2021 Entry Clinical Fellowship
Graphical modelling of brain tumours
Cancer of the brain is a major cause of death and disability that is rising in prevalence while remaining stubbornly resistant to treatment. Despite intense research, survival rates have remained essentially unchanged over the past thirty years. Other kinds of cancer have seen striking improvements in treatment outcomes over recent decades: why is the brain different? One possible answer is the unusual complexity of brain tumours: the disease mechanisms underlying the uncontrolled, disorganised cell division that is the hallmark of all cancer appear to be both many and diverse, varying greatly from one patient to another.
As with all human diversity, to understand this biological diversity we must first describe it in sufficient detail to render each individual distinct and recognizable. At the heart of our proposed approach lies the idea of making sense of biological patterns as networks, where biological characteristics are conceived as nodes, and their relations as connections between nodes. By way of analogy, the path of a cell from normal to cancerous may be seen as a journey through the London Underground, where the final destination of malignancy is reached via a set of genetic stops defining a characteristic path. Capturing the set of all possible paths—a map of the “tumour underground”—then gives us a means of understanding what is going on, and how the disease process varies from one patient to another. Machines able to make sense of these complex patterns—such as the artificial intelligence systems now revolutionizing the world—can then be deployed to the task of identifying the right treatment for the right patient, helping deliver care that is both personalised and founded on robust evidence. But no framework to deliver it currently exists: our task is to create its foundations, establish its feasibility, and prototype its application.
Currently MRC Clinical Research Training Fellow
Publications
Brain tumour genetic network signatures of survival
Brain, https://doi.org/10.1093/brain/awad199
2023
Brain tumour segmentation with incomplete imaging data
Brain Communications, Volume 5, Issue 2, 2023, fcad118, https://doi.org/10.1093/braincomms/fcad118
2023
The human cost of artificial intelligence
Brain Structure and Function 228, 1365–1369
2023
Graph lesion-deficit mapping of fluid intelligence
Brain, Volume 146, Issue 1, January 2023, Pages 167–181, https://doi.org/10.1093/brain/awac304
2023
A framework for focal and connectomic mapping of transiently disrupted brain function
Communications Biology 6, 430, https://doi.org/10.1038/s42003-023-04787-1
2023
The legibility of the imaged human brain
arXiv, https://arxiv.org/abs/2309.07096
2023
Compressed representation of brain genetic transcription
arXiv, https://arxiv.org/abs/2310.16113
2023
Deep Learning for Tumour Segmentation with Missing Data. Neuro-Oncology
Neuro-Oncology. 2022;24(Supplement_4):iv16-iv16, https://doi.org/10.1093/neuonc/noac200.070
01 October 2022
Identifying Enhancing Tumour Without Contrast-Enhanced Imaging
Neuro-Oncology, 2022;24(Supplement_4):iv3-iv3, https://doi.org/10.1093/neuonc/noac200.012
01 October 2022
Translating automated brain tumour phenotyping to clinical neuroimaging
arXiv, https://arxiv.org/abs/2206.06120
13 June 2022