SICSURFIS: Spectral Imaging of Complex Surface Tomographies

Main result

Main result of the whole consortium was non-invasive hyperspectral imaging system, which involves shape and depth data analysis by convolutional neural networks. The imager is feasible for differentiating between malignant and benign pigmented and non-pigmented skin tumours, even on complex skin surfaces.

• JYU: User interface for spectral imager
• JYU: Processing pipeline and AI method for 3D spectral data
• VTT: Further development of metallic mirror based MEMS Fabry-Perot technology (US 2022/0091471 )
• VTT: developed the Led light source and FPI based hyperspectral camera which was used in clinical studies at HUS.
• Hospital: Several pilot studies with different lesion types were conducted (including melanomas, pigmented and intradermal nevi, basal cell  and  squamous cell carcinomas),
• Vaasa University: FPGA processing for FPI data was developed
   

Main personnel

• University of Jyväskylä : Ilkka Pölönen, Leevi Annala, Anna-Maria Raita-Hakola, Sampsa Kiiskinen, Samuli Rahkonen
• HUS: Annamari Ranki, Sari Pitkänen Kirsi Isoherranen, Sari Koskenmies, Vivian Lindholm, Mari Salmivuori
• VTT: Heikki Saari, Martti Blomberg, Sari Elomaa, Harri Ojanen, Kari Rainio, Ingmar Stuns, Kristiina Rutanen and Kirsi Järvi
• Vaasa University: Jarmo Alander, Vladimir Bochko, Severi Sutinen
• Large number of assisting personnel from several HUS and JYU has also participated to the project