C9809 - Applicazioni di Intelligenza Artificiale e Radiomica in Diagnostica per Immagini e Radioterapia (RN)

Learning outcomes

The course aims to introduce the principles and applications of artificial intelligence and radiomics in the fields of medical imaging and radiation therapy, fostering the ability to understand and effectively utilize these tools in support of clinical, decision-making, and organizational processes, while adhering to the principles of appropriateness, safety, and professional ethics.

Course contents

The following topics will be delivered with the contribution of Professor Stefano Neri, serving as Subject Matter Expert (Cultore della Materia).

 

1. Artificial Intelligence in Healthcare and Radiology:
Fundamentals of Artificial Intelligence and machine learning, with a focus on how AI systems learn from medical images; examples of AI applications currently implemented in diagnostic imaging; the European AI Act and the principles of safety, appropriateness, transparency, and human oversight in clinical practice.

2. When AI Interprets Medical Images:
Detection, recognition, and segmentation of imaging findings; practical applications in conventional radiography, computed tomography (CT), and magnetic resonance imaging (MRI); AI-driven image reconstruction and enhancement techniques, including noise reduction and dose optimization.

3. AI in Action: From the Patient to the Image:
Applications of AI across diagnostic pathways and emergency settings; stroke imaging, CT perfusion, and CT angiography; AI-supported triage, prioritization, and clinical decision support systems; integration of AI tools into the workflow of the Medical Radiology Technologist (MRT).

4. Radiomics: When Images Become Quantitative Data:
Extraction of quantitative information from medical images; radiomic features including shape, intensity, and texture descriptors; practical applications of radiomics in lesion characterization, precision medicine, and oncological imaging.

5. Artificial Intelligence and Radiomics in Radiation Therapy:
AI applications in auto-contouring, treatment planning, and adaptive radiotherapy; use of quantitative imaging and radiomic biomarkers to improve tumor characterization, patient stratification, and prediction of treatment response.

6. Can We Trust AI? Critical Appraisal and Professional Responsibility:
Clinical cases and examples of algorithmic errors; false positive and false negative results, bias, and limitations of AI systems; critical evaluation and interpretation of AI-generated outputs; data protection, professional accountability, and the role of the Medical Radiology Technologist in the safe and effective use of AI technologies.

Readings/Bibliography

1. Erickson B.J., Korfiatis P., Akkus Z., Kline T.L. Machine Learning for Medical Imaging: Principles and Applications. Academic Press, Cambridge, MA, 2020.

2. Hosny A., Parmar C., Quackenbush J., Schwartz L.H., Aerts H.J.W.L. Artificial Intelligence in Radiology. Springer Nature, Cham, 2024.

3. Lambin P., Leijenaar R.T.H., Deist T.M., et al. Radiomics and Radiogenomics: Technical Basis and Clinical Applications. Springer, Cham, 2022.

4. van Timmeren J.E., Cester D., Tanadini-Lang S., Alkadhi H., Baessler B. Radiomics in Medical Imaging: Concepts, Methodologies and Clinical Applications. Springer Nature, Cham, 2023.

5. Mazurowski M.A. Deep Learning in Medical Image Analysis. CRC Press, Boca Raton, FL, 2019.

6. Bourhis J., Dörr W., Lee N. Image-Guided and Adaptive Radiation Therapy. Springer, Cham, 2021.

Radiologia e diagnostica per immagini

1. Brady A.P., Neri E., Granata V. (Eds.) Artificial Intelligence in Medical Imaging. Springer Nature, Cham, 2019.

1. European Society of Radiology (ESR) ESR Guide to Artificial Intelligence in Radiology. European Society of Radiology Publications, Vienna, ultima edizione disponibile.

2. Tang A., Tam R., Cadrin-Chênevert A., et al. Canadian Association of Radiologists White Paper on Artificial Intelligence in Radiology. Canadian Association of Radiologists Journal, 2018.

Radioterapia, imaging quantitativo e IA

1. El Naqa I., Li R., Murphy M.J. (Eds.) Machine Learning in Radiation Oncology: Theory and Applications. Springer, Cham, 2015.

2. Thor M., Deasy J.O., Muren L.P. Artificial Intelligence and Machine Learning for Radiation Oncology. CRC Press, Boca Raton, FL, 2021.

3. Lee W.R., Marks L.B., Das S.K. Radiomics and Artificial Intelligence in Radiation Oncology. Elsevier, Amsterdam, 2023.

Articoli scientifici fondamentali

1. Lambin P., Rios-Velazquez E., Leijenaar R., et al. “Radiomics: Extracting More Information from Medical Images Using Advanced Feature Analysis.” European Journal of Cancer, 48(4), 2012, pp. 441-446.

2. Aerts H.J.W.L., Velazquez E.R., Leijenaar R.T.H., et al. “Decoding Tumour Phenotype by Noninvasive Imaging Using a Quantitative Radiomics Approach.” Nature Communications, 5, 2014.

3. Hosny A., Parmar C., Quackenbush J., Schwartz L.H., Aerts H.J.W.L. “Artificial Intelligence in Radiology.” Nature Reviews Cancer, 18(8), 2018, pp. 500-510.

4. Litjens G., Kooi T., Bejnordi B.E., et al. “A Survey on Deep Learning in Medical Image Analysis.” Medical Image Analysis, 42, 2017, pp. 60-88.

5. Esteva A., Robicquet A., Ramsundar B., et al. “A Guide to Deep Learning in Healthcare.” Nature Medicine, 25, 2019, pp. 24-29.

6. Sutton R.T., Pincock D., Baumgart D.C., et al. “An Overview of Clinical Decision Support Systems: Benefits, Risks, and Strategies for Success.” NPJ Digital Medicine, 3, 2020.

Linee guida, standard e documenti normativi

1. European Commission Artificial Intelligence Act (Regulation (EU) 2024/1689). Official Journal of the European Union, 2024.

2. European Society of Medical Imaging Informatics (EuSoMII) Recommendations on Artificial Intelligence in Medical Imaging. Ultima versione disponibile.

3. Image Biomarker Standardisation Initiative (IBSI) Reference Manual and Standardized Definitions for Radiomic Features. International collaboration, aggiornamenti periodici.

4. World Health Organization (WHO) Ethics and Governance of Artificial Intelligence for Health. Geneva: WHO, 2021.

Sitografia essenziale

• European Society of Radiology (ESR): https://www.myesr.org
• European Society for Radiotherapy and Oncology (ESTRO): https://www.estro.org
• Radiological Society of North America (RSNA): https://www.rsna.org
• The Cancer Imaging Archive (TCIA): https://www.cancerimagingarchive.net
• Image Biomarker Standardisation Initiative (IBSI): https://theibsi.github.io
• World Health Organization, Digital Health: https://www.who.int/health-topics/digital-health

Teaching methods

Interactive teaching activities based on the analysis of clinical cases and the application of practical algorithms in diagnostic imaging and radiation therapy.

Students with specific learning disorders (SLDs) and temporary or permanent disabilities are encouraged to contact the relevant University Support Service (<https://site.unibo.it/studenti-con-disabilita-e-dsa/it/per-studenti>) as early as possible in order to arrange appropriate accommodations and support measures.

Requests for accommodations must be submitted to the course instructor well in advance, and no later than 15 days prior to the examination date. The instructor will assess the suitability of the requested measures, taking into account the learning outcomes and educational objectives of the course.

Assessment methods

Student assessment will be based on the development and presentation of an individual or group analytical project focused on a topic addressed during the course.

Teaching tools

simulation lab, laptop, video projectors

Office hours

See the website of Gioele Santucci