Biomedical Imaging Analysis

Code:

EBE0056

Acronym:

AIBI

Keywords
Classification	Keyword
OFICIAL	Biomedical Engineering

Instance: 2012/2013 - 2S

Active?	Yes
Web Page:	http://moodle.fe.up.pt
Responsible unit:	Department of Electrical and Computer Engineering
Course/CS Responsible:	Master in Bioengineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
MEB	4	Syllabus	1	-	6	56	162
MIB	40	Syllabus	3	-	6	56	162
MIEEC	13	Syllabus (Transition) since 2010/2011	4	-	6	56	162
			5
		Syllabus	4	-	6	56	162
			5

Teaching language

Suitable for English-speaking students

Objectives

Develop knowledge and skills in:
• concepts and methodologies for digital image processing;
• principles, concepts and methods of physics and imaging technologies used in Biology and Medicine;
• students' exposure to various forms of Image Analysis and Processing in Biology and Medicine (IAP-BM).

Learning outcomes and competences

Learning outcomes are:

• knowledge acquisition in IPA-BM;
• analysis of problems in IPA-BM;
• design of IPA-BM;
• oral and written presentation.

Working method

Presencial

Program

1. INTRODUCTION 1.1. The image processing cycle 1.2. The machine and computer vision cycle 1.3. The Biomedical image analysis cycle 1.4. Applications 2. DIGITAL IMAGES: ACQUISITION, SAMPLING, QUANTIZATION AND REPRESENTATION 2.1. Introduction 2.2. Digital Images 2.2.1. Image acquisition 2.2.2. Sampling and quantization 2.2.3. An image in the frequency domain 2.2.4. Type of images 2.3. Biomedical Images 2.3.1. Microscopic Images 2.3.2. Light intensity images 2.3.3. Ultrasonic images 2.3.4. X ray images 2.3.5. CT and MR images 2.3.6. PET and SPECT 2.3.7. Thermographic images 3. IMAGE ENHANCEMENT 3.1. Basic intensity operations 3.1.1. Pixel operations 3.1.2. Image averaging 3.1.3. Image subtraction 3.1.4. Intensity histograms 3.2. Image enhancement using local operators 3.2.1. Smoothing filters 3.2.2. Sharpening filters 3.2.3. Edge enhancement 3.2.4. Non-linear filters 3.3. Adaptive image filtering 3.3.1. Wiener Filters 3.3.2. Anisotropic filtering 4. EDGE and CORNER DETECTION 4.1. Introduction 4.1.1. Initial considerations 4.1.2. Goals of edge and corner detection 4.1.3. Types of edges and corners 4.1.4. Basic definitions 4.2. Edge detection 4.2.1. First and second order derivative based operators 4.2.2. Canny Edge detector 4.2.3. Criteria for evaluating the performance of edge detectors 4.3. Line and curve fitting 4.3.1. Edge linking 4.3.2. Hough transform 4.4. Corner detectors 4.4.1. Introduction 4.4.2. Harris detector 5. MORPHOLOGICAL IMAGE PROCESSING 5.1. Basic principles 5.2. Binary images 5.2.1. Erosion and Dilation 5.2.2. Opening and Closing 5.2.3. Thinning 5.3. Grey level images 5.3.1. Basic operations 5.3.2. Morphological smoothing and gradient 5.3.3. Top-hat transform 5.4. Applications 6. IMAGE SEGMENTATION 6.1. Introduction 6.1.1. From images to objects 6.1.2. Goals, definition and overview 6.1.3. Categorization of segmentation methods 6.2. Feature domain 6.2.1. Brightness and colour 6.2.2. Texture 6.2.3. Clustering in the feature domain 6.3. Image domain 6.3.1. Region-based 6.3.2. Boundary-based 7. QUANTITATIVE IMAGE ANALYSIS 7.1. Introduction 7.1.1. Discrete geometry 7.1.2. Connected components labelling 7.2. Feature measurement 7.2.1. Boundary measures 7.2.2. Region measures 7.2.2.4. Invariant Moments 7.3. Object representation 7.3.1. Boundary 7.3.2. Region representation 7.3.2.3. Skeletons 8. IMAGE REGISTRATION AND MOSAICING 8.1. Fundamentals of image registration 8.1.1. Feature selection 8.1.2. Feature correspondence 8.1.3. Transformation functions 8.1.4. Resampling 8.2. Image mosaising 8.2.1. Determination of the global transformation 8.2.2. Image blending 9. MEDICAL IMAGING APPLICATIONS 9.1. In Ophthalmology 9.2. In Thoracic Imaging 9.3. In Chromatographic Imaging 9.4. Ultrasonic Imaging

Mandatory literature

Gonzalez, Rafael C; Digital image processing using Matlab. ISBN: 0-13-008519-7
Gonzalez, Rafael C; Digital image processing. ISBN: 0-201-50803-6

Teaching methods and learning activities

Theoretical-practical (TP) classes are mainly dedicated to the presentation of theoretical concepts and methods, but explanation will be complemented by the demonstration of practical examples.

Practical (P) sessions in the computer lab. Students will be asked solve  problems that require the application of concepts and methods previously presented in the theoretical and practical lessons.

Software

Matlab 6 R12.1

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Description	Type	Time (hours)	Weight (%)	End date
Attendance (estimated)	Participação presencial	68,00
Final exam	Exame	3,00	60,00	2013-07-19
Assignment	Trabalho laboratorial	20,00	40,00	2013-06-05
	Total:	-	100,00

Amount of time allocated to each course unit

Description	Type	Time (hours)	End date
Attendance	Frequência das aulas	68	2013-06-05
Assignment	Trabalho laboratorial	20	2013-06-05
Individual study	Estudo autónomo	74	2013-07-19
	Total:	162,00

Eligibility for exams

To be admitted to the final examination, the student:

1. Should miss more than 25% of classes ( both TP and lab) (necessary condition);

2. Do a  group assignment (study-EST) on a theme to be defined; this assignment involves the development of a routine in MatLab code that implements a method of IPA; the assignment the work should be presented by group members at a special session to be held in theoretical and practical lessons.

The student frequency grade (CF) is the grade of the group assignment.

Students who have attended practical classes in previous years, are not required to attend the practical classes, and do not need to do the group assignment. However, if they choose to assist TP classes, the previous frequency grade will not be considered.

Calculation formula of final grade

The final grade (NF) is obtained from two components, both expressed in the range [0 .. 20]:

1. Grade of the written final examination (PE);

2. Frequency grade (CF);

The final grade will be calculated according to the following expression:

NF = 0.6* PE +0.4 * F, where F = min (CF, PE +4).

(meaning that the frequency component of the final grade can never be higher than the exam grade plus 4 values)

Examinations or Special Assignments

1. Group assignment (two students) (40%)

2. Examination covering all course subjects.

Special assessment (TE, DA, ...)

Students with a special status will be evaluated as regular students.

Classification improvement

Students have to attend recurso (resit) exam to improve their grades. The exam will cover the entire program.