MMIV Newsletter December 2019 

Helse-Vest Funding to MMIV initiatives

Helse-Vest has allocated funds to 61 of the total 285 applications submitted by the deadline of September 15. Njål Lura, PhD candidate in the gynecological cancer imaging project, has received PhD funding from this competitive call. In addition, Satheshkumar Kaliyugarasan, of the same project, is on the waiting list for PhD-scholarship, which may also turn out to be awarded. 

Cecilie Brekke Rygh was awarded financial support for her project “Imaging biomarkers for precision medicine in Acute Myeloid Leukemia (AML)”, in which Noeska Smit and Alexander Lundervold co-lead a workpackage on image data analyses and visualization. 
Congratulations to all awardees!

Ingfrid Haldorsen awarded Honorary Membership of the Norwegian Radiological Society 

Sigmund Ytre-Hauge Awarded with Best Article in abdominal Radiology in 2018

MMIV Conference 2019

Welcome to the 2nd MMIV Conference at Bikuben Conference Center (Haukeland University Hospital) on December 9th and 10th 2019. The theme of the conference is Convergence of Medical Data Science for Improved Patient Care.

International world-leading experts will give their perspectives on the topic. Furthermore, researchers from the MMIV center will present ongoing projects that capitalize on machine learning and advanced imaging- and visualization techniques to improve patient care. The conference will be followed by a Hackathon on December 11th.

The conference and workshop is open to everyone, and there is no admission fee. Free lunch will be provided. All participants are encouraged to submit abstracts for poster presentation.

MMIV Hackathon: The MMIV 2019 BrainAge Challenge

In conjunction with the MMIV conference, there will be a Hackaton and industry talks on December 11th on the topic of brain age. 

The age of a research participant is easy to obtain - just ask the person when they come in. So why do we want to post a brain-age challenge? Why estimate a person’s age based on images and measures from the brain? The reason is that knowledge about the correlation between actual age and age as calculated from the image data can give us insight into normal aging processes.

Knowing how the brain changes throughout adolescence and old age can tell us what each of us has to expect. Once we have an understanding of that process in healthy individuals we can look for cases in which our assumption is wrong. Say our model is - on average - able to tell us the true age given the brain images, what happens if we encounter a mismatch? Can we highlight that case and ask if this particular participant has something else going on? Maybe he is 80 years old but looks like a 40 year old person given the image data. How did the participant stay that young?

These and other questions can be posed when we have a good understanding of the normal aging process as captured by medical structured imaging. Hopefully you can help us to identify our surprising participants.

The challenge will have two parts:
 

• Using data we have prepared: construct a model that can predict the age of a person from imaging-derived features (computed by Freesurfer 6.0). This will be organized as a competition on Kaggle.
• We’ll provide links to the underlying image-data, additional images and demographic information about the subjects. Use this together with your brain age model to tell an interesting story. Each team will give a short presentation at the end of the day, and the winner will be chosen (as a vote among all participants)

Shonan Meeting on Formalizing Biological and Medical Visualization

Helwig Hauser, Stefan Bruckner, and Noeska Smit will be attending a Shonan meeting in Japan February 24 - 27 in 2020 on the topic of ‘Formalizing Biological and Medical Visualization’. The aim of this meeting is to formalize the current status of the field of BioMedical Visualization and to determine future challenges for novice researchers.

Recent Publication Highlights

• H. Espedal, T. Fonnes, K. E. Fasmer, C. Krakstad, and I. S. Haldorsen, "Imaging of Preclinical Endometrial Cancer Models for Monitoring Tumor Progression and Response to Targeted Therapy," Cancers, vol. 11, iss. 12, p. 1885, 2019. https://doi.org/10.3390/cancers11121885

• K. Hugdahl, K. Kazimierczak, J. Beresniewicz, K. Kompus, R. Westerhausen, L. Ersland, R. Grüner, and K. Specht, "Dynamic up- and down-regulation of the default (DMN) and extrinsic (EMN) mode networks during alternating task-on and task-off periods," PLOS ONE, vol. 14, iss. 9, pp. 1-15, 2019. https://doi.org/10.1371/journal.pone.0218358

• O. T. Ousdal, T. Kaufmann, K. Kolskår, A. Vik, E. Wehling, A. J. Lundervold, A. Lundervold, and L. T. Westlye, "Longitudinal stability of the brain functional connectome is associated with episodic memory performance in aging," Human Brain Mapping, 2019. https://doi.org/10.1002/hbm.24833 

• L. Garrison, J. Vasicek, R. Grüner, N. N. Smit, and S. Bruckner, "SpectraMosaic: An Exploratory Tool for the Interactive Visual Analysis of Magnetic Resonance Spectroscopy Data," in Eurographics Workshop on Visual Computing for Biology and Medicine, 2019. https://doi.org/10.2312/vcbm.20191225

• H. Bartsch, L. Garrison, S. Bruckner, A. Wang, S. F. Tapert, and R. Grüner, "MedUse: A Visual Analysis Tool for Medication Use Data in the ABCD Study," in Eurographics Workshop on Visual Computing for Biology and Medicine, 2019. https://doi.org/10.2312/vcbm.20191236

• E. Mörth, R. G. Raidou, I. Viola, and N. Smit, "The Vitruvian Baby: Interactive Reformation of Fetal Ultrasound Data to a T-Position," in Eurographics Workshop on Visual Computing for Biology and Medicine, 2019. https://doi.org/10.2312/vcbm.20191245

MMIV on GitHub