Our team is composed such that it possess expert knowledge of both deep learning/machine learning and healthcare.

 

 

Robert Jenssen [Brief CV] is the head of the UiT Machine Learning Group. He develops novel deep learning methodology and information theoretic and kernel-based machine learning algorithms, focusing on health analytics and on remote sensing applications. Robert is also a Prof II at the Norwegian Computing Center in Oslo. Robert is responsible for UiT’s Machine Learning and Statistics education within the Applied Physics and Mathematics study program. Please see Robert’s official UiT web page or Robert’s somewhat outdated semi-official web page.

Robert Jenssen

Associate Professor
UiT

Fred Godtliebsen works in the Department of Mathematics and Statistics in the Statistics group, and is in addition an associate member of the Machine Learning Group, especially on health related research from a statistical viewpoint.

Fred Godtliebsen

Professor
UiT

Arthur Revhaug Professor of Surgery, University of Tromsø and Director Division of Surgery, Oncology and Womens health, Tromsø University Hospital, Norway.
Revhaug has published 156 papers listed by PubMed. These publications are mostly related to the patophysiology of sepsis, infections, growth factors, perioperative care and other surgical subjects. In addition he has written several chapters in different books related to surgical patophysiology and edited a book on The Catabolic State published by Springer Verlag.

Arthur Revhaug

Surgeon, Director Division of Surgery
UNN

Rolv-Ole Lindsetmo Head and Chief Surgeon, Department of Gastrosurgery, University Hospital of North Norway. Adjunct Professor at the Department of Clinical Medicine at UiT The Arctic University of Norway. Lindsetmo has published extensively in e.g. American Journal of Surgery and in the Journal of Gastrointestinal Surgery, to name a few.

Rolv-Ole Lindsetmo

Chief Surgeon
UNN

Karl Øyvind Mikalsen works on health data analytics in a close collaboration with researchers at the University Hospital of North Norway (UNN), and the Norwegian Center for E-Health Research. The data source is the Department of Gastrointestinal Surgery at UNN with several years of big clinical data related to colon cancer and surgery including free text (nurses notes, surgeon’s report etc), semi-structured text, physiological data, blood tests, etc. The group works for example on prediction of post-operative anastomosis leakage and delirium, to name a few. Prof Fred Godtliebsen and Senior researcher Stein Olav Skrøvseth are co-supervisors.

Karl Øyvind Mikalsen

Graduate Student
UiT

Michael Kampffmeyer works on applications and development of deep learning algorithms in a joint effort with researchers at the Norwegian Computing Center in Oslo, Norway. Michael studies issues related to transfer learning, the handling of different image resolutions and multi-modality. He is also interested in the combination of CNNs and unsupervised learning. Senior researcher Arnt-Børre Salberg at the Norwegian Computing Center is co-supervisor. Michael is funded by the Norwegian Research Council over FRIPRO project on “Next Generation Learning Machines”. Please visit Michael’s home page.

Michael Kampffmeyer

Graduate Student
UiT

Cristina Soguero Ruiz works at the Rey Juan Carlos University, but did her PhD partly in the Machine Learning Group at UiT where she is an associate member and a close long-term collaborator, especially on health related research from a machine learning viewpoint. She received the Telecommunication Engineering degree, the B.Sc. degree in Business Administration and Management, and the M.Sc. degree in Biomedical Engineering from the Rey Juan Carlos University, Madrid, Spain, in 2011 and 2012. She got the PhD in Machine Learning with applications in Healthcare in 2015. She won the Orange Foundation Best PhD Thesis Award by the Spanish Official College of Telecommunications Engineers.

Cristina Soguero Ruiz

Associate Professor
URJC

Filippo Bianchi received the B.Sc. in Computer Engineering (2009), the M.Sc. in Artificial Intelligence and Robotics (2012) and the PhD in Machine Learning (2015) from “Sapienza” University, Rome. Filippo worked 2 years as research assistant at the Computer Science department at Ryerson University, Toronto. Filippo’s research interests in machine learning and pattern recognition include graph and sequence matching, clustering, classification, reservoir computing, deep learning and data mining. Filippo is funded by the Norwegian Research Council over FRIPRO project on “Next Generation Learning Machines”. Latest research activities can be found at Filippo’s home page.

Filippo Bianchi

Postdoc
UiT

Sigurd Løkse works on robust kernel and information theoretic methods exploiting for example probabilistic cluster kernels as weak learners to build powerful similarity measures for ranking and spectral clustering. Sigurd works on aspects related to ensemble clustering, spectral clustering, Markov chains, and new approaches to missing data problems.

Sigurd Løkse

Graduate Student
UiT

Kristoffer Wickstrøm is a master student at UiT The Arctic University of Norway working on polyp segmentation using fully convolutional neural networks. Area of interest includes machine learning and deep learning, with a special interest in convolutional neural networks. His supervisors are Michael Kampffmeyer, Karl Øyvind Mikalsen, and Robert Jenssen.

Kristoffer Wickstrøm

Master Student
UiT

Andreas Storvik Strauman is a master student at UiT The Arctic University of Norway working on modeling of health data time series using recurrent neural networks. He is interested in many fields of machine learning, and hasn’t really picked a favorite field. Yet. Supervised by Filippo Bianchi and Robert Jenssen.

Andreas Storvik Strauman

Master Student
UiT

Mads Adrian Hansen is working on the deep anchor framework. This framework combines so-called anchor learning with deep auto-encoders for feature extraction. The project’s main focus is prediction of postoperative delirium based on unstructured text obtained from nurses notes. From the text, certain anchors are defined from which predictive models for postoperative delirium may be obtained based on basic natural language processing (NLP) tools. On top of this NLP representation, a deep auto-encoder extracts powerful features for the models to use. Promising results are submitted for publication. Supervised by Karl Øyvind Mikalsen​, Michael Kampffmeyer, Filippo Bianchi and Robert Jenssen.

Mads Adrian Hansen

Master Student
UiT

Robert Jenssen [Brief CV] is the head of the UiT Machine Learning Group. He develops novel deep learning methodology and information theoretic and kernel-based machine learning algorithms, focusing on health analytics and on remote sensing applications. Robert is also a Prof II at the Norwegian Computing Center in Oslo. Robert is responsible for UiT’s Machine Learning and Statistics education within the Applied Physics and Mathematics study program. Please see Robert’s official UiT web page or Robert’s somewhat outdated semi-official web page.
Fred Godtliebsen works in the Department of Mathematics and Statistics in the Statistics group, and is in addition an associate member of the Machine Learning Group, especially on health related research from a statistical viewpoint.
Arthur Revhaug Professor of Surgery, University of Tromsø and Director Division of Surgery, Oncology and Womens health, Tromsø University Hospital, Norway.

Revhaug has published 156 papers listed by PubMed. These publications are mostly related to the patophysiology of sepsis, infections, growth factors, perioperative care and other surgical subjects. In addition he has written several chapters in different books related to surgical patophysiology and edited a book on The Catabolic State published by Springer Verlag.
Rolv-Ole Lindsetmo Head and Chief Surgeon, Department of Gastrosurgery, University Hospital of North Norway. Adjunct Professor at the Department of Clinical Medicine at UiT The Arctic University of Norway. Lindsetmo has published extensively in e.g. American Journal of Surgery and in the Journal of Gastrointestinal Surgery, to name a few.
Karl Øyvind Mikalsen works on health data analytics in a close collaboration with researchers at the University Hospital of North Norway (UNN), and the Norwegian Center for E-Health Research. The data source is the Department of Gastrointestinal Surgery at UNN with several years of big clinical data related to colon cancer and surgery including free text (nurses notes, surgeon’s report etc), semi-structured text, physiological data, blood tests, etc. The group works for example on prediction of post-operative anastomosis leakage and delirium, to name a few. Prof Fred Godtliebsen and Senior researcher Stein Olav Skrøvseth are co-supervisors.
Michael Kampffmeyer works on applications and development of deep learning algorithms in a joint effort with researchers at the Norwegian Computing Center in Oslo, Norway. Michael studies issues related to transfer learning, the handling of different image resolutions and multi-modality. He is also interested in the combination of CNNs and unsupervised learning. Senior researcher Arnt-Børre Salberg at the Norwegian Computing Center is co-supervisor. Michael is funded by the Norwegian Research Council over FRIPRO project on “Next Generation Learning Machines”. Please visit Michael’s home page.
Cristina Soguero Ruiz works at the Rey Juan Carlos University, but did her PhD partly in the Machine Learning Group at UiT where she is an associate member and a close long-term collaborator, especially on health related research from a machine learning viewpoint. She received the Telecommunication Engineering degree, the B.Sc. degree in Business Administration and Management, and the M.Sc. degree in Biomedical Engineering from the Rey Juan Carlos University, Madrid, Spain, in 2011 and 2012. She got the PhD in Machine Learning with applications in Healthcare in 2015. She won the Orange Foundation Best PhD Thesis Award by the Spanish Official College of Telecommunications Engineers.
Filippo Bianchi received the B.Sc. in Computer Engineering (2009), the M.Sc. in Artificial Intelligence and Robotics (2012) and the PhD in Machine Learning (2015) from “Sapienza” University, Rome. Filippo worked 2 years as research assistant at the Computer Science department at Ryerson University, Toronto. Filippo’s research interests in machine learning and pattern recognition include graph and sequence matching, clustering, classification, reservoir computing, deep learning and data mining. Filippo is funded by the Norwegian Research Council over FRIPRO project on “Next Generation Learning Machines”. Latest research activities can be found at Filippo’s home page.
Sigurd Løkse works on robust kernel and information theoretic methods exploiting for example probabilistic cluster kernels as weak learners to build powerful similarity measures for ranking and spectral clustering. Sigurd works on aspects related to ensemble clustering, spectral clustering, Markov chains, and new approaches to missing data problems.
Kristoffer Wickstrøm is a master student at UiT The Arctic University of Norway working on polyp segmentation using fully convolutional neural networks. Area of interest includes machine learning and deep learning, with a special interest in convolutional neural networks. His supervisors are Michael Kampffmeyer, Karl Øyvind Mikalsen, and Robert Jenssen.
Andreas Storvik Strauman is a master student at UiT The Arctic University of Norway working on modeling of health data time series using recurrent neural networks. He is interested in many fields of machine learning, and hasn't really picked a favorite field. Yet. Supervised by Filippo Bianchi and Robert Jenssen.
Mads Adrian Hansen is working on the deep anchor framework. This framework combines so-called anchor learning with deep auto-encoders for feature extraction. The project's main focus is prediction of postoperative delirium based on unstructured text obtained from nurses notes. From the text, certain anchors are defined from which predictive models for postoperative delirium may be obtained based on basic natural language processing (NLP) tools. On top of this NLP representation, a deep auto-encoder extracts powerful features for the models to use. Promising results are submitted for publication. Supervised by Karl Øyvind Mikalsen​, Michael Kampffmeyer, Filippo Bianchi and Robert Jenssen.