Course catalogue doctoral education - HT21

  • Ansökan kan ske mellan 2021-04-15 och 2021-05-17
Application closed
Title Introduction to Artificial Intelligence in Cancer Precision Medicine
Course number 5313
Programme Tumörbiologi och onkologi (FoTO)
Language English
Credits 1.5
Date 2021-10-18 -- 2021-10-22
Responsible KI department Institutionen för medicinsk epidemiologi och biostatistik
Specific entry requirements
Purpose of the course This course aims to provide an introduction to artificial intelligence (AI) and its contemporary applications in cancer precision medicine, including key principles, challenges and routes to clinical translation. The course will also provide course participants with a starting point to understand how AI can be applied in their own research.

AI and machine learning (ML) hold the promise to provide decision support tools for clinical use that can contribute to increased quality and precision in routine diagnostics, and provide means to develop novel solutions that go beyond current diagnostic capabilities. The emergence of AI applications in cancer research at this point in time is driven by increased availability of large amounts of biological and medical data, together with emergence of new methodologies and growing compute resources. Typically, such models are trained on huge amounts of data, e.g. millions of images, and address a very specific problem. We have recently seen several examples of AI models performing on a level that is comparable to human experts, especially in the domain of medical image analysis, indicating a potential for AI both in research applications and in the clinic.
Intended learning outcomes After successfully completing this course you as a student are expected to be able to understand:
- Basic principles of machine learning (ML) and AI
- Key application domains of AI in cancer research
- How to critically assess AI-based medical research and AI-based tools
- Risks, opportunities and limitations of AI in the medical domain
- Ethical aspects of AI for medical purposes
Contents of the course This course provides a conceptual introduction to AI and ML, with application examples from medical research. The course includes basic theory and ideas, and aims to provide understanding of key concepts behind AI (e.g. deep learning) and ML, limitations and challenges associated with prediction models in the medical domain, and how to critically assess research studies and clinical evidence. In the domain of cancer diagnostics, primary examples include deep learning models to detect and classify cancer based on stained cell and tissue samples, and the assessment of radiology images to detect e.g. breast cancer. It will be explained why the development of successful AI models requires careful study design and validation strategies together with an understanding of both the strengths and limitations.

The different parts of the course are: Introduction to AI, ML and deep learning, supervised learning, study design, validation & cross-validation, measures of accuracy; assessing medical evidence; understanding risks and limitations; basic regulatory requirements for diagnostic products; and examples of applications of AI in medical research.
Teaching and learning activities The course is based around lectures, exercises, student presentations and discussions.
Compulsory elements All lectures and group sessions are considered mandatory. Missed events should be compensated for with a written report on the subject in accordance with instructions from the course organizer.
Examination The students will present and discuss an AI project design based on the course content and related to their research. Each student needs to show that all intended learning outcomes are achieved during the presentation and discussion of the project in order to pass the course.
Literature and other teaching material Current reference literature and group exercises will be provided during the course.
Number of students 8 - 25
Selection of students Selection will be based on 1) the relevance of the course syllabus for the applicant's doctoral project (according to written motivation), 2) start date of doctoral studies (priority given to earlier start date)
More information
Additional course leader Course directors: Mattias Rantalainen and Johan Lundin
Latest course evaluation Not available
Course responsible Mattias Rantalainen
Institutionen för medicinsk epidemiologi och biostatistik
Contact person -