Code EB7
Type Elective
Semester B
ECTS credits 5

COURSE OUTLINE 

(1) GENERAL 

SCHOOL  ENGINEERING 
ACADEMIC UNIT  POSTGRADUATE PROGRAM in BIOMEDICAL ENGINEERING 
LEVEL OF STUDIES  MSc  
COURSE CODE  CEID_NE4828  SEMESTER  Spring 
COURSE TITLE  MEDICAL IMAGE PROCESSING AND ANALYSIS 
INDEPENDENT TEACHING ACTIVITIES
if credits are awarded for separate components of the course, e.g. lectures, laboratory exercises, etc. If the credits are awarded for the whole of the course, give the weekly teaching hours and the total credits 
WEEKLY TEACHING HOURS  CREDITS 
Lectures and tutorials  3  3 
Laboratory Exercises  2  2 
Add rows if necessary. The organisation of teaching and the teaching methods used are described in detail at (d).  5  5 
COURSE TYPE  

general background,
special background, specialised general knowledge, skills development 

Special background  

skills development 

PREREQUISITE COURSES: 

 

Recommended prerequisite courses: 

  • Probability and Basic Statistics  
  • Signals and Systems Theory  
  • Digital Signal Processing  
  • Programming 
LANGUAGE OF INSTRUCTION and EXAMINATIONS:  English (in case of foreign students attending the course). Also relevant material is available in English  
IS THE COURSE OFFERED TO ERASMUS STUDENTS  YES 
COURSE WEBSITE (URL)  https://eclass.upatras.gr/courses/CEID1033/ 

(2) LEARNING OUTCOMES 

Learning outcomes 
The course learning outcomes, specific knowledge, skills and competences of an appropriate level, which the students will acquire with the successful completion of the course are described. 

Consult Appendix A  

  • Description of the level of learning outcomes for each qualifications cycle, according to the Qualifications Framework of the European Higher Education Area 
  • Descriptors for Levels 6, 7 & 8 of the European Qualifications Framework for Lifelong Learning and Appendix B 
  • Guidelines for writing Learning Outcomes  
Α. Theory 

The student that will successfully attend the course, will be able to: 

  • describe the basic structure and the main subsystems of an Image Processing and Analysis System 
  • describe a generic image acquisition system and the relevant degradations it may introduce 
  • understand the basic concepts of 2-D signal processing and know the main 2-D transforms 
  • analyze a specific image processing problem and suggest suitable methods for: 
  • image enhancement 
  • image restoration  
  • image compression 
  • analyze a specific image analysis application and suggest suitable methods for: 
  • edge detection and linking 
  • segmentation 
  • shape description and representation 
  • object recognition 
  • know main principles of color theory and understand the particularities of color image processing and analysis. 
  • Know the modern developments (theory and methods) for image processing & analysis based on machine learning techniques  
  • Know basic deep neural network architectures which are suitable for the problems at hand. 

 

B. Laboratory exercise 

The student that will successfully complete the laboratory part of the course, will be able to: 

  • simulate and study a generic image acquisition system 
  • simulate and study basic 2-D signal processing transforms 
  • implement main image processing techniques for:  enhancement, restoration, compression (both lossless and lossy) 
  • implement and study algorithms for:  edge detection, region segmentation 
  • implement and study algorithms for shape description and object recognition. 
  • Implement and study machine learning (and deep learning) techniques for typical image processing and analysis problems. 

 

 

General Competences  
Taking into consideration the general competences that the degree-holder must acquire (as these appear in the Diploma Supplement and appear below), at which of the following does the course aim? 
Search for, analysis and synthesis of data and information, with the use of the necessary technology  

Adapting to new situations  

Decision-making  

Working independently  

Team work 

Working in an international environment  

Working in an interdisciplinary environment  

Production of new research ideas  

Project planning and management  

Respect for difference and multiculturalism  

Respect for the natural environment  

Showing social, professional and ethical responsibility and sensitivity to gender issues  

Criticism and self-criticism  

Production of free, creative and inductive thinking 

…… 

Others… 

……. 

Working independently 

Team work 

Working in an international environment 

Working in an interdisciplinary environment 

Production of new research ideas 

(3) SYLLABUS

A. Lectures

During the course, the following material, among others, will be covered: 

  • Introductory concepts for Image Processing & Analysis and their applications 
  • Basic elements of 2-D signal processing and image transforms 
  • Image acquisition systems and different types of degradation  
  • Image enhancement methods 
  • Image restoration methods 
  • Techniques for lossless and lossy image compression  
  • Elements of color theory and color image processing basics.  
  • Reconstruction of 3D objects based on 2D projections 
  • Edge detection and linking 
  • Image segmentation 
  • Shape description and representation 
  • Object recognition 
  • Basic structure of an image analysis system 
  • Basic principles of machine learning for image processing & analysis 
  • Elements of deep neural networks (DNN) theory and architectures  
  • Emphasis on DNN architectures suitable for image processing & analysis. 

 B. Laboratory exercises and project

 

Exercises: 

  • Exercise 1: Image transforms and image filtering in the frequency domain  
  • Exercise 2: Image quantization (scalar and vector) 
  • Exercise 3: Image compression using DCT transform 
  • Exercise 4: Histogram based image processing 
  • Exercise 5: Image restoration (inverse filtering, Wiener filtering) 
  • Exercise 6: Edge detection. 

 

Project: 

  • Each student will choose to implement one from a list of possible projects.  Indicative list of project subjects: 
  • Denoising of images (e.g. medical) based on sparse representation 
  • Registration of spatio-temporally correlated images 
  • Reconstruction of MRI images via dictionary learning techniques 
  • Comparative study of Convolutional Neural Networks for object classification (in different applications contexts)  
  • Image retrieval: Comparative study of techniques based on PCA and Autoencoders. 

 

 

(4) TEACHING and LEARNING METHODS – EVALUATION 

DELIVERY
Face-to-face, Distance learning, etc. 
Face-to-face 
USE OF INFORMATION AND COMMUNICATIONS TECHNOLOGY
Use of ICT in teaching, laboratory education, communication with students 
Extensive use of ICT tools. In particular: 

  • Web site (university e-class platform) with material for the lectures, the tutorial exercises and the laboratory exercises. 
  • Maintaining a forum for technical discussions, answering questions, etc. 
  • Contact with students either via the Forum or via email. 
  • Electronic announcements and notifications via email. 
  • Via the open class version of the course, there is additional material available.  
TEACHING METHODS 

The manner and methods of teaching are described in detail. 

Lectures, seminars, laboratory practice, fieldwork, study and analysis of bibliography, tutorials, placements, clinical practice, art workshop, interactive teaching, educational visits, project, essay writing, artistic creativity, etc. 

 

The student’s study hours for each learning activity are given as well as the hours of non-directed study according to the principles of the ECTS 

Activity  Semester workload 
Lectures  26 hours 
Tutorials  13 hours 
Studying during the course  26 hours 
Implementation of laboratory exercises   60 hours 
Preparation and participation in exams  25 hours 
   
   
   
   
Course total   150 hours 

 

STUDENT PERFORMANCE EVALUATION 

Description of the evaluation procedure 

 

Language of evaluation, methods of evaluation, summative or conclusive, multiple choice questionnaires, short-answer questions, open-ended questions, problem solving, written work, essay/report, oral examination, public presentation, laboratory work, clinical examination of patient, art interpretation, other 

 

Specifically-defined evaluation criteria are given, and if and where they are accessible to students. 

Performance evaluation is based on: 

  • Written or oral examination (50% of the final grade) 
  • Laboratory exercises (25% of the final grade) 
  • Laboratory project (25% of the final grade) 

 

 

 

 

 

 

 

(5) ATTACHED BIBLIOGRAPHY 

– Suggested bibliography: 

  • «Digital Image Processing»,  R. Gonzalez and R. Woods, Pearson, 4th edition, 2017. 
  • «Digital Image Processing and Analysis», N. Papamarkos, Edition 2013 (in Greek) 

 

– Related academic journals and conferences: 

  • IEEE Transactions on Image Processing 
  • IEEE Transactions on Signal Processing 
  • IEEE Signal Processing Magazine 
  • ELSEVIER  –  EURASIP  Image Communication  Journal  
  • IEEE ICIP, IEEE ICASP, IEEE Globalsip, Eusipco