Refine your search

Biomedical Image Analysis

Our current research focus lies in identifying biomarkers of brain disorders from neuroimaging data, which is an exciting and rapidly growing research area at the intersection of machine learning, biomedical engineering and neuroscience. Conventional approaches towards imaging biomarkers reduce the data dimensionality by averaging the image information to one or few variables of a-priori interest – for example, the volume of Hippocampus for Alzheimers diagnosis. However, such methods discard much information present in brain images. Instead, allowing machine learning algorithms to decide what is important and decipher the predictive pattern (sometimes called statistical biomarker) is projected to be beneficial. This leads to challenging and underconstrained machine learning problems where the data dimensionality is larger than the number of samples and advanced computational techniques are required to solve these problems. We develop these techniques and apply to them to large brain image databases to help neuroscientists to find imaging markers to different brain disorders.

Jukka Lipponen (jukka.lipponen@uef.fi)

Jukka A. Lipponen, Ph.D, received his PhD degree (Medical Physics) in 2014 and M.Sc. (Information technology) in 2007 at the University of Eastern Finland. During his research career (2007-2016) he has been project manager of several scientific projects. His current research interest includes medical signal analysis, data analysis and medical device development. The main research applications include cardiovascular health and cardiovascular disease diagnostics.

He is currently working on Heart2Save Oy, where he is been principal developer of arrythmia monitoring algorithms, which are the core of the Heart2Save’s Aivoni arrythmia analysis service. Jukka Lipponen is also the co-founder of Kubios Oy, start-up company providing HRV and other biomedical signal analysis software tools for researchers and consumers.

Marja Hedman (marja.hedman@uef.fi)

Prediction of aortic dilatation and rupture by means of modern 4D flow MRI technology, molecular biology methods and mathematical algorithms in preclinical models and in clinical study.

Mika Tarvainen (mika.tarvainen@uef.fi)

Mika P. Tarvainen, Ph.D, Docent, received the M.Sc. degree in 1999 and the Ph.D. degree in 2004 from the University of Kuopio, Kuopio,Finland. He is currently a Senior Researcher at the Department of Applied Physics,University of Eastern Finland and Consultant at the Department of Clinical Physiology and Nuclear Medicine, Kuopio University Hospital.
His current research interests include medical signal analysis methods and physiological modelling and their applications in assessing human health. Specifically, development of analysis methods for cardiovascular signals, including heart rate variability (HRV), and psychophysiological measurements. The main research applications include objective assessment of occupational stress, complications of diabetes, and cardiovascular diseases.
Mika Tarvainen is also the founder of Kubios Oy and Partner at Heart2Save Oy, both companies are based in Finland. Kubios Oy is a start-up company providing HRV and other biomedical signal analysis software tools for researchers and consumers, as well as algorithms and custom-built software for the health and wellbeing industry. Kubios HRV software is the most detailed HRV analysis software in the market and is used at roughly 1200 universities in 128 countries.

Pasi Fränti (pasi.franti@uef.fi)

Pasi Fränti received his MSc and PhD degrees from the University of Turku, 1991 and 1994 in Science. Since 2000, he has been a professor of Computer Science at the University of Eastern Finland (UEF). He has published 79 journals and 167 peer review conference papers, including 14 IEEE transaction papers. His main research interests are in machine learning, data mining, and pattern recognition including clustering algorithms and intelligent location-aware systems. Significant contributions have also been made in image compression, image analysis, vector quantization and speech technology.

Pasi Fränti is the head of the Machine Learning group at the school of computing at UEF. He has supervised 25 PhD students on the following topics: Clustering (9), Image and audio compression (5), Speech technology (4), Image processing, de-noising and HDR (3), Location-aware systems (3), and web mining (1). Six of the students originate from Russian including St. Petersburg (3), Uljanovsk (2) and Novosibirsk (1). All graduates work in research, teaching (postdoc, lecturer, associate professor), or in research & development in academia or in IT companies located in Finland, Shanghai, Singapore, Germany, Romania and Iran.

Sana Jahangir (sana.jahangir@uef.fi)

I am a highly motivated Doctoral Researcher with a passion for the intersection of biomechanics, computational modeling, musculoskeletal diseases, and osteoarthritis. My research focus is on developing innovative computational methods to transform the way knee injuries and early osteoarthritis are treated. As part of the DEEPMECHANOKNEE consortium project under ERA PerMed, I am working on a cutting-edge multi-scale modeling workflow combined with deep learning algorithms to provide personalized intervention options to prevent or delay the progression of osteoarthritis. With a goal to improve public health, I am dedicated to advancing our understanding of musculoskeletal diseases through cutting-edge research.

Vittorio Fortino (vittorio.fortino@uef.fi)

I hold a Bachelor’s and Master’s degree in Computer Science, a PhD in Bioinformatics, and a Docentship in Health Bioinformatics. My research is centered on developing and implementing machine learning, heuristic optimization, and network data mining algorithms to tackle the principal computational challenges inherent in the precision medicine (PM) approach. PM is dedicated to the integration of molecular markers with conventional clinical data to customize medical treatment and enhance patient outcomes. My team’s current projects include: 1) patient stratification utilizing both single- and multi-view datasets, facilitated by deep learning, dimensionality reduction, and knowledge-driven clustering analyses; 2) biomarker identification through the analysis of extensive genomics data, applying metaheuristic techniques for feature selection, and; 3) the creation of network data mining algorithms aimed at discovering drug targets and repurposing existing drugs. Our work is pivotal in translating complex biological data into actionable insights for PM, ultimately aiming to optimize individual patient care.