Keynotes

Institute of Machine Learning in Biomedical Imaging

Bio: Julia A. Schnabel (FIEEE, FMICCAI, FELLIS) is a Professor in Computational Imaging and AI in Medicine (TUM Liesel Beckmann Distinguished Professorship) at the TUM School of Computation, Information & Technology, as well as the TUM School of Medicine & Health, Technical University of Munich, Germany, and Director of the Institute of Machine Learning in Biomedical Imaging (Helmholtz Distinguished Professorship) at Helmholtz Munich, Germany. She holds part-time appointment as Chair in Computational Imaging at the School of Biomedical Engineering and Imaging Sciences, King’s College London, UK, and was previously Professor of Engineering Science (Medical imaging) at the University of Oxford, UK. She has served on the IEEE TMI steering board, as Associate Editor for IEEE TMI and IEEE TBME, is on the Medical Image Analysis editorial board, and a Founding Editor for Machine Learning in Biomedical Imaging (MELBA). She has served on the IEEE EMBS AdComm as Technical Representative, and on the MICCAI Society Board of Directors, also as its Executive Secretary, and was Program Chair for MICCAI 2018, General Chair for MICCAI 2024, General Chair for WBIR 2016 and 2022, General Chair for IPMI 2021 and is incoming General Chair for IPMI 2027.

Julia’s research interests include the topics of image reconstruction, registration, segmentation, classification and image quality control, using machine/deep learning, with applications in motion reconstruction and image compounding, physics-informed modelling, representation learning and anomaly detection, multi-organ segmentation, multimodality imaging and data integration, applied across imaging modalities (MRI, CT, PET, ultrasound, X-ray, optical imaging) and different diseases and conditions, ranging from neuroimaging, over cardiovascular imaging and perinatal imaging, to oncological imaging, for screening, early detection and treatment stratification.

Oxford Centre for Integrative Neuroimaging (OxCIN)

Abstract: There is an increasing consensus in the neuroscience community that the next major advances in neuroscience require us to span scales, species and tools. In this talk, I’ll present examples of how our group is taking on this challenge by directly comparing MRI with microscopy. I’ll overview the technical challenges for performing these kind of studies, particularly in whole-brain samples. I’ll describe a range of kinds of investigation that this can enable. And time permitting, I’ll discuss how we’re aiming to integrate this into a broader range of imaging studies, including virtuous cycles of discovery-hypothesis-discovery linking in-vivo, ex-vivo, animal and population neuroimaging.

Bio: Karla Miller is a biomedical engineer at the Oxford Centre for Integrative Neuroimaging. She is interested in developing novel MRI techniques, understanding their relationship to neurobiology, and deploying these techniques to enable novel neuroscience investigations. Current themes in her work include population imaging, integrated acquisition and analysis, and relating MRI to microscopy. She also is passionate about equality, diversity and inclusion in academia.

European Molecular Biology Laboratory

Bio: Anna Kreshuk holds a PhD in Computer Science from Heidelberg University and a Diploma in Mathematics from Lomonosov Moscow State University. Between her two degrees, she worked at CERN in Geneva as a scientific programmer on the ROOT framework.

Dr. Kreshuk is a Group Leader and Senior Scientist at the European Molecular Biology Laboratory (EMBL), where she also serves as Interim Head of the Cell Biology and Biophysics Unit. Her research lies at the intersection of AI and biology, focusing on machine learning methods for the analysis of biological images. Her interests include large-scale image and volumetric segmentation, sparse and weak supervision, multimodal data integration, and learned representations of visual phenotypes.

Dr. Kreshuk is particularly committed to making machine learning more accessible to researchers in the life sciences. She leads the development of ilastik, an interactive image analysis platform designed to make advanced machine learning methods usable without extensive computational expertise. The ilastik team also contributes to the BioImage Model Zoo, an initiative that promotes the interoperability and easy sharing of deep learning models for microscopy.