Postgraduate Diploma in Radiomics and Risk Models
Online 800 h Postgraduate Diploma in radiomics and risk models. 8 modules with IBSI (Image Biomarker Standardisation Initiative), TRIPOD+AI (reporting of predictive models) and PyRadiomics. Assigned tutor and open enrolment.
Postgraduate Diploma in Radiomics and Risk Models — studying from the United Kingdom
The United Kingdom has a strong medical technology and healthcare engineering base, with research in biomechanics, medical devices and wearables across universities and companies in London, Oxford, Leeds and Glasgow. The NHS, medical device manufacturers and digital health firms require engineers who understand clinical requirements and regulatory compliance. Operational safety in workplaces, transport and sport drives work on human factors and ergonomics. The Medicines and Healthcare products Regulatory Agency regulates medical devices, and the Health and Safety Executive oversees workplace safety.
Fees for the United Kingdom: £1,070 (Pound sterling), with instalments and employer sponsorship available.
Relevant bodies in the United Kingdom
Typical roles
Questions from the United Kingdom
Will this qualification be recognised by UK professional bodies such as the Institution of Engineering and Technology or the Institution of Mechanical Engineers?
SEIUM's qualifications are private qualifications, not official state degrees, and they are not accredited by any national body. Professional bodies such as the IET or IMechE decide whether to accept training for membership, usually through their own assessment of your experience and learning. Chartered Engineer status is awarded by the Engineering Council via licensed professional engineering institutions. Check directly with the relevant body before you enrol.
Will UK employers in healthcare technology, wearables or occupational safety value this training on a CV?
Employers decide for themselves how much weight to give a private qualification. Many value evidence of specialist skills, such as a completed final project and demonstrable work on biomechanics or wearable sensor systems, more than the name of the provider. Recognition is not guaranteed, so review relevant job adverts and ask prospective employers how they view online private training before committing.
Can I complete this programme alongside a full-time job in the UK, and does my employer need to fund it?
The programmes are 100% online and taught in English, so you can study at your own pace around work and across UK time zones. Master's programmes total 1,900 hours, postgraduate diplomas 800 hours and specialist courses 300 hours. Fees can be paid in instalments, and employer sponsorship is possible, though you should agree arrangements with your employer in advance.
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.
What you will be able to do
Describe quantitative medical imaging and its sources of variability.
Segment regions of interest in a reproducible way.
Extract IBSI-compliant radiomic features.
Harmonise multicentre data and assess its robustness.
Select variables and train predictive models while avoiding overfitting.
Build risk and survival models.
Validate radiomic models and assess their clinical utility.
Who it's for
- Data scientist in medical imaging who wants to specialise in Radiomics and Risk Models.
- Medical physicist who wants to specialise in Radiomics and Risk Models.
- Radiomics researcher who wants to specialise in Radiomics and Risk Models.
- Biostatistician who wants to specialise in Radiomics and Risk Models.
- Clinical AI engineer who wants to specialise in Radiomics and Risk Models.
- Research radiologist who wants to specialise in Radiomics and Risk Models.
- Engineering or science graduates looking to enter hospitals.
What you'll work with
- IBSI (Image Biomarker Standardisation Initiative)
- TRIPOD+AI (reporting of predictive models)
- DICOM
- Radiomics Quality Score (RQS)
- Regulation (EU) 2024/1689 (Artificial Intelligence)
- Regulation (EU) 2017/745 (MDR)
8 modules · 800 h
1.1CT physics: Hounsfield units and reconstruction1.2MRI sequences and intensity heterogeneity1.3PET and standardised uptake values (SUV)1.4DICOM format and relevant metadata1.5Effect of acquisition parameters on measurements1.6Calibration phantoms and quality control1.7Preprocessing: resampling, normalisation and discretisation1.8Public repositories: TCIA and LIDC-IDRI1.9Anonymisation of imaging studies1.10Laboratory: reading and resampling DICOM series with Python
2.1Manual segmentation and inter-observer variability2.2Semi-automatic methods: thresholding and region growing2.3Deep segmentation with U-Net and nnU-Net2.4Overlap metrics: Dice and Hausdorff distance2.5Mask formats: RTSTRUCT, NIfTI and DICOM SEG2.6Tools: 3D Slicer and ITK-SNAP2.7Peritumoural and habitat segmentation2.8Effect of segmentation on feature stability2.9Radiological review of contours2.10Practical: segmentation of lung nodules in 3D Slicer
3.1Three-dimensional shape and size features3.2First-order histogram statistics3.3GLCM, GLRLM and GLSZM texture matrices3.4NGTDM and GLDM matrices3.5Wavelet and Laplacian of Gaussian filters3.6Standardisation under the IBSI initiative3.7PyRadiomics library and its configuration3.8Delta-radiomic features in longitudinal studies3.9Deep features versus handcrafted features3.10Laboratory: extraction with PyRadiomics on a public cohort
4.1Test-retest reproducibility of features4.2Intraclass correlation coefficient and agreement4.3Scanner and acquisition protocol effects4.4Statistical harmonisation with ComBat4.5Image and mask perturbations4.6Filtering unstable features4.7Radiomic quality according to the RQS score4.8CLEAR guideline for reporting radiomic studies4.9Multicentre studies and batch bias4.10Practical: stability analysis with contour perturbations
5.1High-dimensionality and small-sample problem5.2Reduction by correlation and redundancy5.3LASSO regression and elastic net5.4Random forest and gradient boosting5.5Support vector machines5.6Nested cross-validation and data leakage5.7Class imbalance and resampling5.8Integration with clinical and genomic variables5.9Interpretability with SHAP values5.10Workshop: LASSO model for malignancy prediction
6.1Survival analysis and Kaplan-Meier curves6.2Cox regression and the proportional hazards assumption6.3Random survival forests and DeepSurv6.4Concordance index and time-dependent AUC6.5Calibration and calibration plots6.6Decision curves and net benefit6.7Radiomic-clinical nomograms6.8Stratification into risk groups6.9TRIPOD+AI guidelines for prediction models6.10Case study: prognostic radiomic signature in lung cancer
7.1Internal, temporal and external validation7.2Risk of bias with PROBAST7.3Data drift after deployment7.4Integration into PACS and radiological workflow7.5MDR requirements for diagnostic software7.6EU AI Regulation and high-risk systems7.7Explainability for clinicians and patients7.8Impact assessment on clinical decision-making7.9Publishing reproducible code and models7.10Case study: external validation plan for a published model
8.1Clinical question and definition of objective8.2Cohort selection and curation8.3Segmentation protocol and quality control8.4Feature extraction and harmonisation8.5Variable selection and training8.6Assessment of discrimination and calibration8.7External validation and interpretation8.8Report in line with CLEAR and TRIPOD+AI8.9Dissertation and presentation8.10Final review with the tutor
How you'll learn
100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetable: students progress at their own pace within the intake, which makes it possible to combine study with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is PyRadiomics, 3D Slicer, LIFEx, R (survival), scikit-learn, in free, academic or evaluation versions. Studies are examined using real radiomic extraction procedures in retrospective cohorts, test-retest reproducibility studies and multicentre external validation. Assessment is continuous, module by module, plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Describe quantitative medical imaging and its sources of variability.
Segment regions of interest in a reproducible way.
Extract IBSI-compliant radiomic features.
Harmonise multicentre data and assess its robustness.
Select variables and train predictive models while avoiding overfitting.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is required.
- Internet connection and a computer capable of running the programme's software.
- A level of Spanish sufficient to follow technical regulatory texts.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme comprises 800 hours in total, spread over 6 to 8 months. That is between 10 and 15 hours a week on average, compatible with a full-time job.
You work with PyRadiomics, 3D Slicer, LIFEx, R (survival), scikit-learn. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
An own-award diploma from the SEIUM Institute upon passing continuous assessment and the integrative project. This is in-house training, not an official Ministry qualification.
Yes. Modules passed in a course or Postgraduate Diploma in the same area are credited towards the advanced programme. Check the credit transfer policy when you enrol.
Related programmes
Postgraduate Diploma in PSM Performance Metrics and Compliance
Online 800-hour Postgraduate Diploma in PSM Performance Metrics and Compliance. 8 modules covering OSHA 29 CFR 1910.119 (Process Safety Management), API RP 754 (process safety indicators)…
Postgraduate Diploma in MCU/NPU Inference (TFLite/ONNX/TensorRT)
Online 800 h Postgraduate Diploma in MCU/NPU inference (TFLite/ONNX/TensorRT). 8 modules covering ISO/PAS 8800 (artificial intelligence in road vehicles), ISO 26262 (functional safety in automotive) and…
Postgraduate Diploma in Risk Assessment and Operational Controls
Online 800-hour Postgraduate Diploma in Risk Assessment and Operational Controls. 8 modules covering ISO 31000 (risk management), IEC 31010 (risk assessment techniques) and advanced Excel. Assigned…
More in Health, Biomechanics, Wearables & Operational Safety
All Health, Biomechanics, Wearables & Operational Safety programmes → · How to apply · Fees & financing · Scholarships