Computer Vision News - October 2022

62 Congrats, Doctor! Brain tumours strike people in the prime of life. Surgical resection – the primary treatment of most brain tumours – aims at maximising the extent of tumour resection while preserving the patient's cognitive function. To optimise this tradeoff, Reuben's PhD research aimed at developing automated brain structures and pathology segmentation for improved surgical guidance. While Neural Networks have become the state-of-the-art for most image segmentation tasks, annotated databases required to train them are usually dedicated to a single task, leading to partial annotations (e.g. brain structure or pathology delineation but not both). Moreover, the information required for these tasks may come from distinct magnetic resonance (MR) sequences, leading to datasets with heterogenous sets of image modalities ( hetero-modality ). Similarly, the scans may have been acquired at different centres, with different MR parameters, leading to differences in resolution and visual appearance among databases ( domain shift ). Given the large amount of resources, time and expertise required to carefully annotatemedical images, it is unlikely that large and fully-annotated databases will become readily available for every joint problem . For this reason, there is a need to develop collaborative approaches that exploit existing heterogeneous and task-specific datasets and weak annotations instead of time-consuming pixel-wise annotations. Reuben Dorent has recently completed his PhD at King's College London. His research aims to improve brain tumour surgery using medical image analysis. In particular, Reuben's research tackles a fundamental challenge for translating algorithms to clinical practice: the lack of large annotated medical datasets. His research lies at the intersection of weakly-supervised learning, domain adaptation and Bayesian modelling. Reuben is now a postdoctoral fellow at Harvard Medical School in image registration for computer-assisted surgery. Congrats, Doctor Reuben!