Researchers compare existing approaches for automating diagnostic procedures of skin lesions

Aug 15 2018

The three prevalent skin cancers, according to the literature are melanoma, basal cell carcinoma and squamous cell carcinoma.

Melanoma is an archetype of skin cancer that typically result from an unpredictable disorder in the melanocytic cells, thus causing improper synthesis of the melanin. While melanoma might account for the least amongst the three aforementioned skin cancer types, it has, however, been umpired to account for 75-79% of skin cancer related deaths. Literature reports have it that Melanoma melanoma is the 5th most common cancer occurring amongst males, 7th most commonly occurring cancer in females, and 2nd most common form of cancer amongst young adults ranging from 15-29 years of age.

The above concerns have propelled the need to provide automated systems for medical diagnosis of skin cancer diseases within a strict time window, which means working towards reducing the unnecessary biopsies, increasing the speed of diagnosis and providing reproducibility of diagnostic results.

Okuboyejo and Olugbara, in their work, used have applied comparative analysis to review and compare the existing novel approaches for automating the diagnostic procedures of melanocytic skin lesions, including their success and shortcomings. These lesion images could either be microscopic (dermoscopic) or macroscopic (clinical) in nature. The authors have equally enlightened the research community on the homogeneous skin lesion diagnostic procedures frequently used in the research community. This work is particularly valuable for decision makers to consider tradeoffs between accuracy of diagnostic procedures versus complexity of the procedures. Recommendations such as the need to embrace feature selection optimization are made in order to reduce complexity and protracted computation. In addition, the authors proposed to favor a better classification model over the need to identify a large number of features required to discriminate between lesion categories.