Course Schedule

Inauguration

Inaugural Lecture: Introduction to AI in Healthcare

Introduction to AI in Healthcare

Introduction to Bioinformatics and Multiomics

• Overview of genomics, transcriptomics (RNA-seq), proteomics, metabolomics
• Differential gene expression (DEG) analysis: RNA-seq & microarray
• Pathway and gene ontology (GO) analysis

Introduction to Bioinformatics and Multiomics

• GEO data retrieval and alignment using GeoR
• GO and KEGG pathway enrichment

Introduction to Bioinformatics and Multiomics

• Protein-protein interaction (PPI) networks
• Hub gene identification
• Multi-omics integration strategies

Introduction to Bioinformatics and Multiomics

• Cytoscape for hub gene extraction (via STRING)
• Volcano and heatmap plotting

Introduction to Bioinformatics and Multiomics

• Survival analysis
• Prognostic biomarker discovery

• Kaplan-Meier plot generation for survival analysis

Machine Learning Foundations in Medical Sciences

Overview:

• Supervised learning
• Unsupervised learning
• Reinforcement learning

Case study with real-time healthcare use cases

Machine Learning Foundations in Medical Sciences

• Feature engineering
• Missing data imputation
• Handling imbalanced datasets (SMOTE)

Machine Learning Foundations in Medical Sciences

• Introduction to Neural Networks
• Deep Learning

• Model building using Scikit-learn
• TensorFlow
• PyTorch

Machine Learning Foundations in Medical Sciences

Evaluation Metrics:

• ROC
• AUC
• PR Curve
• Confusion Matrix
• F1-Score
• Calibration

Machine Learning Foundations in Medical Sciences

• Classification of cancer subtypes using TCGA dataset
• Model evaluation

Medical Imaging and Data Handling

Imaging modalities such as :

• Ultra sound
• X - Ray
• Histopathology
• Mammography

Image formats and standards:

• DICOM
• PNG
• TIFF

• Image loading
• Metadata inspection (DICOM tags)

Annotation tools

• ITK-SNAP
• LabelMe

PACS systems and metadata extraction

• Manual annotation exercise
• Image augmentation
• Denoising
• Resizing
• Normalization

Deep Learning and CNNs for Medical Image Analysis

CNN building blocks:

• Convolution
• Pooling
• Padding
• Filters

• Image classification using CNNs

Deep Learning and CNNs for Medical Image Analysis

• 2D vs 3D CNNs for volumetric data (MRI / CT)
• U-Net and variants for segmentation

• Medical image segmentation using U-Net

AI in Radiology (MRI/ CT)

• Classification
• Segmentation
• Anomaly detection

AI in Pathology

• Digital histopathology
• Disease classification

Transfer learning:

• ResNet
• EfficientNet

Real-world use cases:

• Diabetic retinopathy
• Skin lesion classification
• Tumor segmentation

AI in Drug Discovery and Cheminformatics

• Introduction to molecular docking
• Structure-based drug discovery

AI in Drug Discovery and Cheminformatics

• Ligand-based drug discovery
• Introduction to scoring functions

AI in Drug Discovery and Cheminformatics

• Molecular docking
• Scoring functions

• RDKit
• DeepChem
• Compound featurization

AI in Drug Discovery and Cheminformatics

• ADMET prediction using AI

• Protein-ligand docking demo

AI in Drug Discovery and Cheminformatics

• Virtual screening
• Compound ranking

• AI models for drug-target interaction prediction

Deep generative models in drug design

• Variational Autoencoders (VAEs)
• Generative Adversarial Networks (GANs)

Introduction to GSEA and ULCAN and lab session

Explanable AI in Healthcare

NLP in Healthcare

NLP in Healthcare

Ethics, Regulation and Future of AI in Medicine

Ethics, Regulation and Future of AI in Medicine