Computer-Aided Diagnosis of Melanoma Subtypes Using Reflectance Confocal Images

SIMPLE SUMMARY: Melanoma is a serious public health concern that causes significant illness and death, especially among young adults in Australia and New Zealand. Reflectance confocal microscopy is a non-invasive imaging technique commonly used to differentiate between different types of melanomas, but it requires specialized expertise and equipment. In this study, we used machine learning to develop classifiers for classifying patient image stacks between two types of melanoma. Our approach achieved high accuracy, demonstrating the utility of computer-aided diagnosis to improve expertise and access to reflectance confocal imaging among the dermatology community. ABSTRACT: Lentigo maligna (LM) is an early form of pre-invasive melanoma that predominantly affects sun-exposed areas such as the face. LM is highly treatable when identified early but has an ill-defined clinical border and a high rate of recurrence. Atypical intraepidermal melanocytic proliferation (AIMP), also known as atypical melanocytic hyperplasia (AMH), is a histological description that indicates melanocytic proliferation with uncertain malignant potential. Clinically and histologically, AIMP can be difficult to distinguish from LM, and indeed AIMP may, in some cases, progress to LM. The early diagnosis and distinction of LM from AIMP are important since LM requires a definitive treatment. Reflectance confocal microscopy (RCM) is an imaging technique often used to investigate these lesions non-invasively, without biopsy. However, RCM equipment is often not readily available, nor is the associated expertise for RCM image interpretation easy to find. Here, we implemented a machine learning classifier using popular convolutional neural network (CNN) architectures and demonstrated that it could correctly classify lesions between LM and AIMP on biopsy-confirmed RCM image stacks. We identified local z-projection (LZP) as a recent fast approach for projecting a 3D image into 2D while preserving information and achieved high-accuracy machine classification with minimal computational requirements.