Taught By

Dr. Anil Yadav

Dr. Anil Yadav is a Postdoctoral Research Fellow at the National Institutes of Health (NIH) and earned his Ph.D. in Biomedical Engineering from UCLA. His work sits at the intersection of deep learning and medical imaging, with experience spanning CT harmonization (including developing the CT-Norm toolkit), cancer detection, and whole-slide pathology workflows. He has led commercialization-focused projects through NIH’s Concept to Clinic program and built and deployed models in industry roles at Genentech and LungLife AI. Anil values collaboration and mentorship, and he cares deeply about translating research into practical solutions that improve healthcare.

Week by Week Curriculum

Week 1 - Project Initiation

Introduction to AI in medical imaging and disease detection
Overview of X-ray, CT, and MRI modalities
AI detection examples: Lung cancer and Brain tumor
Reflection on the future of AI in medicine

Week 2 - Planning Ideas

Master public datasets (TCIA) and imaging formats (DICOM/NIfTI)
Introduction to voxel processing and 3D visualization
Hands-on practice with ITK-SNAP and 3D Slicer
Analyze sample medical images

Week 3 - Project Definition

Convert medical images to numerical features using Pyradiomics
Explore feature distribution with boxplots and scatter plots
Introduction to supervised vs. unsupervised learning
Create data visualizations and correlation maps

Week 4 - Machine Learning Methodologies

Build supervised ML workflows with Orange Data Mining
Implement Logistic Regression and SVM models
Learn data splitting (K-Fold) and evaluation metrics
Test model reliability across different splits

Week 5 - Model Error & Limitations

Interpret prediction errors and confusion matrices
Analyze False Positives/Negatives and class imbalance
Discuss ethics and limitations in biomedical AI
Introduction to Deep Learning and CNNs

Week 6 - Conclusion

Final Research Symposium presentations
Synthesize research findings and methods
Peer review and feedback session
Present Capstone Report on AI possibilities and limitations

Biomedical Invention Lab: Medical Imaging & Diagnostic AI Research

In Partnership With