Go to:
Logótipo
Esta página em português Ajuda Autenticar-se
Formação regular da Biblioteca |fevereiro a maio
Today is sunday
You are here: Start > EBE0149
Authentication




Site map
Edifício A (Administração) Edifício B (Aulas) - Bloco I Edifício B (Aulas) - Bloco II Edifício B (Aulas) - Bloco III Edifício B (Aulas) - Bloco IV Edifício C (Biblioteca) Edifício D (CICA) Edifício E (Química) Edifício F (Minas e Metalurgia) Edifício F (Minas e Metalurgia) Edifício G (Civil) Edifício H (Civil) Edifício I (Electrotecnia) Edifício J (Electrotecnia) Edifício K (Pavilhão FCNAUP) Edifício L (Mecânica) Edifício M (Mecânica) Edifício N (Garagem) Edifício O (Cafetaria) Edifício P (Cantina) Edifício Q (Central de Gases) Edifício R (Laboratório de Engenharia do Ambiente) Edifício S (INESC) Edifício T (Torre do INEGI) Edifício U (Nave do INEGI) Edifício X (Associação de Estudantes)

Computer-Aided Diagnostics

Code: EBE0149     Acronym: DACO

Keywords
Classification Keyword
OFICIAL Biomedical Engineering

Instance: 2016/2017 - 1S Ícone do Moodle

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 2 Syllabus 1 - 6 56 162
MIB 34 Syllabus 4 - 6 56 162

Teaching Staff - Responsibilities

Teacher Responsibility
Aurélio Joaquim de Castro Campilho

Teaching - Hours

Recitations: 3,00
Laboratory Practice: 1,00
Type Teacher Classes Hour
Recitations Totals 1 3,00
Aurélio Joaquim de Castro Campilho 3,00
Laboratory Practice Totals 2 2,00
Adrian Galdran Cabello 2,00

Teaching language

Portuguese

Objectives

Computer aided diagnosis can be defined as the the diagnosis made by the radiologist supported by a computer based medical image analysis that acts as a second opinion system. The course aims at giving the students the knowledge and ability to develop image enhancement, image analysis and classification systems useful in CAD environments.

Learning outcomes and competences

 

To contribute to develop the capacity of the students to work autonomously and in group, to do bibliographic research, to prepare written reports and to deliver oral presentations.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

Previous knowledge:

Biomedical Image Analysis, Signal Processing, Matlab

Program

PART 1: Computer-aided Diagnosis (CAD): Overview

  •      Typical organization of a CAD system
  •      Developments in CAD Systems
PART 2: Methodologies

1.     Mathematical Foundations
            Linear Algebra
            Statistical Analysis
2.     Introduction to pattern recognition (PR)
            A PR architecture for CAD
            Data collection and feature choice
3.     Bayesian Classification
            Class characterization
            A posterior probabilities and MAP classifier
            The normal density case
4.     Non-parametric learning
            Histograming
            Parzen method
            K-nearest neighbor
            Linear discriminant functions
            Support vector machines
5.     Feature reduction
            Feature extraction
            Feature selection
6.     Image enhancement
            Spatial domain: Linear, Morphological and adaptive filters
            Frequency domain: Homomorphic filtering; Wavelets
7.     Image segmentation in CAD
            Thresholding and clustering
            Texture analysis
            Organ segmentation and Detection of lesions
8.      Evaluation and interpretation

PART 3: Applications

Application examples in Ophthalmology, Thorax imaging and Mammography

Mandatory literature

Rangaraj M. Rangayyan; Biomedical image analysis. ISBN: 0-8493-9695-6
2. F. Der Heijden, R. Duin, D. Ridder, D. Tax; Classification, Parameter Estimation and State Estimation. An Engineering Approach using Matlab, Wiley, 2004

Teaching methods and learning activities

Presentation of image analysis and classification methodologies and discussing of Computer Aided Diagnosis topics.
Groups of 4 students will present five CAD case studies .

Software

Matlab

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation Weight (%)
Exame 50,00
Trabalho laboratorial 50,00
Total: 100,00

Eligibility for exams

To reach a passing grade during the semester

Calculation formula of final grade

The final mark (NF) has 2 components: CF - Evaluation during the semester (50%) which includes the study, analysis and 2 assigments on pattern recognition and image analysis (PR1+PR2), by groups of 2 students and a challenge (CH) by groups of 4 students.; 2.EX -Exam (50%), which is a written exam with problems about the taught material. A student to be approved, have to have a mark greater or equal to 8.0 in each of the components CF and EX, and NF has to be greater or equal to 10. The corresponding expressions are:

CF = 0.2*PR1+0.2*PR2+0.6*CH

NF=0.5*CF+0.5*EX, para EX >= 8.0

NF=EX para EX < 8.0



Examinations or Special Assignments

Case studies: Challenge (group of 4 students)
Two Assignments (2 students)

Special assessment (TE, DA, ...)

The students are submitted to the same type of evalutation and with the same rules  of the other students with a normal statue

Classification improvement

In the same academic year, the students may apply to improve the mark for the written exam only.

Recommend this page Top
Copyright 1996-2019 © Faculdade de Engenharia da Universidade do Porto  I Terms and Conditions  I Accessibility  I Index A-Z  I Guest Book
Page generated on: 2019-05-26 at 01:01:20