It is recommended to have passed or to have previous background in the subjects of Biomedical Image Processing, Machine Learning, and Deep Learning.

The 'Artificial Intelligence in Radiology and Microscopy' course explores the intersection of AI, radiology, and microscopy, teaching students to apply machine learning and computer vision techniques to medical image analysis. Covering topics such as segmentation, classification, and automated diagnosis, students will engage in hands-on exercises and interdisciplinary collaboration to gain practical skills and address the ethical implications of AI-driven medical imaging. The particular objectives of the course are: - To provide a comprehensive understanding of the principles, techniques, and applications of AI in the fields of radiology and microscopy. - To familiarize students with the latest advancements in AI technologies, such as deep learning, machine learning, and computer vision, and their role in improving the accuracy and efficiency of radiological and microscopy image analysis. - To develop proficiency in using AI tools and algorithms for the identification, segmentation, and classification of medical images, including X-rays, CT scans, MRI scans, and microscopic slides. - To equip students with the skills required to critically evaluate the strengths, limitations, and ethical implications of AI applications in radiology and microscopy. - To encourage interdisciplinary collaboration between computer scientists, engineers, radiologists, and pathologists, fostering a deeper understanding of the potential synergies between these fields. - To promote a culture of innovation and research in the application of AI to radiology and microscopy, inspiring students to contribute to the development of new algorithms, techniques, and solutions that address existing challenges and emerging needs in these fields. - To prepare students for careers in AI-driven medical imaging, providing them with the knowledge and skills needed to excel in research, industry, and clinical settings.

1. AI in Biomedical Imaging - Historical background - Recent developments - Impact of methods on research and clinical practice 2. Evaluation of AI-based methods - Public databases - Challenges 3. AI-based methods in microscopy - Noise reduction and preprocessing - Image synthesis - Segmentation - Object detection and tracking - Practical considerations and existing solutions 4. AI-based methods in radiology and radiotherapy - Segmentation - Image synthesis - Classification and automatic diagnosis - Treatment response prediction - Practical considerations and existing solutions 5. Ethical considerations, data protection and federated learning 6. Invited talks (Researchers and companies such as Siemens, Cella, Spotlab...)

AF3 Theoretical practical classes AF4 Laboratory practices AF6 Team work AF7 Student individual work AF8 Partial and final exams Activity code total hours number presencial hours number non-presencial hours number AF3 84 84 0 AF4 63 63 0 AF6 90 0 90 AF7 222 0 222 AF8 9 9 0 TOTAL MATERIA 468 156 312