�鶹��Ʒ��Ƶ

Skin cancer is the most common cancer in the U.S., but distinguishing cancerous lesions from benign growths can be challenging without a biopsy. �鶹��Ʒ��Ƶ researchers are exploring a non-invasive approach that combines Raman spectroscopy, which provides a molecular fingerprint of tissue, with machine learning to identify skin cancer. Using a handheld Raman system, they analyzed nearly 1,000 spectra from more than 50 samples of normal skin, basal cell carcinoma and squamous cell carcinoma.

Results of the study, published in the Proceedings of SPIE, showed that the strongest machine-learning models correctly classified the three tissue types about 81% to 84% of the time. The researchers also found that the models were better at distinguishing cancerous tissue from normal skin than at differentiating basal cell carcinoma from squamous cell carcinoma. The preliminary findings demonstrate promise for a rapid, non-invasive diagnostic tool. Larger studies and more advanced machine-learning techniques are needed to improve accuracy before the approach can be used clinically.

“The promise of this technology is that it could give clinicians another way to look beneath the surface of a skin lesion without immediately having to remove tissue,” said Andrew Terentis, Ph.D., senior author, professor and chair, Department of Chemistry and Biochemistry, �鶹��Ʒ��ƵCharles E. Schmidt College of Science. “By combining the molecular information provided by Raman spectroscopy with machine learning, we are beginning to see how subtle differences in tissue chemistry can be used to distinguish cancer from normal skin.”

Read the press releasefor this story.