Machine Learning in Melanoma Diagnosis. Limitations About to be Overcome

A Narrative Review: Opportunities and Challenges in Artificial Intelligence Skin Image Analyses Using Total Body Photography

Artificial intelligence (AI) algorithms for skin lesion classification have reported accuracy at par with and even outperformance of expert dermatologists in experimental settings. However, the majority of algorithms do not represent real-world clinical approach where skin phenotype and clinical background information are considered. We review the current state of AI for skin lesion classification and present opportunities and challenges when applied to total body photography (TBP). AI in TBP analysis presents opportunities for intrapatient assessment of skin phenotype and holistic risk assessment by incorporating patient-level metadata, although challenges exist for protecting patient privacy in algorithm development and improving explainable AI methods.

A protocol for annotation of total body photography for machine learning to analyze skin phenotype and lesion classification

Introduction

Artificial Intelligence (AI) has proven effective in classifying skin cancers using dermoscopy images. In experimental settings, algorithms have outperformed expert dermatologists in classifying melanoma and keratinocyte cancers. However, clinical application is limited when algorithms are presented with 'untrained' or out-of-distribution lesion categories, often misclassifying benign lesions as malignant, or misclassifying malignant lesions as benign. Another limitation often raised is the lack of clinical context (e.g., medical history) used as input for the AI decision process. The increasing use of Total Body Photography (TBP) in clinical examinations presents new opportunities for AI to perform holistic analysis of the whole patient, rather than a single lesion. Currently there is a lack of existing literature or standards for image annotation of TBP, or on preserving patient privacy during the machine learning process.

Methods

This protocol describes the methods for the acquisition of patient data, including TBP, medical history, and genetic risk factors, to create a comprehensive dataset for machine learning. 500 patients of various risk profiles will be recruited from two clinical sites (Australia and Spain), to undergo temporal total body imaging, complete surveys on sun behaviors and medical history, and provide a DNA sample. This patient-level metadata is applied to image datasets using DICOM labels. Anonymization and masking methods are applied to preserve patient privacy. A two-step annotation process is followed to label skin images for lesion detection and classification using deep learning models. Skin phenotype characteristics are extracted from images, including innate and facultative skin color, nevi distribution, and UV damage. Several algorithms will be developed relating to skin lesion detection, segmentation and classification, 3D mapping, change detection, and risk profiling. Simultaneously, explainable AI (XAI) methods will be incorporated to foster clinician and patient trust. Additionally, a publicly released dataset of anonymized annotated TBP images will be released for an international challenge to advance the development of new algorithms using this type of data.

Conclusion

The anticipated results from this protocol are validated AI-based tools to provide holistic risk assessment for individual lesions, and risk stratification of patients to assist clinicians in monitoring for skin cancer.

Interpretability of a Deep Learning Based Approach for the Classification of Skin Lesions into Main Anatomic Body Sites

Over the past few decades, different clinical diagnostic algorithms have been proposed to diagnose malignant melanoma in its early stages. Furthermore, the detection of skin moles driven by current deep learning based approaches yields impressive results in the classification of malignant melanoma. However, in all these approaches, the researchers do not take into account the origin of the skin lesion. It has been observed that the specific criteria for in situ and early invasive melanoma highly depend on the anatomic site of the body. To address this problem, we propose a deep learning architecture based framework to classify skin lesions into the three most important anatomic sites, including the face, trunk and extremities, and acral lesions. In this study, we take advantage of pretrained networks, including VGG19, ResNet50, Xception, DenseNet121, and EfficientNetB0, to calculate the features with an adjusted and densely connected classifier. Furthermore, we perform in depth analysis on database, architecture, and result regarding the effectiveness of the proposed framework. Experiments confirm the ability of the developed algorithms to classify skin lesions into the most important anatomical sites with 91.45% overall accuracy for the EfficientNetB0 architecture, which is a state-of-the-art result in this domain.

Diagnosis and Management of Lentigo Maligna: Clinical Presentation and Comprehensive Review

Lentigo maligna (LM), also known as Hutchinson's melanotic freckle, is a form of in situ melanoma characterized by the proliferation of atypical melanocytes along the basal epidermis in sun-damaged skin. If left untreated, LM will progress to lentigo maligna melanoma (LMM), a form of invasive melanoma with the same prognosis as other forms of invasive melanoma. LM is more common in the elderly, with a peak occurrence between the ages of 65 and 80 years. LM, however, is rarely present on the trunk and extremities. The diagnosis of LM, confirmed by histopathological and biopsy examination, is based on clinical and dermoscopic features. It typically begins as a tan-brown macule or patch, but it can progress to a variegated pigmentation with dark black color or even amelanotic characteristics. The risk factors involved in the LM development include a history of sunburns, lighter skin types, advanced age, history of nonmelanoma skin cancers, and tendency to form solar lentigines. This article explains the clinical presentation of LM, also reviews the available information on the diagnosis and management of LM, and discusses the potential of such information in facilitating the future prospective.

Lentigo Maligna: Clinical Presentation and Appropriate Management

Lentigo maligna (LM) is a type of melanoma in situ that has distinctive characteristics regarding epidemiology, risk factors and clinical features. In addition, LM has a potential to progress to an invasive tumor with potentially aggressive behavior: lentigo maligna melanoma (LMM). Overall, LM has a very good prognosis, whereas LMM has the same prognosis as other invasive melanomas with similar Breslow thickness. LM/LMM represents a challenging entity not only regarding the diagnosis but also regarding the management. Diagnostic criteria are not well established, and there is an overlap of clinical, dermoscopic and pathological features with other benign pigmented skin lesions such as lentigines, pigmented actinic keratoses or macular seborrheic keratoses. LM/LMM's common appearance within photodamaged skin makes lesion border identification difficult. Wide excisions are often required, but since LM/LMM typically appears on cosmetically sensitive areas such as the face, sometimes large excisions are not possible nor desirable. In this sense, specialized approaches have been developed such as margin-controlled surgery or image-guided treatment using reflectance confocal microscopy. Other treatments for LM such as cryosurgery, imiquimod, radiotherapy or photodynamic therapy have been proposed, although recurrence/persistence is common. The current manuscript reviews extensively the published data regarding the diagnosis, treatment and management of both complex entities LM and LMM.