python and C++ for image processing. The VLFeat and OpenCV libraries will be used. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - Identify the right tools to segment important structures, to register images, to detect features, to classify images as healthy or unhealthy and to evaluate imaging classification system; - Understand different types of medical images and the rationale of their use; - Implement a pipeline (a chain of processing elements) to analyse images; - Consult with medical experts to understand the characteristics of specific types of images that influence the diagnosis. 2. Skills: By the end of the study-unit the student will be able to: - Use any of the techniques covered to process different types of images; - Compare the appropriateness of a number of segmentation, registration, delineation and feature detection techniques to solve various problems; - Implement algorithms with state of the art libraries; - Assess the quality of given images; - Present research work in front of an audience. Main Text/s and any supplementary readings: Title: "Digital Image Processing" 3rd edition, Prentice-Hall Authors: Gonzalez & Woods Date: 2008 ISBN: 9780131687288 Title: Fundamentals of Medical Imaging Author: Paul Suetens Year: 2009 ISBN: 0521519152 Title: Handbook of Medical Imaging, Volume 2. Medical Image Processing and Analysis Authors: J. Michael Fitzpatrick and Milan Sonka Year: 2009 ISBN: 0819477605 |
|||||||||
ADDITIONAL NOTES | Before taking this study-unit you are advised to take ICS2129 or a similar study-unit. | |||||||||
STUDY-UNIT TYPE | Lecture | |||||||||
METHOD OF ASSESSMENT |
|
|||||||||
LECTURER/S | ||||||||||
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2023/4. It may be subject to change in subsequent years. |