MIDL Vision 2020

2 Irene's Picks Irene Brusini is a PhD student in a joint doctoral programme between KTH Royal Institute of Technology and Karolinska Institute in Stockholm (Sweden). She works on the development of methods for the analysis and characterisation of brain morphology from MRI images, with a special focus on Alzheimer's disease and its neurodegenerative patterns. "I have always been fascinated by the intersection between technology and neuroscience. My researchwork allows me to explore both fields at the same time, which is really exciting! Machine learning and deep learning are playing an increasingly big role in neuroimaging, and it is very rewarding for me to use these tools for contributing to the advancement of neuroscientific research." "I am very excited to be at MIDL for the first time and I am looking forward to interacting and exchanging ideas with fellow researchers. Irene told us her top picks for today, but we recommend that you do not miss her own poster presentation today at 9:30 (UTC-4): S198 - A deep learning-based pipeline for error detection and quality control of brain MRI segmentation results. Here is her teaser video: Read on page 12 Read on page 6 Irene's Picks of the day: Orals: O171 - A Heteroscedastic Uncertainty Model for Decoupling Sources of MRI Image Quality O042 - Automatic Diagnosis of Pulmonary Embolism Using an Attention-guided Framework: A Large-scale Study O089 - Automated Labelling using an Attention model for Radiology reports of MRI scans (ALARM) Posters: P250 - Feature Disentanglement to Aid Imaging Biomarker Characterization for Genetic Mutations S282 - Uncertainty Evaluation Metric for Brain Tumour Segmentation S312 - Using Generative Models for Pediatric wbMRI