AI and imaging for cancer

Link al trailer del corso: edvance.it
Target: studentesse e studenti di CdS triennali
Lingua: eng
Il corso appartiene ad una serie?: No
Breve Descrizione:

The MOOC “AI and Imaging for Cancer” explores how artificial intelligence is revolutionizing medical imaging and precision medicine — from radiomics to pathomics — up to the clinical validation of models that bring innovation from the laboratory to the patient’s bedside.
Informazioni Base:
The course is divided into 5 modules and aims to provide learners with an overview of the use of radiomics.
 
  1. Introduction to AI
    1. AI - Intro, definitions, turing test
    2. Intelligent Systems - Expert, ML, DL
  2. Radiomics
    1. ARTIFICIAL INTELLIGENCE AND PRECISION MEDICINE 
    2. Radiomics - introduction
    3. Clustering e classification models.
    4. Interpretative use of AI
    5. Usi non interpretativi AI
  3. Deep learning and machine learning in medical imaging.
    1. DL in medical imaging - explanation. 
    2. Example ML -> characterization of hepatic metastases in ComputedTomography (CT) images
    3. Example ML -> characterization of response to chemotherapy of rectal cancer on MR and PET images
    4. Example DL -> Segmentation of colorectal cancer on MR images
    5. Example DL -> Segmentation of liver metastases on CT images 
  4. Pathomics
    1. What pathomics is.
    2. AI-Driven Pathomics for Predicting Chemotherapy Response in Metastatic Colorectal Cancer
  5. Model assessment and clinical validation. 
    1. From bench to bedside
    2. Steps to clinical validation
 
Risultati Attesi:

  • The student will be able to define artificial intelligence, explain the Turing test, and recognize the limitations of traditional definitions in the context of the historical evolution of intelligent systems.

  • The student will be able to compare expert systems, machine learning, and deep learning, discussing their features and areas of application in the context of radiology.

  • The student will be able to describe the radiomics workflow and identify the main oncological applications in the context of precision medicine.

  • The student will be able to explain how AI integrates clinical, radiomic, and genomic data to develop personalized predictive models in the context of precision oncology therapy.

  • The student will be able to apply clustering and classification techniques to distinguish pathological patterns in the context of medical image analysis and complex datasets.

  • The student will be able to distinguish between interpretative and non-interpretative applications of AI, assessing their advantages and limitations in the context of clinical practice and ethical implications.

  • The student will be able to describe the differences between ML and DL, explaining how they are applied to the processing and interpretation of medical images in the context of diagnostic imaging.

  • The student will be able to analyze ML applications for the characterization of hepatic metastases and the prediction of chemotherapy response in the context of oncological radiology.

  • The student will be able to evaluate DL applications for the automatic segmentation of colorectal tumors and hepatic metastases in the context of oncological treatment planning.

  • The student will be able to define pathomics, describe the extraction of features from digital histopathological images, and discuss their potential in the context of oncological diagnosis and prognosis.

  • The student will be able to analyze AI-based pathomics models for predicting chemotherapy response in the context of therapeutic personalization.

  • The student will be able to describe the steps of AI model validation, explain the concept of “from bench to bedside,” and discuss the challenges of clinical translation in the context of precision medicine.
Strategia di valutazione:

At the end of each module the student will be able to try a self-evaluation test.
Attività Base:

Interactive exercises and quizzes will be available to assess your learning progress and reinforce the knowledge you have acquired.
Prerequisiti:

Basic knowledge of artificial intelligence and radiological techniques.
Livello EQF: EQF Level 5
ISCED-F: 0619 Information and Communication Technologies (ICTs) not elsewhere classified
Categoria: Transdisciplinarità
SDGs: GOOD HEALTH AND WELLBEING
Docenti:

Valentina Giannini, Department of Oncology
Carico Lavoro Totale (in ore/settimana): 5
Numero settimane del corso: 1
Contatti:

For any queries or technical issues relating to the course and the platform, please contact:

edvancedeh@unito.it

Contact details of the MOOC lecturer:

valentina.giannini@unito.it