Judging Melanoma Thickness: Comparison of Dermatologists and Machine-Learning Algorithm
Assessing the thickness of melanoma is difficult—whether done by an experienced dermatologist or a well-trained machine-learning algorithm. A study published by Polesie et al in the Journal of the European Academy of Dermatology and Venereology showed that an algorithm and a group of approximately 400 dermatologists had an equal success rate in interpreting dermoscopic images.
In diagnosing melanoma, dermatologists evaluate whether it is invasive, where the cancer cells grow down into the dermis and there is a risk of metastasis, or in situ, which develops in the outer skin layer (the epidermis) only. Invasive melanomas that grow deeper than 1 mm into the skin are considered thick and thus more aggressive.
Melanomas are assessed by investigation with a dermatoscope, a type of magnifying glass fitted with a bright light. Diagnosing melanoma is often relatively simple, but estimating its thickness is a much greater challenge.
“As well as providing valuable prognostic information, the thickness may affect the choice of surgical margins for the first operation and how promptly it needs to be performed,” said first study Sam Polesie, MD, PhD, Associate Professor (Docent) of Dermatology and Venereology at Sahlgrenska Academy, University of Gothenburg. Dr. Polesie is also a dermatologist at Sahlgrenska University Hospital.
Algorithm vs Dermatologist
Using a web platform, 438 international dermatologists assessed nearly 1,500 melanoma images captured with a dermatoscope. The dermatologists’ results were then compared with those from a machine-learning algorithm trained in classifying melanoma depth.
Among the dermatologists, overall accuracy was 63% for correct classification of melanoma in situ, and 71% for that of invasive melanomas.
“Interestingly, professional background and experience in dermoscopy had no bearing on diagnostic accuracy in predicting melanoma thickness. The area under the curve (AUC)… was 0.83 for the pretrained machine learning algorithm and 0.85 for the combined AUC of the individual readers. Collectively, the dermatologists’ assessment performed on par with an algorithm trained in distinguishing melanoma in situ and invasive melanomas,” said Dr. Polesie.
“Our study highlights the difficulties of correctly assessing melanoma thickness on the basis of dermoscopic images,” Dr. Polesie continued. “In future studies, we aim to explore the usefulness of predefined dermoscopic structures… We also want to test whether clinical decision-making in this situation can be improved by means of machine-learning algorithms.”
Disclosure: For full disclosures of the study authors, visit onlinelibrary.wiley.com.The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.