Dermal Radiomics: a new approach for computer-aided melanoma screening system

Skin cancer is the most common form of cancer in North America, and melanoma is the most dangerous type of skin cancer. Melanoma originates from melanocytes in the epidermis and has a high tendency to develop away from the skin surface and cause metastasis through the bloodstream. Early diagnosis is known to help improve survival rates. Under the current diagnosis, the initial examination of the potential melanoma patient is done via naked eye screening or standard photographic images of the lesion. From this, the accuracy of diagnosis varies depending on the expertise of the clinician. Radiomics is a recent cancer diagnostic tool that centers around the high throughput extraction of quantitative and mineable imaging features from medical images to identify tumor phenotypes. Radiomics focuses on optimizing a large number of features through computational approaches to develop a decision support system for improving individualized treatment selection and monitoring. While radiomics has shown great promise for screening and analyzing different forms of cancer such as lung cancer and prostate cancer, to the best of our knowledge, radiomics has not been previously adopted for skin cancer, especially melanoma. This work presents a dermal radiomics framework, which is a novel computer-aided melanoma diagnosis. While most computer-aided melanoma screening systems follow the conventional diagnostic scheme, the proposed work utilizes the physiological biomarker information. To extract physiological biomarkers, non-linear random forest inverse lightskin interaction model is proposed. The construction of dermal radiomics sequence is followed using the extracted physiological biomarkers, and the dermal radiomics framework for melanoma is completed by constructing diagnostic decision system based on random forest classification algorithm.