B5420 - Seminario Intelligenza Artificiale

Learning outcomes

The student acquires the skills of artificial intelligence applied to Radiology and all the diastics for Imaging, radiotherapy and Nuclear Medicine.

Course contents

Main Contents:

Fundamentals of Artificial Intelligence and Machine Learning

Supervised, Unsupervised, and Deep Learning

Convolutional Neural Networks (CNNs) for Medical Imaging

AI in Radiology and Diagnostic Imaging

Pathology Pattern Recognition and Classification

Automatic Organ and Lesion Segmentation

Computer-Aided Diagnosis (CAD) Systems

AI in Radiotherapy

Treatment Plan Optimization

Predictive Analytics for Treatment Response

AI-Guided Adaptive Radiotherapy

AI in Nuclear Medicine

Reconstruction Enhancement and Noise Reduction

Automatic Uptake Quantification

Multimodal Fusion (PET/CT, PET/MRI) and Radiomics Analysis

Ethics, Validation, and Regulatory Issues

Clinical Validation of AI Models

Regulatory Compliance (e.g., MDR, AI Act)

Ethical and Interpretability Considerations

Readings/Bibliography

Slides and lecture notes

"Artificial Intelligence for Health" – Giovanni Rinaldi, 2022 (Il Pensiero Scientifico)

"Deep Learning for Medical Image Analysis" – S. Kevin Zhou, Hayit Greenspan & Dinggang Shen, 2017 (Academic Press)

Teaching methods

Lectures

Practical exercises with real datasets

Discussion of clinical cases and scientific articles

Use of open-source software and AI tools for medical imaging (e.g., MONAI, nnU-Net)

Assessment methods

Practical project on medical image datasets

Presentation of an application case.

Students with learning disorders and\or temporary or permanent disabilities: please, contact the office responsible (https://site.unibo.it/studenti-con-disabilita-e-dsa/en/for-students) as soon as possible so that they can propose acceptable adjustments. The request for adaptation must be submitted in advance (15 days before the exam date) to the lecturer, who will assess the appropriateness of the adjustments, taking into account the teaching objectives.

Teaching tools

Articles, software, and database access.

Example:

1. Development environments

Google Colab, Jupyter Notebook

MONAI, nnU-Net, TotalSegmentator

2. Open access datasets

TCIA, MIDRC, BraTS, LIDC-IDRI, MICCAI Challenges

3. Processing software

3D Slicer, ITK-SNAP, QuPath

4. E-learning and collaboration

Moodle, Teams, Zoom

Padlet, Miro, Notion

Office hours

See the website of Gastone Castellani