Research

Current reserach activities

My research is mainly within applications of machine learning to medical data analysis, with a particular focus on medical imaging.

Most of my activities are related to the Medical Imaging and Visualization Centre at the Department of Radiology, Haukeland University Hospital, funded by the Trond Mohn Foundation, where I am part of the leadership team.


At the Western Norway University of Applied Sciences (HVL) I am part of Computer Science: Software Engineering, Sensor Networks and Engineering Computing, the Health Informatics research group, the Data Science & AI group, and the multidisciplinary research group Idrett, Helse og Funksjon (Sports, health and function).

I'm also a "Secondary Proposer" for the COST action PARENCHIMA: Magnetic Resonance Imaging Biomarkers for Chronic Kidney Disease, OC-2016-1-20493).


PhD supervision

Main supervisor

Co-supervision


Postdocs, main mentor

Publications

2D and 3D U-Nets for skull stripping in a large and heterogeneous set of head MRI using fastai.
Kaliyugarasan S, Kocinski M, Lundervold A, Lundervold AS. , To appear in the Proceedings of the NIK-2020 conference, 2020
Synthesizing skin lesion images using CycleGANs – a case study.
Fossen-Romsaas S, Storm-Johannessen A, Lundervold AS. , To appear in the Proceedings of the NIK-2020 conference, 2020
An overview of deep learning in medical imaging focusing on MRI
with A. Lundervold, Zeitschrift fuer Medizinische Physik, Volume 29, Issue 2, 2019
Fast estimation of kidney volumes and time courses in DCE-MRI using convolutional neural networks
with K. Sprawka, A. Lundervold. Scientific Paper at ECR 2018, Austria Center Vienna, Austria, Feb. 2018
​​Fast semi-supervised segmentation of the kidneys in DCE-MRI using convolutional neural networks and transfer learning
with A. Lundervold, J. Rørvik. Functional Renal Imaging: Where Physiology, Nephrology, Radiology and Physics Meet, Max Delbrück Communications Center, Berlin, Oct. 2017
​​"Deep learning" i medisin
HMT, 2017/4
Post-Lie algebras and isospectral flows
with K. Ebrahimi-Fard, I. Mencattini, H.Z. Munthe-Kaas Symmetry, Integrability and Geometry: Methods and Applications (SIGMA), 11, 093, 2015
arXiv version
On the Lie enveloping algebra of a post-Lie algebra
with K. Ebrahimi-Fard and H.Z. Munthe-Kaas, Journal of Lie Theory, Vol. 25, No. 4, 1139--1165, 2015
arXiv version
On algebraic structures of numerical integration on vector spaces and manifolds
with H.Z. Munthe-Kaas, IRMA Lectures in Mathematics and Theoretical Physics Vol. 21, 2015
arXiv version
Noncommutative Bell polynomials, quasideterminants and incidence Hopf algebras
with K. Ebrahimi-Fard and D. Manchon, International Journal of Algebra and Computation, Volume 24, Issue 5, 2014
arXiv version
On post-Lie algebras, Lie–Butcher series and moving frames
with H.Z. Munthe-Kaas, Foundations of Computational Mathematics, Volume 13, Issue 4, 2013
arXiv version
Backward error analysis and the substitution law for Lie group integrators
with H.Z. Munthe-Kaas, Foundations of Computational Mathematics, Volume 13, Issue 2, 2013
arXiv version
Algebraic structure of stochastic expansions and universally accurate simulation
with K. Ebrahimi-Fard, S.J.A. Malham, H.Z. Munthe-Kaas, A. Wiese, Proceedings of the Royal Society. Mathematical, Physical and Engineering Sciences, Volume 468 (2144), 2012
arXiv version

Selected conference posters

Brain Age versus Chronological Age: A Large Scale MRI and Deep Learning Investigation
S. Kaliyugarasan, A. Lundervold and A.S. Lundervold Poster at ECR 2020 Electronic poster
Discrimination between Alzheimer’s disease, mild cognitive impairment and cognitively normal subjects using 3D T1w MRI - a multi-atlas, machine learning approach
S. Alam, A.S. Lundervold and A. Lundervold Poster at ECR 2020 Electronic poster
fastai for 3D MRI deep learning & explainable AI
S. Kaliyugarasan and A.S. Lundervold Poster at MMIV Conference 2019, Bergen, Dec. 2019
BrainAge: From DICOM to age
S. Kaliyugarasan and A.S. Lundervold Poster at MMIV Conference 2019, Bergen, Dec. 2019
Machine learning and electronic health records: some challenges, opportunities and ongoing experiments
S. Stavland and A.S. Lundervold Poster at MMIV Conference 2019, Bergen, Dec. 2019
Generative adversarial networks and medical image synthesis
A. Storm-Johannessen, S. Fossen-Romsaas and A.S. Lundervold Best poster award at MMIV Conference 2019, Bergen, Dec. 2019
A multi-atlas-based classification of Alzheimer’s disease using 3D T1w MRI and a supervised classifier
S. Alam, A. Lundervold and A.S. Lundervold Poster at MMIV Conference 2019, Bergen, Dec. 2019
Brain age versus chronological age: a work-in-progress, large-scale machine learning approach
J. Helle and A.S. Lundervold Poster at MMIV Conference 2019, Bergen, Dec. 2019
Transfer learning for medical images: a case study
with S. Kaliyugarasan. Poster at GTC Europe 2018, Munich, Germany, Oct. 2018
Python-based software for medical imaging and machine learning — an example from brain imaging in IBS
with K. Le Cornec, O. Verdier, V. Barra, and A. Lundervold, Abstract and poster at MedViz 2016
Predicting irritable bowel syndrome (IBS) from brain MR imaging data using machine learning
with A. Lundervold, E. A. Valestrand, T. Hausken, Poster at 2017 Geilo Winter School in eScience

Preprints, submitted and in preparation

Submitted: Automated segmentation of endometrial cancer on multimodal MR images using deep learning.
with E. Hodneland and others
Submitted: Cognitive and MRI trajectories for prediction of Alzheimer’s disease.
S.A. Mofrad, A.J. Lundervold, A. Vik and A.S. Lundervold
Submitted: A predicitive framewok based on brain volume trajectories enabling early detection of Alzheimer's disease.
S.A. Mofrad, A. Lundervold and A.S. Lundervold
In prep: Alzheimer’s disease classification using multi-atlas-based features
S. Alam, A. Lundervold, A.S. Lundervold
In prep: Brain age versus chronological age: A large scale MRI and deep learning investigation.
A.S. Lundervold, S. Kaliyugarasan, A. Lundervold,

Talks and travels

Recent and upcoming

Older


Recent research projects

More to be added

Through the MobiFORSK programme I led a project on machine learning together with NordicNeuroLab, a company providing products and solutions for functional MR imaging.

In 2015 I was co-PI in the project Computational medicine: Numerical models for medical images and signals, funded by UH-Nett Vest, with partners from HVL, UiB, HUS and UiS

PhD thesis