Vai al contenuto principale
Oggetto:

ONC0261A Machine learning for biomedical image processing

Oggetto:

Machine learning for biomedical image processing

Oggetto:

Academic year 2024/2025

Course ID
ONC0261A
Teachers
Attilio Fiandrotti (Lecturer)
Year
2nd year
Teaching period
Second semester
Type
Basic
Credits/Recognition
5
Course disciplinary sector (SSD)
INF/01 - informatics
Delivery
Formal authority
Language
English
Attendance
TBD
Type of examination
Practice test
Type of learning unit
modulo
Modular course
Biological and diagnostic imaging and image analysis (ONC0261)
Oggetto:

Sommario del corso

Oggetto:

Course objectives

The educational objectives are to provide both theoretical and practical skills in the field of medical image processing. The course is devised to meet to the specific educational objectives of the Artificial Intelligence for Biomedicine and Healthcare master, so all lecturesd, labs and teaching materials will be delivered exclusively in English. The course provides first the methodological foundations for image processing in the spatial and frequency domains. Next, the course will present the most recent leraning-based methodologies for medical image analysis, with hands-on lab sessions.

Oggetto:

Results of learning outcomes

Upon completion of the course, the student shall be able to understand which are the most approrpiate tools to apply for supervised tasks such as detection, classification, localization, regresstion, etc. over medical images of different type.

KNOWLEDGE AND UNDERSTANDING SKILLS. Acquisition of methodologies of selection, parameterization and application of medical image processing agorithms.

ABILITY TO APPLY KNOWLEDGE AND UNDERSTANDING. Acquisition of theoretical and practical tools for medical image processing.

SELF-JUDGMENT. Acquisition of the basic criteria for determining how to set up proper algorithm design for medical image analysis.

COMMUNICATION SKILLS. Acquisition of the technical terminolgy in the area of medical image processing.

LEARNING SKILLS. Development of autonomous learning skills for future training in the field.

Oggetto:

Program

* Foundamentals
Components of an image processing system
Image filtering in the spatial domain
Image filtering in the frequency domain
Colorspaces and transformations

* Applications of image processing
Lossy and lossless images compression
Morphological operators -> check!
Image segmentation -> check!

* Learnable medical image processing
Recap on (deep) convolutional neural networks for supervised tasks such as classification, detection, segmentation
Training deep convolutional models with PyTorch
Classification, regression and segmentation of RX images, hystological imaages, CT scan images, ecographies
Transformer based methods for medical image processing
Application of imaging methods to other medical data domains

Oggetto:

Course delivery

Lectures will take place in presence, with an option for remote only in exceptional circumstances. The students are invited to attend all lectures and labs, interacting with the lecturer both in presence and remotely offline via e-mail or through the course Moodle messaging system.

Oggetto:

Learning assessment methods

The students will be evaluated and graded on a lab project of their choice that will be prepared in part during the lab hours, and part will be left to the student to be complted as homework.

Suggested readings and bibliography



Oggetto:
Book
Title:  
Digital Image Processing, fourth ed.
Year of publication:  
2017
Publisher:  
Pearson Education
Author:  
R. C. Gonzalez, R. E. Woods
Required:  
No


Oggetto:
Book
Title:  
Deep Learning with PyTorch
Year of publication:  
2020
Publisher:  
Manning
Author:  
Eli Stevens, Luca Antiga, and Thomas Viehmann
Required:  
No


Oggetto:
Last update: 11/09/2024 11:28
Location: https://www.aibh.unito.it/robots.html
Non cliccare qui!