Caricamento in corso...
Multiscale and Multimodal Biocybernetics
01DWHMV
A.A. 2024/25
Course Language
Inglese
Degree programme(s)
Master of science-level of the Bologna process in Ingegneria Biomedica - Torino
Course structure
| Teaching | Hours |
|---|---|
| Lezioni | 39 |
| Esercitazioni in laboratorio | 21 |
Lecturers
| Teacher | Status | SSD | h.Les | h.Ex | h.Lab | h.Tut | Years teaching |
|---|---|---|---|---|---|---|---|
| Salvi Massimo | Collaboratore Esterno | 15 | 0 | 0 | 0 | 2 |
Co-lectures
Context
| SSD | CFU | Activities | Area context | ING-INF/06 | 6 | B - Caratterizzanti | Ingegneria biomedica |
|---|
2024/25
The most common pathologies with a high morbidity in developed countries (e.g., cancer, cardiovascular diseases, lung infections) are very complex diseases that often involve more than one biological system. The continuous progress of medical signal and image acquisition technologies has allowed the development of new disciplines for the study of these diseases. An innovative approach that aims to understand the behavior and evolution of these pathologies within the complex biological mechanisms is biomedical cybernetics, or biocybernetics.
In particular, biocybernetics refers to the technology-abstracted study of biological and biomedical systems and signals: systems theory and modelling; data, signal and image acquisition, analysis and processing; study and extraction of information, predictive patterns and artificial intelligence; decision-making processes; design and development of methods and devices to achieve these goals; and the application of digital technologies to medicine and wellbeing.
In this course, focus will be put on the principles, technologies, instruments and methods for computational analysis, increasing the amount of informative content, and the interpretation of biological data in terms of biomedical signals and images. Throughout the course, numerous complex pathologies that have a large impact on patients will be presented, analyzed and investigated. The main technical solutions that are used today to (a) understand and model the pathology and its evolution, (b) screen subjects and do preventive medicine, and (c) personalize the diagnosis and treatment will be presented and implemented.
The most common pathologies with a high morbidity in developed countries (e.g., cancer, cardiovascular diseases, lung infections) are very complex diseases that often involve more than one biological system. The continuous progress of medical signal and image acquisition technologies has allowed the development of new disciplines for the study of these diseases. An innovative approach that aims to understand the behavior and evolution of these pathologies within the complex biological mechanisms is biomedical cybernetics, or biocybernetics.
Biocybernetics has a wide range of applications in healthcare, and is increasingly being used to improve our understanding and treatment of complex medical conditions. Specifically, biocybernetics refers to the technology-oriented study of biological systems: systems theory and modelling; data, signal and image acquisition, analysis and processing; study and extraction of information, predictive patterns and artificial intelligence; decision-making processes; and the application of digital technologies to medicine and wellbeing.
In this course, we will focus on the principles, technologies, instruments and methods for computational analysis to increase the informative content and interpretation of biological data in terms of biomedical signals and images. We will also explore different complex pathologies that have a significant impact on patients by presenting, analyzing, and investigating them. Throughout the course, we will cover the main technical solutions used in healthcare today (artificial intelligence, deep learning, predictive models). These include understanding and modeling the pathology and its evolution, screening subjects for preventive medicine, and personalizing diagnosis and treatment.
At the end of the course, the students will know:
- the principles of biocybernetics and its application in multiscale and multimodal contexts.
- the context of numerous complex pathologies together with the biological mechanisms that are involved in the progression and evolution of the pathology
- the techniques that are mainly used to identify a specific pathology, to understand its conduct and to employ personalized medicine
At the end of the course, the students will have gained the following skills:
- given a specific biological system or pathology, the ability to identify the possible techniques that can be used to describe and analyze the relative biological context
- the ability to implement numerous strategies based on artificial intelligence with the aim to identify, understand and characterize the specific pathology that is analyzed in a multiscale and multimodal way
By the end of the course, students will have gained knowledge in the following areas:
• The principles of biocybernetics and its application in multiscale and multimodal contexts.
• The context of numerous complex pathologies, including the biological mechanisms involved in their progression and evolution
• The techniques mainly used to identify a specific pathology, understand its conduct, and employ personalized medicine
In addition, students will have gained the following skills:
• The ability to identify possible techniques for describing and analyzing a specific biological system or pathology
• The ability to implement numerous strategies based on artificial intelligence to identify, understand, and characterize a specific pathology in a multiscale and multimodal way
Overall, this course will equip students with the knowledge and skills necessary to apply biocybernetics principles and techniques to analyze and interpret biological data, and to understand the latest techniques used in personalized medicine.
The students should have a good knowledge of the subjects that are taught in the following courses: Biomedical signal processing, Artificial intelligence in medicine.
The students should have a good knowledge of the subjects that are taught in the following courses: Biomedical signal processing, Artificial intelligence in medicine.
- Course introduction and fundamental principles of biocybernetics (3h)
- Machine learning and Deep learning applied to biocybernetics (1.5h)
- Biomedical signals (EEG, ECG; etc.) and possible applications in biocybernetics (4.5h)
- Review of machine learning and deep learning techniques (classification, detection, segmentation tasks) (3h)
- Technologies at the line between biomedical signals and images, beamforming (3h)
- Biomedical optical imaging methods, basic concepts and applications to vasculature studies (3h)
- Focus on cancer: analysis and extraction of quantitative parameters for characterizing tumor lesions (3h)
- Focus on lung (viral infections, coronavirus): Analysis of diagnostic CT images in a 3D context, classification and development of predictive models of symptomatology (3h)
- Focus on lung (cancer): digital pathology images, segmentations, extension to whole slide imaging (WSI) (3h)
- Generative Adversarial Networks (GAN) and potential applications to Biocybernetics (1.5h)
- Concluding remarks, statistics, etc. (1.5h)
Intro
• Course introduction and fundamental principles of biocybernetics [3h]
Technical part & AI
• Review of statistical and Bayesian methods [1.5h]
• Artificial Intelligence applied to biocybernetics [4.5h]
• Deep Generative models and potential applications to Biocybernetics [1.5h]
• Explainable AI and uncertainty estimation of complex systems [1.5h]
Applications
• Biomedical signals (EEG, ECG; etc.) and possible applications in biocybernetics [4.5h]
• Technologies at the line between biomedical signals and images, beamforming [3h]
• Biomedical optical imaging methods, basic concepts and applications to vasculature studies [4.5h]
• Focus on cancer: analysis and extraction of quantitative parameters for characterizing tumor lesions [4.5h]
• Focus on lung (viral infections, coronavirus): Analysis of diagnostic CT images in a 3D context, image classification [3h]
• Focus on lung (cancer): digital pathology, image segmentations, extension to whole slide imaging [3h]
Future trends
• Predictive models based on statistics and AI [3h]
Conclusions
• Concluding remarks, etc. [1.5h]
The course will be divided into 30 hours of lectures and 30 hours of lab work that will be done in groups of 3-4 people. It is not mandatory to participate in the lab work, but it is strongly advised as specific techniques and methods analyzed during the lab work are integral to the exam. During the lab work, the students will work on specific problems that the lecturer will propose and they will develop projects that are linked to the subjects taught in the course. Moreover, part of the lab work will be dedicated to an in-depth literature research that the lecturer will propose on purely technical aspects of biocybernetics and on clinical/implementation aspects.
Based on the number of students and space of the lab, a visit to some of the labs of the PolitoBIOMed Lab will be organized, if possible.
The course will be divided into 39 hours of lectures and 21 hours of lab work that will be done in groups of 3-4 people. It is not mandatory to participate in the lab work, but it is strongly advised as specific techniques and methods analyzed during the lab work are integral to the exam. During the lab work, the students will work on specific problems that the lecturer will propose and they will develop projects that are linked to the subjects taught in the course. Moreover, part of the lab work will be dedicated to an in-depth literature research that the lecturer will propose on purely technical aspects of biocybernetics and on clinical/implementation aspects.
Based on the number of students and space of the lab, a visit to some of the labs of the PolitoBIOMed Lab will be organized, if possible.
Slides provided by the lecturers and recently published scientific papers on techniques described in class.
Slides provided by the lecturers and recently published scientific papers on techniques described in class.
Dispense; Esercitazioni di laboratorio; Materiale multimediale ;
Lecture notes; Lab exercises; Multimedia materials;
Modalità di esame: Prova orale obbligatoria; Elaborato progettuale in gruppo;
Exam: Compulsory oral exam; Group project;
...
The exam consists in the preparation of a short paper of maximum 4 pages (double column format, as often required for bioengineering international conferences) on a subject that the lecturer will assign. The preparation of the short paper will be done in groups, ideally the same as the lab groups. If a student decides to not participate in the labs, they will automatically be assigned to a group for the exam. The short paper will undergo a review process (“peer review” – similar to the submission of a paper to a journal) and corrected by the exam committee. The short paper will be graded up to 22 points.
Individual oral discussions on specific subjects of the short paper will follow, also potentially including in-depth analyses of theoretical aspects of the entire course. The oral exam will be evaluated up to 10 points.
The final grade is made up of the sum of the two grades. If a student obtains a sum greater than 30, the exam is passed with honors. The two grades must be obtained in the same exam session.
Gli studenti e le studentesse con disabilità o con Disturbi Specifici di Apprendimento (DSA), oltre alla segnalazione tramite procedura informatizzata, sono invitati a comunicare anche direttamente al/la docente titolare dell'insegnamento, con un preavviso non inferiore ad una settimana dall'avvio della sessione d'esame, gli strumenti compensativi concordati con l'Unità Special Needs, al fine di permettere al/la docente la declinazione più idonea in riferimento alla specifica tipologia di esame.
Exam: Compulsory oral exam; Group project;
The exam consists in the preparation of a short paper of maximum 4 pages (double column format, as often required for bioengineering international conferences) on a subject that the lecturer will assign. The preparation of the short paper will be done in groups, ideally the same as the lab groups. If a student decides to not participate in the labs, they will automatically be assigned to a group for the exam. The short paper will undergo a review process (“peer review” – similar to the submission of a paper to a journal) and corrected by the exam committee. The short paper will be graded up to 22 points.
Individual oral discussions on specific subjects of the short paper will follow, also potentially including in-depth analyses of theoretical aspects of the entire course. The oral exam will be evaluated up to 10 points.
The final grade is made up of the sum of the two grades. If a student obtains a sum greater than 30, the exam is passed with honors. The two grades must be obtained in the same exam session.
In addition to the message sent by the online system, students with disabilities or Specific Learning Disorders (SLD) are invited to directly inform the professor in charge of the course about the special arrangements for the exam that have been agreed with the Special Needs Unit. The professor has to be informed at least one week before the beginning of the examination session in order to provide students with the most suitable arrangements for each specific type of exam.