This module covers the fundamental concepts and advanced methodologies of machine learning for imaging and relates those to real-world problems in computer vision and medical image analysis. You will experience different approaches to machine learning including supervised and unsupervised techniques with an emphasis on deep learning methods. Applications include image classification, semantic segmentation, object detection and localisation, and registration. A key objective is to equip you with the skills needed to work in, and conduct research into, image computing and applied machine learning.
Predicting the age of a patient from their brain MRI scan can have diagnostic value for a number of diseases that may cause structural changes and potential damage to the brain. A discrepancy between the predicted age and the real, chronological age of a patient might indicate the presence of disease. This requires an accurate predictor of brain age which may be learned from a set of healthy reference subjects, given their brain MRI data and their actual age. The objective for the coursework is to implement two supervised learning approaches for age regression from brain MRI.
Note: Pull repo and use with a obsidain to see notes.
| Week | Topics | Notes | Lecture Notes | Papers |
|---|---|---|---|---|
| 2 | Introduction to Imaging | [[Week 2]] | [[Week 2 - Introduction to ML for Imaging.pdf]] | [[Week 2 - LeCun, Bengio, Hinton. 2015. Deep learning. Nature.pdf]] |
| 3 | Feature Extraction | [[Week 3 - 01]] | [[Week 3 - Image Classification and NN.pdf]] | [[Week 3 - Vaswan et al. 2017. Attention is all you need. NIPS.pdf]] |
| Image Classification | [[Week 3 - 02]] | |||
| Neural Networks | [[Week 3 - 03]] | |||
| Convolution Neural Networks | [[Week 3 - 04]] | |||
| 4 | Image Segmentation | [[Week 4 - 01]] | [[Week 4 - Image Segmentation.pdf]] | [[Week 4 - Dosovitskiy et al. 2021. An image is worth 16x16 words. ICLR.pdf]] |
| Evaluating Image Segmentation | [[Week 4 - 02]] | |||
| Intensity-Based Segmentation | [[Week 4 - 03]] | |||
| CNNs for Image Segmentation | [[Week 4 - 04]] | |||
| 5 | Introduction to image registration | [[Week 5 - Introduction to image registration]] | [[Week 5 - Image Registration.pdf]] | [[Week 5 - Ranftl et al. 2021. Vision Transformers for Dense Prediction. ICCV.pdf]] |
| Applications of Image Registration | [[Week 5 - Applications of Image Registration]] | |||
| Intensity-based Registration | [[Week 5 - Intensity-based Registration ]] | |||
| Registration with Neural Networks | [[Week 5 - Registration with Neural Networks ]] | |||
| 6 | Unsupervised Learning: Clustering | [[Week 6 - Unsupervised Learning - Clustering]] | [[Week 6 - Unsupervised Learning.pdf]] | [[Week 6 - Ho et al. 2020. Denoising Diffusion Probabilistic Models. NeurIPS.pdf]] |
| Dimensionality reduction & data encoding | [[Week 6 - Dimensionality reduction & data encoding]] | |||
| Generative Modelling | [[Week 6 - Generative Modelling]] | |||
| 7 | Solving Inverse Problems | [[Week 7 - Solving Inverse Problems]] | [[Week 7 - Inverse Problems.pdf]] | [[Week 7 - Chen et al. 2020. A simple framework for contrastive learning of visual representation. ICML.pdf]] |
| Solving Inverse Problems with Deep Learning | [[Week 7 - Solving Inverse Problems with Deep Learning]] | |||
| DL for Super-resolution | [[Week 7 - Deep Learning for Image Super-Resolution]] | |||
| DL for Image Reconstruction | [[Week 7 - Deep Learning for Image Reconstruction]] | |||
| Object Detection | [[Week 7 - Object Detection]] | [[Week 7 - Object Detection.pdf]] | ||
| R-CNNs | [[Week 7 - Region Proposals-CNN (R-CNN)]] | |||
| Fast R-CNN, Faster R-CNN & Mask R-CNN | [[Week 7 - Fast R-CNN, Faster R-CNN & Mask R-CNN]] | |||
| YoLo | [[Week 7 - You Only Look Once (YOLO)]] | |||
| 8 | Federated Learning | [[Week 8 - Trustworthy AI & ML]] | [[Week 8 - Trustworthy ML.pdf]] | |
| Homomorphic Encryption / Secure Multi-Party Computation | [[Week 8 - ML and homomorphic encryption and Secure Multi-Party Computation]] | |||
| Introduction to Interpretability | [[Week 8 - Interpretability and Explainability (Introduction)]] | |||
| Visualisation and Attribution | [[Week 8 - Visualization and Attribution]] | |||
| Inceptionism | [[Week 8 - Inceptionism & Inversion]] | |||
| Deep Image Prior | [[Week 8 - Deep Image Prior]] | |||
| Adversarial Methods | [[Week 8 - Adversarial Methods]] |