Abstract
Malignant melanoma is by far the most dangerous type of skin cancer. Currently, the gold standard to diagnose melanoma in the clinic is excisional biopsy and histopathologic analysis. Approximately 15-30 benign lesions are biopsied to diagnose each melanoma. Additionally, biopsies are invasive and result in pain, anxiety, scarring and disfigurement of patients, and they can be a financial burden to the health care system. Among several imaging techniques developed to enhance melanoma diagnosis, optical coherence tomography (OCT) with its high-resolution and intermediate penetration depth can potentially provide required diagnostic information, noninvasively. We propose an image analysis algorithm, ‘optical properties extraction (OPE)’ that drastically improves the specificity and sensitivity of OCT by identifying unique optical radiomic signatures pertinent to melanoma detection. We evaluate the performance of the algorithm using several tissue-mimicking phantoms. We then test the OPE algorithm with sixty-nine human subjects and demonstrate that melanoma can be differentiated from benign nevi with 97% sensitivity, and 98% specificity.
© 2019 SPIE/OSA
PDF ArticleMore Like This
Aditi Sahu, Aundree Hermawan, Melissa Gill, Ucalene Harris, Thomas Reiner, Ashfaq Marghoob, M. Cecelia Lezcano, Anthony Rossi, Allan Halpern, Klaus Busam, Chih-Shan Jason Chen, Manu Jain, and Milind Rajadhyaksha
TW3B.4 Clinical and Translational Biophotonics (Translational) 2022
Katrina Bolochko, Dmitrijs Bliznuks, Dilshat Uteshev, Ilze Lihacova, Alexey Lihachev, Yuriy Chizhov, and Andrey Bondarenko
11074_66 European Conference on Biomedical Optics (ECBO) 2019
Karen M. Reiser, Lyudmila Gulyaeva, S.V. Sidirov, and André Knoesen
FTuO4 Frontiers in Optics (FiO) 2007