Lecturer	Ana Namburete
Degrees	Schedule B1 (CS&P) — Computer Science and Philosophy Schedule A2 — Computer Science Schedule B1 — Computer Science Schedule A2(M&CS) — Mathematics and Computer Science Schedule B1(M&CS) — Mathematics and Computer Science
Term	Hilary Term 2026  (16 lectures)

Overview

Deep learning is reshaping how we acquire, interpret, and act on medical data: from 3D imaging and waveform streams to clinical text and electronic records. This course builds a practical foundation in modern neural networks while grounding every concept in the realities of healthcare data, ethics, and deployment. We begin with the unique challenges of medical data and core training principles; progress to model families for images, sequences, and text without focusing on specific architectures; and close with advanced topics such as transfer and self-supervised representation learning, contrastive objectives, generative modeling, domain-specific evaluation and losses, explainability and fairness, and privacy-preserving learning. Assessment is via a practical take-home mini-project using real medical data with an emphasis on clear, reproducible model development.

Learning outcomes

The goal of this course is to provide an intuition for adapting deep learning algorithms to healthcare data and understanding the subtleties in applying these methods to real-world data. We will also discuss open challenges for future research.

In this course, students will:

• Broaden knowledge and fluency about state-of-art deep learning algorithms.
• Develop practical ability to design and train neural networks, and understand how to adapt models to diverse types of healthcare data.
• Understand practical considerations and domain-specific challenges associated with the use of medical data.
• Demonstrate how to systematically explore a basic deep learning problem.

Prerequisites

The emphasis of this introductory course will be on the application of deep learning to healthcare. Nonetheless, it is important to have good mathematical background in the following topics:

Essential (as covered in first-year Computer Science course)

• Linear Algebra
• Continuous Mathematics 

Desirable

• Proficiency in Python programming or significant experience with an alternative programming language are essential for the practical sessions and the mini-project examination. Experience with Pytorch is desirable

Synopsis

Module 1: Introduction to medical data context and deep learning foundations 

• What makes healthcare data and context unique?: modalities, labelling challenges, site variability, heterogeneity, governance
• Neural network fundamentals: multi-layer perceptrons, activations, loss functions, gradient descent, backpropagation
• Training at scale: optimisers (momentum/NAG/Adam), initialisation (He/Glorot), normalisation (batch/layer/instance), regularisation (early stopping, dropout)

Module 2: Deep learning architectures for medical data

• Convolutional neural networks (CNNs) for imaging: convolutuons, receptive fields, pooling, residual and encoder-decoder designs
• Medical image segmentation & ViTs: UNet and variants, upsampling choices, ViT for classification/segmentation
• Sequence learning & transformers: RNN/LSTM/GRU, attention & multi-head self-attention, positional encoding, masked attention; architectures for clinical NLP
• Low-data strategies & representations: transfer learning, domain adaptation, autoencoders, contrastive learning

Module 3: Advanced topics and real-world deployment

• Generative models: GANs, DDPM/latent diffusion, conditioning, applications to e.g., denoising/reconstructions, augmentation, anomaly detections; benefits versus risks
• Explainability, trust & fairness: saliency maps; adversarial robustness; model cars/datasheets; bias
• Privacy-preserving learning: federated learning (FedAvg); differential privacy (DP-SDG); practical constraints
• Troubleshooting: error analysis; dataset pathologies; hyperparameter sensitivity; reproducibility

Reading list

The application of deep learning to healthcare data is still an expanding field, and there are no textbooks that cover this topic in great depth. As such, the material will be self-contained within the lecture slides, with several references to relevant academic articles. 

Where relevant, the lecture slides may refer to the following textbooks:

• Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning. MIT Press, 2016
• Raul Rojas. Neural Networks: A systematic introduction. Springer-Verlag, 1996 

A good resource for finding influential papers can be found here. 

Taking our courses

This form is not to be used by students studying for a degree in the Department of Computer Science, or for Visiting Students who are registered for Computer Science courses

Other matriculated University of Oxford students who are interested in taking this, or other, courses in the Department of Computer Science, must complete this online form by 17.00 on Friday of 0th week of term in which the course is taught. Late requests, and requests sent by email, will not be considered. All requests must be approved by the relevant Computer Science departmental committee and can only be submitted using this form.