Kivanc Kose

Assistant Lab Member
Kivanc Kose

I’m a researcher who is a part of the Dermatology Service at Memorial Sloan Kettering Cancer Center (MSK).

I have extensive experience in developing quantitative image analysis and using artificial intelligence (AI) tools for the non-invasive diagnosis of skin diseases. I am an expert in using machine learning, computer vision, and signal processing, for dermatological imaging.

This includes using tools such as dermoscopy, clinical imaging, and total body photography. It also includes microscopic tools such as reflectance confocal microscopy (RCM), an imaging technology that uses laser light to look at your skin cells. All these tools help us detect skin cancers and other skin conditions.

I have a proven track record of leading and contributing to large, federally funded international research projects and translating novel algorithms from the lab into clinical practice.

Education

PhD, Signal Processing, Bilkent University, Turkey
Master of Science, Signal Processing, Bilkent University, Turkey
Bachelor of Science, Electrical & Electronics Engineering, Bilkent University, Turkey

Publications

  1. Kurtansky, N.R., Gillis, M.C., Codella, N.C.F. et al. Automated triage of cancer-suspicious skin lesions with 3D total-body photography. npj Digit. Med. 8, 708 (2025).
  2. Kentley J, Kurtansky N, Jain M, … Kose K. Non-invasive diagnosis of melanoma using machine learning and reflectance confocal microscopy. Journal of Investigative Dermatology. 2025.
  3. Kose K, Bozkurt A, Alessi-Fox C, et al. Segmentation of cellular patterns in confocal images of melanocytic lesions in vivo via a multiscale encoder-decoder network (MED-Net). Med Image Anal. 2020;67:101841.
  4. Kose K, Gou M, Yélamos O, et al. Automated video-mosaicking approach for confocal microscopic imaging in vivo: an approach to address challenges in imaging living tissue and extend field of view. Sci Rep. 2017;7(1):10759.
  5. Kurtansky NR, D’Alessandro BM, Gillis MC, … Kose K, et al. The SLICE-3D dataset: 400,000 skin lesion image crops extracted from 3D TBP for skin cancer detection. Sci Data. 2024;11:884.