9 papers
To do() or not to do(): Medical Image Counterfactuals for Dataset Augmentation
Yasin Ibrahim, Robin J. Evans, Konstantinos Kamnitsas
Medical image analysis is often hindered by biased datasets, which can lead to biased models and limited clinical applicability. A promising strategy for mitigating such biases is…
Counterfactual Marginalisation: Framework for Evaluating Robustness to Nuisance Variables
Yasin Ibrahim, Hermione Warr, Robin J. Evans +1
Machine learning models can achieve strong test performance while relying on demographic or acquisition-related shortcuts. We propose counterfactual (CF) marginalisation as a test-…
Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models
Hermione Warr, Harry Anthony, Lilli J Freischem +3
Errors in radiology reports can adversely affect patient treatment, yet automated report quality assurance remains challenging because errors are often subtle and require domain ex…
The Invisible Gorilla Effect in Out-of-distribution Detection
Harry Anthony, Ziyun Liang, Hermione Warr +1
Deep Neural Networks achieve high performance in vision tasks by learning features from regions of interest (ROI) within images, but their performance degrades when deployed on out…
Specialised or Generic? Tokenization Choices for Radiology Language Models
Hermione Warr, Wentian Xu, Harry Anthony +3
The vocabulary used by language models (LM) - defined by the tokenizer - plays a key role in text generation quality. However, its impact remains under-explored in radiology. In th…
Quality Control for Radiology Report Generation Models via Auxiliary Auditing Components
Hermione Warr, Yasin Ibrahim, Daniel R. McGowan +1
Automation of medical image interpretation could alleviate bottlenecks in diagnostic workflows, and has become of particular interest in recent years due to advancements in natural…
An Organism Starts with a Single Pix-Cell: A Neural Cellular Diffusion for High-Resolution Image Synthesis
Marawan Elbatel, Konstantinos Kamnitsas, Xiaomeng Li
Generative modeling seeks to approximate the statistical properties of real data, enabling synthesis of new data that closely resembles the original distribution. Generative Advers…
As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?
Anjun Hu, Jindong Gu, Francesco Pinto +2
Foundation models pre-trained on web-scale vision-language data, such as CLIP, are widely used as cornerstones of powerful machine learning systems. While pre-training offers clear…
Semi-Supervised Learning for Deep Causal Generative Models
Yasin Ibrahim, Hermione Warr, Konstantinos Kamnitsas
Developing models that are capable of answering questions of the form "How would x change if y had been z?'" is fundamental to advancing medical image analysis. Training causal gen…