Skip to main content
If you continue browsing this website, you agree to our policies:
  • Condizioni di utilizzo e trattamento dei dati
Continue
x
e-Learning - UNIMIB
  • Home
  • My Media
  • More
Listen to this page using ReadSpeaker
 Log in
e-Learning - UNIMIB
Home My Media
Percorso della pagina
  1. Science
  2. Master Degree
  3. Artificial Intelligence for Science and Technology [F9103Q - F9102Q]
  4. Courses
  5. A.Y. 2024-2025
  6. 1st year
  1. Signal and Imaging Acquisition and Modelling in Healthcare
  2. Summary
Insegnamento Course full name
Signal and Imaging Acquisition and Modelling in Healthcare
Course ID number
2425-1-F9102Q016
Course summary SYLLABUS

Course Syllabus

  • Italiano ‎(it)‎
  • English ‎(en)‎
Export

Obiettivi

L' obiettivo del corso è di fornire i principi fisici e i metodi di elaborazione alla base dei sistemi di acquisizione dei segnali e immagini biomedici per lo sviluppo di modelli di intelligenza artificiale applicati a tali sistemi che supportino la decisione medica nella prevenzione, screening, diagnosi e terapia di pazienti a rischio di patologie multifattoriali complesse.
Le lezioni teoriche sono integrate con esercitazioni pratiche in aula durante le quali saranno forniti dataset di segnali e immagini biomedici per applicare i principi teorici nello sviluppo di modelli di intelligenza artificiale a supporto della decisione medica.

Contenuti sintetici

Principi fisici e metodi di elaborazione dei sistemi di acquisizione dei segnali e immagini biomedici per lo sviluppo di modelli di intelligenza artificiale affidabili e comprensibili applicati che supportino la decisione medica.

Lezioni teoriche integrate con esercitazioni pratiche in aula per lo sviluppo di modelli di intelligenza artificiale a supporto della decisione medica.

Programma esteso

-Biomedical signals: Electrocardiography/Electroencelography/Electromiography/functional NIRS

  • Machine learning and deep learning systems for signal-guided personalized predictive medicine
    -Biomedical imaging: Ultrasonography/Radiography/Computerized Tomography/ Mammography/MRI, mpMRI, fMRI/Positron Emission Tomography/Hybrid systems
    -Biomedical imaging in image-guided radiotherapy
    -Biomedical imaging for lesion detection and semantic segmentation
  • Radiomic/radiogenomic modelling for screening and diagnosis
    -Radiomic/radiogenomic modelling for treatment
    -Machine learning and deep learning systems for explainable image-guided personalized predictive medicine (supervised/unsupervised learning)

Prerequisiti

Livello medio-alto di programmazione in Matlab o Python

Modalità didattica

Lezioni frontali ed esercitazioni mediante codici di programmazione.

Il docente fa molte lezioni in cui inizia con una prima parte in cui vengono esposti dei concetti
(modalità erogativa) e poi si apre un’interazione con gli studenti che definisce la parte successiva
della lezione (modalità interattiva).

  • 9 lezioni frontali da 2 ore svolte in modalità erogativa in presenza in modalità erogativa nella parte iniziale che è volta a coinvolgere gli
    studenti in modo interattivo nella parte successiva;
  • 11 esercitazioni da 4 ore e 1 esercitazion da 2 ore svolte in presenza volta a coinvolgere gli studenti in modo interattivo nel PROJECT WORKS;

Tutte le attività sono svolte in presenza.

Materiale didattico

Appunti, software, dati e articoli scientifici forniti agli studenti durante il corso.

Periodo di erogazione dell'insegnamento

Primo semestre.

Modalità di verifica del profitto e valutazione

L' esame consiste in un colloquio orale volto a verificare il livello di conoscenza dello studente degli argomenti trattati durante il corso e in 2 PROJECT WORKS, progetti di sviluppo di 2 codici di programmazione basati sui
metodi di machine learning e deep learning su presentati durante il corso.

Orario di ricevimento

Al termine della lezione in aula il docente e' disponibile a ricevere gli studenti per 1 h

Sustainable Development Goals

SALUTE E BENESSERE
Export

Aims

The aim of the course is to provide the physical principles and processing methods underlying biomedical signal and image acquisition systems for the development of artificial intelligence models applied to that support medical decision-making in the prevention, screening, diagnosis and therapy of patients at risk of complex multifactorial diseases.
Theoretical lessons are integrated with practical exercises in the classroom during which datasets of biomedical signals and images will be provided to apply the theoretical principles in the development of artificial intelligence models to support medical decision.

Contents

Physical principles and processing methods of biomedical image and signal acquisition systems for the development of trustworth and explainable artificial intelligence models that support medical decision.

Theoretical lessons integrated with practical exercises in the classroom for the development of artificial intelligence models to support medical decisions.

Detailed program

  • Biomedical signals: Electrocardiography / Electroencelography / Electromyography / functional NIRS
  • Machine learning and deep learning systems for signal-driven personalized predictive medicine
  • Biomedical imaging: ultrasound / radiography / computed tomography / mammography / MRI, mpMRI, fMRI / positron emission tomography / hybrid systems
  • Biomedical imaging in image-guided radiotherapy
  • Biomedical imaging for lesion detection and semantic segmentation
  • Radiomic / radiogenomic modeling for screening and diagnosis
  • Radiomic / radiogenomic modeling for treatment
    -Machine learning and deep learning systems for explainable image-guided personalized predictive medicine (supervised / unsupervised learning)

Prerequisites

Medium-High level of programming in Matlab or Python

Teaching form

Lectures and exercises using programming codes.

The teacher gives many lessons in which he begins with a first part in which concepts are exposed
(delivery method) and then an interaction opens with the students which defines the next part
of the lesson (interactive mode).

  • 9 frontal lessons of 2 hours carried out in the delivery mode in presence in the delivery mode in the initial part which is aimed at involving the students
    students interactively in the next part;
  • 11 4-hour exercises and 1 2-hour exercise carried out in person aimed at involving students interactively in the PROJECT WORKS;

All activities are carried out in person

Textbook and teaching resource

Notes, software, data and scientific articles provided to students during the course.

Semester

First semester.

Assessment method

The exam consists of an oral interview aimed at verifying the student's level of knowledge of the topics covered during the course and in 2 PROJECT WORKS development projects of 2 programming codes based on the
machine learning and deep learning methods presented during the course.

Office hours

At the end of the classroom lesson the teacher is available to receive students for 1 hour

Sustainable Development Goals

GOOD HEALTH AND WELL-BEING
Enter

Key information

Field of research
FIS/07
ECTS
6
Term
Second semester
Activity type
Mandatory to be chosen
Course Length (Hours)
64
Degree Course Type
2-year Master Degreee
Language
English

Staff

    Teacher

  • IC
    Isabella Castiglioni

Students' opinion

View previous A.Y. opinion

Bibliography

Find the books for this course in the Library

Enrolment methods

Manual enrolments
Self enrolment (Student)

Sustainable Development Goals

GOOD HEALTH AND WELL-BEING - Ensure healthy lives and promote well-being for all at all ages
GOOD HEALTH AND WELL-BEING

You are not logged in. (Log in)
Policies
Get the mobile app
Powered by Moodle
© 2025 Università degli Studi di Milano-Bicocca
  • Privacy policy
  • Accessibility
  • Statistics