Apply now
Master'sHealth, Biomechanics, Wearables & Operational Safety Applications open

Master’s in Clinical AI and Medical Imaging Engineering

Online master's programme of 1,900 hours in clinical AI and medical imaging engineering. 12 modules covering medical imaging for AI engineers, applied deep learning, data and annotation, classification and detection, segmentation, advanced models, explainability and robustness, clinical validation, hospital integration, regulation and governance, with an assigned technical tutor.

Duration1900 h
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

Take the controls.

Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Understand medical imaging and the radiology workflow.

02

Apply deep learning to classification, detection and segmentation.

03

Prepare and annotate imaging datasets rigorously.

04

Evaluate the robustness, explainability and bias of models.

05

Design multicentre clinical validations.

06

Integrate algorithms into PACS and RIS.

07

Comply with medical AI regulation and governance.

Profile

Who it's for

  • Medical imaging AI engineers developing classification, detection or segmentation models.
  • Radiology data scientists working with hospital imaging data.
  • AI clinical validation engineers designing reader studies and multicentre trials.
  • AI regulatory specialists preparing technical documentation for imaging software.
  • Medical computer vision researchers.
  • PACS integration engineers bringing algorithms into the radiology workflow.
  • Engineering or science graduates seeking to enter radiology and diagnostic imaging.
Standards & tools

What you'll work with

  • Regulation (EU) 2017/745 (EU Medical Device Regulation, MDR)
  • Regulation (EU) 2024/1689 (EU Artificial Intelligence Act)
  • DICOM PS3 (medical imaging format and communication)
  • IEC 62304 (medical device software life cycle)
  • ISO 14971 (risk management)
  • Regulation (EU) 2016/679 (GDPR, data protection)
  • CLAIM (checklist for AI in medical imaging)
  • IHE Radiology AI Results (integration profile for AI results)
  • PyTorch
  • MONAI
  • 3D Slicer
  • nnU-Net
  • Orthanc
Syllabus

12 modules · 1900 h

  1. 1.1Modalities and how they form images
  2. 1.2Basic radiological anatomy
  3. 1.3DICOM format and clinical metadata
  4. 1.4The radiology workflow
  5. 1.5Structured radiology reporting
  6. 1.6Digital pathology and whole-slide images
  7. 1.7Quality and variability between scanners
  8. 1.8Diagnostic errors in radiology
  9. 1.9Role of the radiologist alongside AI
  10. 1.10Case study: journey of a CT study
  1. 2.1Neural networks and backpropagation
  2. 2.2Convolutional networks and ResNet architectures
  3. 2.3Vision transformers applied to medical imaging
  4. 2.4Loss functions for medical imaging
  5. 2.5Optimisation and regularisation
  6. 2.6GPU training
  7. 2.7PyTorch and MONAI frameworks
  8. 2.8Reproducibility of experiments
  9. 2.9Tracking with MLflow
  10. 2.10Laboratory: lesion classifier with MONAI
  1. 3.1Public datasets such as LIDC and BraTS
  2. 3.2Data curation in the hospital
  3. 3.3Anonymisation of DICOM studies for research
  4. 3.4Expert annotation and consensus
  5. 3.5Labelling tools
  6. 3.6Inter-annotator variability
  7. 3.7Class imbalance and rare classes
  8. 3.8Patient- and centre-level data splits
  9. 3.9Dataset documentation
  10. 3.10Practical: nodule annotation protocol
  1. 4.1Chest X-ray classification
  2. 4.2Pulmonary nodule detection
  3. 4.3Fracture detection
  4. 4.4Mammography and screening
  5. 4.5Retinal imaging and diabetic retinopathy
  6. 4.6Object detection with YOLO and Faster R-CNN
  7. 4.7FROC metrics and sensitivity
  8. 4.8Clinical operating thresholds
  9. 4.9Comparison with human readers
  10. 4.10Laboratory: CT nodule detector
  1. 5.1U-Net architecture and variants
  2. 5.2Automatic configuration with the nnU-Net framework
  3. 5.3Brain tumour segmentation
  4. 5.4Organ segmentation for radiotherapy
  5. 5.5Volumetric quantification of lesions
  6. 5.6Dice and Hausdorff metrics
  7. 5.7Uncertainty in segmentation
  8. 5.8AI-assisted interactive correction
  9. 5.9Validation against manual measurements
  10. 5.10Practical: liver segmentation with nnU-Net
  1. 6.1Self-supervised learning with unlabelled images
  2. 6.2Foundation models in medical imaging
  3. 6.3Multimodal image-text models
  4. 6.4Report generation
  5. 6.5Generative models and synthetic data
  6. 6.6Federated learning across hospitals
  7. 6.7Domain adaptation
  8. 6.8Few-shot learning
  9. 6.9Risks of generative models
  10. 6.10Laboratory: fine-tuning a foundation model
  1. 7.1Grad-CAM maps and their interpretation
  2. 7.2Example-based explanations
  3. 7.3Shortcuts and spurious correlations
  4. 7.4Robustness to scanner changes
  5. 7.5Out-of-distribution data detection
  6. 7.6Confidence calibration
  7. 7.7Adversarial attacks on medical images
  8. 7.8Demographic and acquisition-device bias
  9. 7.9Model auditing
  10. 7.10Practical: bias audit of a classifier
  1. 8.1Levels of evidence for AI
  2. 8.2Multicentre external validation
  3. 8.3MRMC reader studies
  4. 8.4Prospective trials in clinical practice
  5. 8.5CLAIM, TRIPOD-AI and DECIDE-AI guidelines
  6. 8.6Impact on the workflow
  7. 8.7Cost-effectiveness assessment
  8. 8.8Real-world monitoring
  9. 8.9Scientific publication of AI results
  10. 8.10Case study: design of an MRMC study
  1. 9.1Integration with PACS and RIS
  2. 9.2Algorithm orchestration
  3. 9.3IHE AI Results profiles
  4. 9.4DICOM SR and segmentation objects
  5. 9.5On-premises or cloud infrastructure
  6. 9.6Latency and study prioritisation
  7. 9.7Interface for the radiologist
  8. 9.8Training radiologists to use the algorithm
  9. 9.9Monitoring in production
  10. 9.10Laboratory: deploying a model with a DICOM server
  1. 10.1Classification of imaging software under the MDR
  2. 10.2AI Act requirements for imaging
  3. 10.3Model card and training data documentation
  4. 10.4False-negative risks and ISO 14971
  5. 10.5IEC 62304 life cycle
  6. 10.6Predetermined change control plans
  7. 10.7FDA listings of AI-enabled devices
  8. 10.8Post-market performance surveillance
  9. 10.9Software cybersecurity
  10. 10.10Case study: technical file for an algorithm
  1. 11.1WHO ethical principles for AI
  2. 11.2Professional responsibility
  3. 11.3Consent and use of images
  4. 11.4AI committees in hospitals
  5. 11.5Transparency towards patients
  6. 11.6Equity and access
  7. 11.7Impact on radiology employment
  8. 11.8Data governance
  9. 11.9Sustainability of computing
  10. 11.10Workshop: hospital AI governance policy
  1. 12.1Clinical question and modality
  2. 12.2Dataset and annotation
  3. 12.3Model design
  4. 12.4Training and optimisation
  5. 12.5Technical evaluation with standard metrics
  6. 12.6Explainability and bias
  7. 12.7Multicentre validation plan
  8. 12.8Classification and CE marking pathway
  9. 12.9Master's Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

100% online training on the SEIUM campus, with downloadable materials, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so the programme is compatible with work.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is PyTorch, MONAI, 3D Slicer, nnU-Net and Orthanc, in free, academic or evaluation versions. Practical work is based on real procedures: training models on public imaging datasets, simulated reader studies and deployment of algorithms on DICOM servers. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: Regulation (EU) 2017/745 on medical devices, Regulation (EU) 2024/1689 on artificial intelligence, DICOM PS3, IEC 62304, ISO 14971, Regulation (EU) 2016/679 (GDPR), CLAIM guideline, IHE Radiology AI Results.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of the MDR, the EU AI Act and DICOM PS3 applied to real cases, not as a theoretical annex.
Industry software:PyTorch, MONAI, 3D Slicer, nnU-Net and Orthanc, in free, academic or evaluation versions.
Master's Thesis with defence:a medical imaging AI model, from clinical question and annotated dataset to training, technical evaluation, explainability and bias analysis, multicentre validation plan and CE marking pathway, defended before a panel.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Dataset and annotation
Define an annotation protocol for nodules and prepare a patient-level data split.
Detection and segmentation
Train a CT nodule detector and segment the liver with nnU-Net.
Bias and robustness audit
Audit a classifier for bias, calibration and out-of-distribution behaviour.
Validation and deployment
Design an MRMC reader study and deploy a model on a DICOM server.
Master's Thesis
A medical imaging AI model with technical evaluation, multicentre validation plan and CE marking pathway, defended before a panel.
Career opportunities

Where this takes you

Medical imaging AI engineerRadiology data scientistAI clinical validation engineerAI regulatory specialistMedical computer vision researcherPACS integration engineer
Admissions & scholarships

Requirements

  • University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
  • Internet connection and a computer capable of running the programme software.
  • English sufficient to read technical standards.

Ready to start?

Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with PyTorch, MONAI, 3D Slicer, nnU-Net and Orthanc, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.

A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.

Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.

A university degree in engineering, science or architecture (or equivalent professional experience), a computer able to run the software, and English sufficient to read technical standards.

Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.

Keep exploring

Related programmes

See all in Health, Biomechanics, Wearables & Operational Safety
Master's8,850 $

Master’s in Industrial Hygiene and Exposure Engineering

Online master's programme of 1,900 hours in Industrial Hygiene and Exposure Engineering, with 12 modules covering hygiene fundamentals, the regulatory framework, measurement strategies, chemical, physical and…

1900 hOnlineHealth, Biomechanics, Wearables & Operational Safety
Master's7,730 $

Master’s in Process Safety Engineering

Online master's programme of 1,900 hours in Process Safety Engineering, with 12 modules covering major accidents, hazardous substances and reactions, HAZOP, LOPA, safety instrumented systems, pressure…

1900 hOnlineHealth, Biomechanics, Wearables & Operational Safety
Master's7,730 $

Master’s in Ethics, Privacy and Security Engineering in Digital Health

Online master's programme of 1,900 hours in ethics, privacy and security engineering in digital health. 12 modules covering digital health ethics, health data protection, privacy by…

1900 hOnlineHealth, Biomechanics, Wearables & Operational Safety
Master’s in Clinical AI and Medical Imaging EngineeringEnrol
Related programmes

More in Health, Biomechanics, Wearables & Operational Safety

Master’s in Movement Neuromechanics and Musculoskeletal Modelling EngineeringView programme →Master’s in Special Transport Environments EngineeringView programme →Master’s in Fatigue, Shift Work and Sleep Management Engineering in OperationsView programme →Master’s in Thermal Comfort EngineeringView programme →Master’s in Regulatory Engineering and Regulatory AffairsView programme →Master’s in Quality, Clinical Trials and Clinical Evaluation EngineeringView programme →

All Health, Biomechanics, Wearables & Operational Safety programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.