STOCKHOLM – May 18th, 2018 – ContextVision, a medical technology software company specializing in image analysis and artificial intelligence, and its academic partners at Uppsala University and Uppsala Hospital have been awarded a grant from Sweden’s innovation agency, Vinnova, for a continuation of a research program within digital pathology research. The company has already achieved very encouraging results in preliminary studies. The grant will cover costs at the hospital and at Uppsala University.
“We are very pleased to develop this collaboration with lung pathology experts such as Associate Professor Patrick Micke and his team,” said Anita Tollstadius, CEO at ContextVision. “Through this collaboration, we will be able to use a unique set of data for training algorithms in our deep learning network and thereby we will be able to develop highly specific algorithms. This is an ideal way to start a new research project within digital pathology.”
One of four cancer deaths are due to lung cancer
The market need for better and faster diagnosis of lung cancer is extensive. Currently, about one of four cancer deaths are due to lung cancer, both globally and in Sweden. Lung cancer is often first indicated by a chest scan (CT), but the final diagnosis has to be made on a tissue biopsy. Thus, the evaluations made by the pathologists provide the basis for the diagnosis and determines the treatment. The distinction between histological subtypes is important for the chemotherapeutic selection. Some agents are contraindicative with decreased efficacy and increased toxicity if used on the wrong subtype.
The evaluation of lung tissue pathology is complex, challenging and time-consuming for the pathologist. In addition, there is a lack of trained specialist pathologists both in Sweden and globally.
“This means that patients sometimes have to wait overlong for the results, and treatment can even be delayed. So, there is a great need for a digital pathology tool within lung cancer,” said Associate Professor Patrick Micke
Incomplete and inaccurate diagnosis
Today’s manual assessment is highly subjective and studies have shown that depending on each pathologist’s individual competence, experience and skill, there is a significant inter and intra-individual variation.
At the same time, the demand in cancer diagnostics is constantly increasing, as new therapy options and treatment modalities in clinical oncology require more detailed and therefore time-consuming diagnosis.
“Lung cancer represents a particular challenge as lung tumours are difficult to assess and tissue can only be procured as small biopsies in the range of few square millimetres,” said Tollstadius.
ContextVision is a medical technology company specializing in image analysis and artificial intelligence. Its cutting-edge technology helps doctors accurately interpret medical images, a crucial foundation for better diagnosis and treatment. As an industry pioneer for more than 30 years, ContextVision is taking a leading position within deep learning, the latest artificial intelligence technology. ContextVision is currently investing significantly in the field to expand its product portfolio. The present product portfolio includes state-of-the-art image enhancement software for 2D/3D/4D ultrasound, MRI, X-ray and mammography which is used by leading equipment manufacturers worldwide. ContextVision is based in Sweden and listed on the Oslo Stock Exchange under the ticker COV. For more information, please visit http://www.contextvision.com.
About the Clinical Pathology and Cytology unit at Uppsala University Hospital
The Clinical Pathology and Cytology unit at Uppsala University Hospital, represents the requirement owner of the solution, and is a tertiary care centre with a long expertise in lung cancer treatment. Associate Professor Patrick Micke (MD, PhD), is a consultant pathologist in lung diagnostics at the clinical unit, the group leader and principal investigator (PI) of the integrative lung cancer pathology group at the Department of Immunology, Genetics and Pathology at Uppsala University, a leading centre for translational lung cancer research in Sweden. The group has access to scanned images of tissue samples (biopsies or resected specimens) to test and to validate the development of a deep learning (DL) network-based tool for digital pathology evaluations.
The Human Protein Atlas (HPA) 3 at Uppsala University is a scientific research program started 2003 with the aim to comprehensively generate a complete map of the human proteome using an integrated omics approach. Dr Cecilia Lindskog Bergström is heading the Uppsala site, which has evaluated tenth of thousands of human tissue samples from a large set of normal and cancer tissue microarrays (TMAs) generated within the project. The group has extensive histopathological expertise and resources including tissue sectioning, production of microarrays and high-resolution scanning and digital archiving. Dr Lindskog Bergström has been involved in the HPA project for more than 10 years.
Vinnova is Sweden’s innovation agency. Its mission is to promote sustainable growth by improving the conditions for innovation, as well as funding needs-driven research. Vinnova’s vision is for Sweden to be a world-leading country in research and innovation, an attractive place in which to invest and conduct business. The agency promotes collaborations between companies, universities, research institutes and the public sector.