Kivanc Kose

Kivanc Kose is an Adjunct Assistant Professor at Columbia GSAPP and works as a senior research scientist at Memorial Sloan Kettering Cancer Center. He received his M.Sc. and Ph.D. degrees in Electrical and Electronics Engineering from Bilkent University, Turkey. He joined the Optical Imaging Group in Dermatology Service at Memorial Sloan Kettering Cancer Center for his post-doctoral studies in 2012.

During his Ph.D., Dr. Kose was involved in the development of novel machine-learning methods for early sensing and modeling of fire and natural disasters that are threatening historical sites and forests. The developed system (FIRESENSE) involves camera-based vision systems and wireless sensor networks covering the perimetry of the heritage sites, aiming for early detection of fires and modeling their propagation. The test sites of deployment involved (i) Rhodiapolis, Antalya, Turkey, (ii) Dodge Hall at Bosphorus University, Istanbul, Turkey, (iii) Temple of Water, Djebel Zaghouan, Tunisia, (iv) Galceti Park, Prato, Italy, and (v) Kabeirion, Thebes, Greece. At the heart of his contributions lay the development of Artificial Intelligence- driven fire detection models, augmented by fire propagation simulations. These simulations integrated topographical, vegetation, and wind data, resulting in a holistic approach to forecasting wildfire propagation and facilitating swift intervention strategies. Supported by the European Union’s FP7-ENVIRONMENT - Specific Programme “Cooperation”: Environment (including Climate Change), Dr. Kose’s work was published in cultural heritage and photogrammetry conferences. He received the best paper award at EuroMed'12: Proceedings of the 4th International Conference on Progress in Cultural Heritage Preservation for his work on video-based early fire warning in cultural heritage preservation.

Upon joining MSKCC for his postdoctoral work, Dr. Kose’s research focus shifted towards developing machine learning and computer vision tools for skin cancer applications, aiming to significantly improve the early detection and treatment of cancer through novel imaging and AI-assisted diagnostic interpretation methods. Dr. Kose maintains his zeal for machine learning and AI in cultural heritage and art domains, continuously exploring related literature alongside his primary research focus.

An active member of the scientific community, Dr. Kose has authored more than a hundred articles in Journals and Conferences. He serves as Associate Editor at Signal Image and Video Processing Journal (SIVP) and reviews for journals and conferences in signal processing, computer vision, machine learning, and biomedical imaging. He’s received grants from the National Institutes of Health, the European Union, and others for AI and Image Processing work spanning Cultural Heritage Preservation to Biomedical Imaging.