logo-polimi
Loading...
Risorse bibliografiche
Risorsa bibliografica obbligatoria
Risorsa bibliografica facoltativa
Scheda Riassuntiva
Anno Accademico 2019/2020
Scuola Scuola di Ingegneria Industriale e dell'Informazione
Insegnamento 054293 - BIOMEDICAL SIGNAL PROCESSING AND MEDICAL IMAGES - BIOE 540-421
  • 054291 - BIOMEDICAL SIGNAL PROCESSING AND MEDICAL IMAGES [1] - BIOE 540
Docente Signorini Maria Gabriella
Cfu 5.00 Tipo insegnamento Modulo Di Corso Strutturato
Didattica innovativa L'insegnamento prevede  0.5  CFU erogati con Didattica Innovativa come segue:
  • Blended Learning & Flipped Classroom

Corso di Studi Codice Piano di Studio preventivamente approvato Da (compreso) A (escluso) Insegnamento
Ing Ind - Inf (1 liv.)(ord. 270) - MI (363) INGEGNERIA BIOMEDICA*AZZZZ054293 - BIOMEDICAL SIGNAL PROCESSING AND MEDICAL IMAGES - BIOE 540-421
Ing Ind - Inf (Mag.)(ord. 270) - MI (471) BIOMEDICAL ENGINEERING - INGEGNERIA BIOMEDICA*AZZZZ054293 - BIOMEDICAL SIGNAL PROCESSING AND MEDICAL IMAGES - BIOE 540-421
098655 - MEDICAL IMAGES - BIOE 421
096281 - BIOMEDICAL SIGNAL PROCESSING AND MEDICAL IMAGES - BIOE 440-421
098654 - BIOMEDICAL SIGNAL PROCESSING - BIOE 440
Ing Ind - Inf (Mag.)(ord. 270) - MI (481) COMPUTER SCIENCE AND ENGINEERING - INGEGNERIA INFORMATICA*AZZZZ098654 - BIOMEDICAL SIGNAL PROCESSING - BIOE 440
054293 - BIOMEDICAL SIGNAL PROCESSING AND MEDICAL IMAGES - BIOE 540-421

Obiettivi dell'insegnamento

Aim of the course is to enable students to master signal  processing methods and to acquire capabilities to the application in the biomedical field.  Students will acquire theoretical notions and will be guided to the main application tools with exercise classes and personal work

The Course covers biomedical signal processing, biomedical signal generation, from the theory to the practical applications.

The Course is organized into two parts: the first one [1] is dedicated to Biomedical Signal Processing.

The BSP objective is to introduce the most used methods of information processing for biomedical signals and to describe some significant applications in Medicine and Biology, in both physiological studies and in clinical applications for diagnosis, therapy and rehabilitation.

 The second part of the Course [2] deals with Medical Images.

The Course is organized in frontal lessons (25 hours), practical exercise sessions with laboratory exercises (15 hours) aiming at deeply analyzing topics related to signal processing by acquiring also practical knowledge making use of MatLab Tools.

5 hours will be spent in project development on topic of the Course proposed to students organized in groups with Tutor involvement and periodic revisions during the activity. 

0,5 CFU (5 hours) will be delivered through innovative teaching methods as “Blended Learning” and “Flipped Classroom”. Students will be actively involved studying and presenting to the class an assigned topic with the supervision of the laboratory tutors and teaching assistants with a final guided discussion.

Inside these activities 1 assignment will be proposed as autonomous student activity. The attendance to the Course is strongly advised both at frontal lessons and exercise sessions whose content is also part of the final evaluation.


Risultati di apprendimento attesi

The student will acquire methodological knowledge about Biomedical Signal Processing and analysis as well as applications and their main processing tools.

Students will be able to work on biomedical signal processing and analysis with Matlab tools.

Moreover, through the knowledge of advanced methods and parameters measuring physiological system changes, they should be able to work autonomously in application problems different from those addressed in the lessons and/or in the practical exercises.

Dublin Descriptors

Expected learning outcomes

Knowledge and understanding

Students will learn how to:

·        To know and use signal processing methods in biomedical field

  • Understand how to analyze biomedical signals
  • Design and apply feature extraction
  • Identify relationships between analysis parameters and physiological systems behavior

Applying knowledge and understanding

Given specific project cases, students will be able to:

  • Identify the corresponding requirements and hypothesize technical solutions
  • Work autonomously in different practical cases also different from those addressed in the lessons and/or in the laboratory practical exercises
  • Apply the theory to assess the applicability of the chosen methods
  • Develop and test signal processing solutions to solve specific application problems

Making judgements

Given a relatively complex problem, students will be able to:

·        Analyze and understand the goals, assumptions and requirements associated with that problem and to model it.

·        Define the methodological solution and evaluate its applicability

  • Identify and define all experimental and applicative steps
  • Estimate the computational effort required and the resources needed for its development, identify risks and define correction actions

Communication

Students will learn to:

  • Write a project specification document
  • Write a document summarizing the project results and make it available for a general audience
  • Communicate their work in front of their colleagues during project labs

Lifelong learning skills

  • Students will learn how to develop an applicative project
  • Students choosing to focus on the research project, will learn how to organize a research activity on some specific aspects of Biomedical signal processing through the development of innovative methodological and technical solutions and experimental data analysis.

 

 


Argomenti trattati

Biomedical Signal Processing [1]

Teaching Activity (25 +5  hours)

  • Introduction on digital signals and their properties: mean, variance, autocorrelation, stationarity, ergodicity. From time to frequency: the Fourier transform.
  • Analog to digital conversion: general workflow from acquisition to digitalization: the sampling theorem, the aliasing phenomenon, quantization error.
  • Digital filters: low and high pass filters, pass and stop band filters. Filter design techniques: windowing, frequency sampling, equiripple. Finite and infinite impulse response filters.
  • Non-parametric spectral analysis: definition and implementation of power spectral density. Non-parametric methods: periodogram, Bartlett, Welch for power spectral density, cross spectrum, and coherence.
  • Parametric spectral analysis: the system identification workflow. Investigation of different model families: AR, ARX, MA, ARMA and optimal order identification.
  • The Electrocardiography signal: signal generation and the physiological mechanisms of propagation of the heart.
  • The heart rate variability: contribution of sympathetic and parasympathetic regulation on the heart rhythms. Time, and frequency analyses of the signals by means of derived parameters.
  • Entropy: different measures for quantification of signal complexity (Approximate Entropy, Sample Entropy, Multiscale Entropy). Applications of complexity parameters on biological signals.
  • Arterial Blood Pressure signals: invasive and non-invasive signal acquisition. Systogram and diastogram series extraction. Different methodologies for the estimation of baroreceptive gain.
  • The Electroencephalography signal: the physiological mechanisms contributing to signal generation. Identification of signal rhythms in different frequency bands. The evoked potentials: characteristics and peculiar processing requirements.
  • Principal component analysis: feature dimensionality reduction. Mathematical description of the technique and application to biological signals.

5 hours out of 30 will be delivered through innovative teaching methods as “Blended Learning” and “Flipped Classroom”. Students will be actively involved studying and presenting to the class an assigned topic and an in-depth final guided discussion.

Laboratory Activity (15 hours)

The laboratory activity requires knowledge of programming in Matlab environment

  • Digital filters: implementation of FIR and IIR designs. Filter design techniques: windowing, frequency sampling, equiripple. Window characteristics and their effect on spectral leakage.
  • Non-parametric spectral analysis: implementation of parametric and non-parametric methods. Direct and indirect estimation of power spectral density. Signal analyzer, window designer, and SPT Tool Matlab toolboxes.
  • Parametric spectral analysis: Yule-Walker methods and system identification. Pipeline of ECG processing: from signal acquisition to time and frequency domain parameters.
  • Entropy: Approximate, Sample, and Quadratic entropy estimators. Parameters settings and their effect on the estimation of signal complexity.
  • Principal Component Analysis: application on signals and images for dimensionality reduction.

Project Activity  (5 hours)

A project laboratory is integral part of the course. The objective is to help students in translating the notions and methodologies learnt throughout the course in a specific case study. Projects will be assigned during the semester. Projects are expected to be delivered fixed deadlines by the end of the course. The evaluation of projects will be based on a final presentation to be discussed by the all project group. The project activity will include open discussions supervised by the course instructor and by tutors throughout the semester. Students who cannot take the project laboratory in this semester can work at the project on their own in the following semester. In this latter case, no support will be provided.


Prerequisiti

Students are required to know the principles and methods of biomedical signal processing as can be obtained after the attendance in the I level Course “Fundamentals of biomedical signal processing”. Basic notions about signal analysis in time and frequency domain, basic knowledge about biomedical signals and systems are also pre requisites. These concepts can be acquired in the I level Laurea with Courses as “Bioelettricità e Bioelettromagnetismo” and “Fundamentals of biomedical signal processing”

 

 


Modalità di valutazione

Assessment

The assessment will be based on a WRITTEN test with exercises and open questions (time 60 min).

It will assign up to 26 points and will be considered sufficient when the score will be equal or higher than 16. The project part will assign up to 4 points. The Lab assignment will assign up to 1 point. Projects and Lab assignments are not mandatory. Students can take the written part at any exam session during the year..

No mid-term assessments will be scheduled.

The score of the written exams (up to 26), the project (up to 4)  and the practical assessment (up to 1) will be summed to compute the total score. 30 cum laude will be assigned when the total score is 31.

To pass the exam the student must obtain an overall average grade of at least 18/30.

 

 

Type of assessment

Description

Dublin descriptor

Written test

·        Solution of numerical problems

·        Exercises focusing on application aspects

·        Theoretical questions on all course topics with open answer

1,2
1, 2, 3, 4, 5

1, 4, 5

Assessment of laboratory practical activity

·        Evaluation of the project

·        Assessment of the computational and experimental work developed by students either individually or in groups

2, 3, 4, 5

Oral presentation

·        Evaluation of the presentation of the project work activity developed as part of laboratory activities by students either individually or in groups

2, 3, 4, 5

 


Bibliografia
Risorsa bibliografica obbligatoriaLesson Notes and other Course materials available for download at : https://beep.metid.polimi.it/
Risorsa bibliografica facoltativaVinay K. Ingle and John G. Proakis, Digital Signal Processing Using MATLAB, Third Edition, ISBN: 978-1-111-42737-5
Risorsa bibliografica facoltativaRangaraj M. Rangayyan, Biomedical Signal Analysis , Editore: John Wiley & Sons., Anno edizione: 2002, ISBN: 0-471-20811-6
Risorsa bibliografica facoltativaA.V. Oppenheim, R.W. Schafer, Digital Signal Processing, Prentice Hall, 1975
Risorsa bibliografica facoltativaG. De Nicolao, R. Scattolini, Identificazione parametrica, Editore: CUSL ed, Anno edizione: 1997

Forme didattiche
Tipo Forma Didattica Ore di attività svolte in aula
(hh:mm)
Ore di studio autonome
(hh:mm)
Lezione
30:00
45:00
Esercitazione
15:00
22:30
Laboratorio Informatico
0:00
0:00
Laboratorio Sperimentale
0:00
0:00
Laboratorio Di Progetto
5:00
7:30
Totale 50:00 75:00

Informazioni in lingua inglese a supporto dell'internazionalizzazione
Insegnamento erogato in lingua Inglese
Disponibilità di materiale didattico/slides in lingua inglese
Disponibilità di libri di testo/bibliografia in lingua inglese
Possibilità di sostenere l'esame in lingua inglese
Disponibilità di supporto didattico in lingua inglese
schedaincarico v. 1.6.4 / 1.6.4
Area Servizi ICT
10/07/2020