STOCKHOLM – Oct. 18, 2016 – ContextVision, a medical technology company specializing in image analysis and artificial intelligence, placed top three among automated image analysis in the Tumor Proliferation Assessment Challenge (TUPAC) 2016 competition with its SLDESUTO partner (HES-SO). Many prestigious teams participated, including both highly reputable academic teams and research groups from companies like IBM and Microsoft. Participating teams were given a dataset of whole slide images, and one of the tasks was to assess tumor proliferation speed by applying machine learning algorithms.
“We achieved good results by applying deep learning, which is a hot technology within artificial intelligence,” said Anita Tollstadius, ContextVision CEO. “While many companies are in the process of learning the technology, ContextVision has invested in moving to the forefront of knowledge in deep learning and artificial intelligence. This result proves that we have developed our skills to reach an international top level. We really are on track for developing our platform within digital pathology”, said Tollstadius.
The tumor proliferation speed (tumor growth) is an important biomarker indicative of breast cancer patients’ prognosis. Breast cancer patients with high tumor proliferation speed have worse outcomes compared to patients with low tumor proliferation speed. Thus, the assessment of this biomarker influences the decisions for the treatment plan of the patient.
“The participation in this challenge on digital pathology images from breast cancer marks a broadening of our present scope for the SLDESUTO project within digital pathology,” Tollstadius said.
The competition was organized by the 19th International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI) at the InterContinental Athenaeum Hotel in Athens.
For further information, please contact ContextVision’s CEO, Anita Tollstadius, at +46 70 337 30 26.
The SLDESUTO project received funding from the Eurostars-2 Joint Program with co-funding from the European Union’s Horizon 2020 research and innovation program. This is a joint project between ContextVision AB, in Linköping, Sweden and the eHealth unit of HES-SO, University of Applied Sciences Western Switzerland in Sierre, Switzerland. State-of-the-art machine learning algorithms including deep learning will be used to train the software to automatically recognize, identify and classify abnormal patterns in digital images with a variety of pathologies. The purpose of this project is to use unique technology and knowledge to develop a Decision Support Toolbox (DST), that will support the pathologists in their challenging task to diagnose and evaluate the prognosis of different types of cancer.
ContextVision is a medical technology company specializing in image analysis and image processing. Its cutting-edge technology helps doctors more accurately interpret medical images, a crucial foundation for better diagnosis and treatment. As an industry pioneer for more than 30 years, ContextVision has decided to take a lead position within deep learning, the latest technology within artificial intelligence. ContextVision is currently investing heavily in this field to develop a broader product portfolio. The present product portfolio includes state-of-the-art image enhancement software for 2D/3D/4D ultrasound, MRI, X-ray and mammography and 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 www.contextvision.com.