MSc Applied AI for Medical Imaging (Subject to Approval)

To apply for a course, you will need to complete and submit our online application form. For information and guidance, see: How to apply

Healthcare is being transformed by the combination of AI and medical imaging, enabling new ways of understanding how the body works, diagnosing disease and monitoring treatment. This course will equip you to drive innovation in this exciting field.

You will learn how to develop state-of-the-art methods for extracting information from medical images, built on a thorough understanding of how images are acquired using a variety of different modalities, such as MR, CT and PET. You will discover how images are used to inform models of the human body and in simulation as part of in silico (computer-based) imaging trials.

The curriculum integrates cutting-edge AI and machine learning (ML) with core principles of image science. Through hands-on training and strong theoretical foundations, you will learn to create novel imaging solutions, enhance diagnostic accuracy and support clinical decision-making.

This course will be of particular interest if you have a background in maths, physics or computer science and would like to apply your knowledge to medical imaging technologies.

A key strength of the course is its focus on practical application. Graduates will be prepared to translate pioneering research into real-world impact, applying AI and ML models to diverse imaging challenges, from general healthcare to personalised medicine and precision diagnostics.

By uniting the latest technology with an interdisciplinary approach, this MSc will train the next generation of AI-driven healthcare innovators.

This course will enable you to:

• Understand and apply the latest methods for extracting useful information from medical images, informed by knowledge of how different types of images are acquired and reconstructed.
• Design and implement new AI systems for extracting clinically relevant information from medical images.
• Apply quantitative modelling to medical image data to measure biophysical and physiological parameters and produce clinically useful biomarkers.
• Explore the role of imaging in computational modelling and virtual in silico trials.
• Understand the challenges of translating imaging AI into research and clinical practice, including safety, ethics, and responsible use.
• Develop transferable skills for multidisciplinary scientific and clinical environments.
  

All units in this course are delivered fully face-to-face. You'll have direct interaction with staff and gain hands-on experience in state-of-the-art facilities. A structured timetable with recommended pacing is in place for each unit, with clear deadlines for all assessments.

You are expected to attend all sessions, including lectures, tutorials and practicals. In the event of mitigating circumstances preventing attendance, it may be possible to repeat the affected unit in a subsequent year. You should ensure you are able to commit to full in-person participation before enrolling.

A variety of assessments are used across the course to ensure students can integrate knowledge, apply it to real-world scenarios and demonstrate understanding of each unit. These include essays, coding exercises, seminar and tutorial presentations, literature reviews, and online quizzes, with each designed to support both learning and evaluation.

Formative assessments, such as early-stage written assignments and coursework, provide feedback to guide progress, while summative assessments contribute to final grades.

Tutorials include elements of self-directed learning, enabling you to build independence, deepen understanding and apply knowledge more effectively. Group work is a key component of the course, reflecting the multidisciplinary nature of health data science and preparing you for professional teamwork. The extent of group assessment varies by unit, depending on the material and the type of applied work.

The final semester is devoted to an extended research project in a specific aspect of medical image analysis, enabling you to undertake unique work and contribute to the field. This is assessed via a written dissertation that should demonstrate independent critical thinking alongside the skills developed throughout the course.

The University of Manchester offers extensive library and online services to help you get the most out of your studies.

Graduates of this MSc will be well-equipped for diverse career pathways at the intersection of AI, imaging science and healthcare innovation.

You may decide to pursue a career in:

Academia: You may choose to continue your academic journey through PhD study, contributing to leading projects in medical imaging, digital health and personalised medicine. Alternatively, you can pursue a role as a research scientist within universities, hospitals or specialist research institutes, where expertise in imaging and AI is increasingly in demand.

Clinical and healthcare careers: You may work as an AI or imaging specialist within healthcare systems such as the NHS, or take on clinical scientist roles in radiology, pathology or digital diagnostics. Your training in advanced machine learning and decision-support systems will equip you to contribute directly to the development and deployment of AI-enabled clinical tools.

Industry: Our graduates are much sought after, taking up positions in health technology companies, biotech and pharmaceutical firms, and medical device manufacturers, where they may contribute to innovations in imaging systems, digital health platforms, or AI-powered diagnostics. Manchester’s strong links with industry and the NHS further enhance these prospects, providing you with valuable real-world experience during your studies.

Policy, consultancy or regulation: For those interested in shaping the broader landscape of healthcare, your understanding of AI ethics, safety, and clinical translation will enable you to contribute to digital transformation strategies, advise regulatory agencies, and ensure the responsible adoption of emerging technologies.