Deep Learning for Medical Imaging Training Course

Name: Advanced Deep Learning for Medical Imaging Training Course
Availability: InStock

Build, test, and govern imaging deep-learning systems for classification, detection, segmentation, and clinical deployment.

At a glance

Duration: 1 Week
Format: Classroom
Cities: Cairo, Porto, Trabzon, Amsterdam, London, Abu Dhabi and more
Next session: 2 – 6 November 2026, Cairo
Average fee: 5,750 €

Home
Our Categories
Advanced Deep Learning for Medical Imaging Training Course

Download Brochure (PDF) Print PDF

Overview

Advanced Deep Learning for Medical Imaging Training Course is a one-week advanced course for imaging data scientists, radiology AI engineers, clinical informaticians, imaging researchers, and technical leads who leave with a Medical Imaging Model Evidence Dossier. Participants develop classification, detection, segmentation, and multimodal systems while addressing reference standards, external testing, calibration, uncertainty, interpretability, dataset shift, workflow integration, and monitoring. Agile Leaders Training Center presents medical imaging deep learning through reproducible experiments and clinical evidence.

Who Should Attend

Data science functions responsible for imaging datasets, model experiments, and performance analysis
Engineering functions responsible for model pipelines, deployment, integration, and monitoring
Clinical informatics functions responsible for intended use, workflow fit, and user requirements
Imaging research functions responsible for reference standards, testing, and reproducible reporting
Technical governance functions responsible for bias, privacy, risk, and lifecycle evidence

The course assumes participants already use Python-based machine learning and medical image data and leaves out introductory programming, diagnostic training, and product-specific regulatory advice.

Departments and Industries

The course supports departments and industries that develop, evaluate, deploy, or govern deep-learning systems for medical images.

Radiology, pathology, ophthalmology, and imaging research departments
Medical-device and clinical-software development teams
Hospital data science and clinical informatics functions
Biotechnology and pharmaceutical imaging-analysis groups
Digital health, research institute, and cloud engineering teams

Learning Objectives

By the end of this course, participants will be able to:

Build reproducible medical image preprocessing pipelines
Apply convolutional and transformer imaging architectures
Use reference standards for classification and segmentation
Analyze calibration, uncertainty, bias, and dataset shift
Evaluate internal, external, and clinical workflow tests
Prioritize deployment, monitoring, and lifecycle controls

Course Agenda

Day 1: Imaging Data and Experiment Design

Medical Image Cohort Definition Canvas
DICOM Preprocessing and Normalization Pipeline
Reference Standard Annotation Protocol
Patient-Level Dataset Split Method
Experiment Reproducibility Register

Day 2: Classification and Detection Models

Convolutional Neural Network Architecture Map
Vision Transformer Patch-Encoding Design
Transfer Learning Selection Matrix
Lesion Detection Anchor Strategy
Class-Imbalance Loss Function Guide

Day 3: Segmentation and Multimodal Learning

U-Net Segmentation Architecture
Volumetric Imaging Patch Pipeline
Segmentation Boundary Error Analysis
Image-Text Representation Alignment Model
Multimodal Fusion Design Canvas

Day 4: Evaluation and Clinical Readiness

CLAIM Evidence Reporting Checklist
Internal and External Testing Matrix
Calibration and Uncertainty Assessment
Subgroup Bias Evaluation Scorecard
Clinical Workflow Integration Risk Map

Day 5: Medical Imaging Model Practice

Exercise: Build an Imaging Preprocessing Pipeline
Exercise: Compare Classification Architectures
Exercise: Evaluate a Segmentation Error Profile
Exercise: Design a Drift Monitoring Dashboard
Capstone Exercise: Medical Imaging Model Evidence Dossier

Practical Exercises

The course uses suggested activities from radiology, pathology, ophthalmology, medical-device, and research settings.

Suggested activity: define an imaging cohort, normalize acquisitions, set patient-level splits, and document reference-standard provenance.
Suggested activity: compare convolutional and transformer models using task-appropriate classification and detection metrics.
Suggested activity: inspect segmentation failures, calibration, uncertainty, and subgroup performance across an external dataset.
Suggested activity: assemble an evidence dossier linking intended use, experiments, clinical tests, deployment, and monitoring controls.

FAQs

Who suits deep learning for medical imaging training, and what does it assume?

Deep learning for medical imaging training suits experienced imaging data, engineering, informatics, research, and governance functions. It assumes working Python machine-learning skills and familiarity with medical image data rather than introductory coding.

How does deep learning for medical imaging differ from general healthcare AI training?

Deep learning for medical imaging focuses on acquisition-aware preprocessing, reference standards, classification, detection, segmentation, volumetric data, image-text models, and imaging workflow tests. General healthcare AI training covers broader clinical and administrative data use.

Why are patient-level splits important in medical imaging deep learning?

Patient-level splits prevent images from the same patient appearing across training and test sets. They reduce leakage and provide a more credible estimate of performance on unseen patients.

What does external testing show for medical imaging models?

External testing evaluates performance on data from a separate institution, population, device mix, or acquisition process. It helps expose dataset shift and limits that internal testing may not reveal.

How should medical imaging deep-learning models be monitored?

Monitoring should track input characteristics, software and device versions, model outputs, user concordance, subgroup performance, calibration, errors, and drift. Defined thresholds guide investigation, updating, restriction, or retirement.

Conclusion

The course connects imaging data, architectures, reference standards, evaluation, clinical integration, and lifecycle monitoring. Participants take back a Medical Imaging Model Evidence Dossier. The dossier changes how their teams document experiments, challenge performance, assess workflow risks, and govern deployed imaging models.

credits: 5 credit per day

Course Mode: full-time

Provider: Agile Leaders Training Center

Download Brochure (PDF) Print PDF

Showing 21-40 of 75 events

Location	Dates	Duration	Mode	Price
Nice	Week 07, 2027 15 – 19 February 2027	1 Week	Onsite	€5,700
Vienna	Week 08, 2027 22 – 26 February 2027	1 Week	Onsite	€5,700
Madrid	Week 08, 2027 22 – 26 February 2027	1 Week	Onsite	€5,700
Doha	Week 08, 2027 28 February – 4 March 2027	1 Week	Onsite	€5,500
Paris	Week 10, 2027 8 – 12 March 2027	1 Week	Onsite	€5,700
Prague	Week 11, 2027 15 – 19 March 2027	1 Week	Onsite	€6,000
Barcelona	Week 12, 2027 22 – 26 March 2027	1 Week	Onsite	€5,700
Athens	Week 12, 2027 22 – 26 March 2027	1 Week	Onsite	€6,700
Phuket	Week 12, 2027 28 March – 1 April 2027	1 Week	Onsite	€6,000
Dubai	Week 13, 2027 29 March – 2 April 2027	1 Week	Onsite	€4,500
Tashkent	Week 13, 2027 4 – 8 April 2027	1 Week	Onsite	€4,500
Tbilisi	Week 15, 2027 12 – 16 April 2027	1 Week	Onsite	€5,000
Kuala Lumpur	Week 16, 2027 19 – 23 April 2027	1 Week	Onsite	€5,200
Madrid	Week 16, 2027 19 – 23 April 2027	1 Week	Onsite	€5,700
Abu Dhabi	Week 17, 2027 26 – 30 April 2027	1 Week	Onsite	€4,700
Manama	Week 17, 2027 2 – 6 May 2027	1 Week	Onsite	€4,700
Rome	Week 18, 2027 3 – 7 May 2027	1 Week	Onsite	€5,700
Amman	Week 18, 2027 9 – 13 May 2027	1 Week	Onsite	€4,100
Zoom	Week 19, 2027 10 – 14 May 2027	1 Week	Online	€1,500
Berlin	Week 20, 2027 17 – 21 May 2027	1 Week	Onsite	€5,700

Frequently asked questions

What does this course cover?

OverviewAdvanced Deep Learning for Medical Imaging Training Course is a one-week advanced course for imaging data scientists, radiology AI engineers, clinical informaticians, imaging researchers, and technical leads who leave with a Medical Imaging Model Evidence Dossier. Participants develop classification, detection, segmentation, and multimodal systems…

Are training dates available?

Yes. Available dates and destinations are listed in the course dates section on this page.

How can I register?

Choose an available date on this page and complete the registration form, or send a programme enquiry.

Can I download the course brochure?

Yes. Use the brochure download link provided on this page.

Deep Learning for Medical Imaging Training Course