Programme Parameters
Advanced Postgrad
8 Weeks (80 Hrs)
Online (e-LMS)
• Prior working knowledge of the field and comfort with core tools and quantitative reasoning.
• A laptop or desktop with a stable internet connection.
• Willingness to complete assignments and the capstone project.
About This Course
AI in Medical Imaging and Diagnostics focuses on one of the most successful and scrutinised applications of machine learning in medicine. You learn how deep learning models read medical images — X-ray, CT, MRI and digital pathology — to classify findings, detect abnormalities and segment structures. The course covers the practical realities that separate a demo from a clinical tool: annotated data, handling modality and scanner variation, robust validation, and interpretability for clinician trust. Regulation and safety run throughout. You finish able to reason about building and validating a medical-imaging AI model. A verified e-Certificate of competency and e-Marksheet from the Deep Science & Technology Consortium.
🎯 Program Aim
This course applies AI to medical imaging — deep learning for classification, detection and segmentation across radiology, pathology and other modalities, with clinical validation.
📋 Course Objectives
1. Apply deep learning to classify and detect in medical images.
2. Segment anatomical structures and lesions.
3. Handle modality, scanner and annotation challenges.
4. Validate models to a clinical standard.
5. Address interpretability, regulation and safety.
👥 Who Should Enroll?
• Radiology, pathology and clinical professionals
• Medical-imaging data scientists
• Health-tech and medical-device teams
• Students of medical AI
🚀 Key Learning Outcomes
• The ability to reason about medical-imaging AI.
• An imaging-analysis project.
• A clinically grounded, safety-first approach.
• A verified e-Certificate of competency and e-Marksheet from the Deep Science & Technology Consortium.
💎 What You'll Gain
Live & Recorded Sessions
Lifetime access to class recordingse-Certificate on Completion
Cryptographically verified credentialPost-Programme Support
Direct access to mentors & councilHands-On Experience
Notebooks, real-world code & datasetsCurriculum Outline
Modalities and What Their Data Means
• Acquisition physics of CT, MR, ultrasound and radiography, and the artefacts each produces
• DICOM structure, windowing, spacing and the metadata models silently depend on
• Reconstruction and dose settings as hidden covariates across sites
Datasets, Labels and Ground Truth
• Annotation protocols and inter-reader variability as the real performance ceiling
• Weak labels from reports, and the noise that introduces
• Patient-level splitting to prevent the same patient appearing in train and test
Detection, Segmentation and Classification
• U-Net style segmentation and nnU-Net as a strong default baseline
• Detection for lesions and nodules, and evaluation with FROC rather than accuracy
• Transfer learning from natural images and where it stops helping
Reading Performance Like a Radiologist
• Sensitivity, specificity and the effect of disease prevalence on predictive value
• Reader studies, standalone versus assisted performance
• External validation and the scanner-generalisation failures that recur in the literature
Regulation and Radiology Workflow
• Regulatory classification and the evidence expected for imaging AI
• PACS integration, worklist prioritisation and turnaround-time effects
• Monitoring after deployment as scanners, protocols and case mix change
Technical Specifications
| Parameter | Requirement |
|---|---|
| Covered Tool / Platform | Python |
| Covered Tool / Platform | SPSS |
| Covered Tool / Platform | DICOM Viewers |
| Covered Tool / Platform | EHR Systems |
| Covered Tool / Platform | TensorFlow |
| Covered Tool / Platform | PubMed |
Frequently Asked Questions
Scholar Feedback & Reviews
Based on 0 scholar submissions
Rating Breakdown
No verified reviews published yet. Be the first to share your academic experience.
Leave Scholar Feedback
Your rating will help prospective scholars. Ratings below 3 stars are routed privately to the faculty mentor for immediate response.
