Institutt for biomedisin

CCBIO seminar: Arvid Lundervold

Computational imaging and machine learning in biomedicine


Arvid Lundervold,
Department of Biomedicine, University of Bergen

Computational (bio)medicine (CM) is a new field of science that can be defined as the application of methods from engineering, mathematics, and computational sciences to improve our understanding of disease mechanisms, and follow-up and treatment of human disease.

CM is characterized by being multi-scale (molecule to man, microseconds to years), sub-specialized (from computational proteomics to computational psychiatry), often dealing with heterogeneous, longitudinal, and high dimensional data, and addressing high-content, high-throughput data from DNA sequencers and imaging scanners as well as data from bio-banks and registers. CM is employing an impressive range of mathematical, statistical, and computational methods, and has a huge potential within personalized medicine, disease prevention, and therapy.

An important class of new computational tools enhancing the abilities of CM, is based on machine learning (ML). ML aims to construct “programs or systems that builds and trains predictive models from input data, and uses the learned models to make useful predictions from new (previously unseen) data, drawn from the same distribution as the one used to train the models”.

In this seminar emphasis will be put on ML in the context of computational imaging and (bio)medicine, focusing on morphological and functional MRI. Examples from previous and ongoing research on ML-based applications in the newly established Mohn Medical Imaging and Visualization Centre (https://mmiv.no) at the Department of Radiology, Haukeland University Hospital will be given. For example automated tissue classification in multispectral brain MRI, fast segmentation of brain and kidney using deep convolutional neural networks and transfer learning (joint with Alexander S. Lundervold), coregistration of histology and multiparametric MRI for the use of ML in prostate cancer, and application of ML in predicting irritable bowel syndrome (IBS) from multimodal brain MRI addressing the brain-gut interaction in functional gastrointestinal disorders.

Finally, some thoughts on machine learning in biomedicine will relate to education and training, moving from “wet-labs” to “dry-labs”, and the implementation of open science, reproducible research, and competitions.

Chairperson: Lars A. Akslen, CCBIO