Aims: High naevus counts, and UV photodamage are strong melanoma risk factors. However, whole-of-body measures fail to capture variability across body sites. Three-dimensional (3D) total body photography (TBP) and artificial intelligence (AI) allows the opportunity to automate the extraction of site-specific distributions of naevi and photodamage. This study combined 3D-TBP, AI, and unsupervised clustering in a high-risk cohort to identify distinct phenotypic patterns associated with melanoma.
Clinical Publications News
Three-dimensional (3D) total body photography (TBP) offers faster and enhanced skin visualization, potentially improving surveillance of high-risk skin cancer patients. This prospective longitudinal observational study (July 2021-December 2023) aimed to report the clinical outcomes of integrating 3D-TBP with digital dermoscopy for follow-up of high-risk melanoma patients.
Concerning early melanoma detection, dermatologists experience two major challenges: an overwhelming number of patients seeking total body skin examinations, and limited access to a standardized imaging system for monitoring their patients with increased risk for melanoma. This study introduces, for the first time, the concept of an independent imaging center utilizing a three-dimensional (3D) imaging system operated without a dermatologist present on site. The 3D scan performed in low-and mid-risk patients serves as a ‘TRIAGE scan’ to filter the patients who require a dermatology consultation. In high-risk patients, it functions as an ‘ASSIST scan’, assisting dermatologists during follow-up consultations.
Three-dimensional total body photography (3D TBP) is a new tool in dermatology, and its role and value in the diagnosis of skin conditions have been shown for skin malignancies with respectable diagnostic accuracies, but not for other skin diseases.
Background/Objectives: This study aims to evaluate and compare the diagnostic accuracy of skin lesion classification among three different classifiers: AI-based image classification, an expert dermatologist, and a non-expert. Given the rising interest in artificial intelligence (AI) within dermatology, it is crucial to assess its performance against human expertise to determine its viability as a reliable diagnostic tool.
Background: Specific phenotypic traits are known to be associated with an increased risk of developing melanoma. The latest 3-dimensional total body photography systems integrate machine learning tools that automatically describe patients’ skin lesions. The aim of the present study is to describe machine learning outcomes from 3-dimensional total body photography and assess their correlation with phenotypic characteristics.
Background: Skin examination through the Vectra WB360 imaging system promises to increase the diagnostic accuracy of melanoma and non-melanoma skin cancers, by early recognition of atypical lesions or detecion of changes within pre-existing ones. The purpose of our study is to assess the performance of the clinical AI algorithm integrated into the VECTRA WB360 examination system in detecting melanomas in high risk patients.
Importance: Diverse racial and ethnic representation in clinical trials has been limited, not representative of the US population, and the subject of pending US Food and Drug Administration guidance. Psoriasis presentation and disease burden can vary by skin pigmentation, race and ethnicity, and socioeconomic differences. Overall, there are limited primary data on clinical response, genetics, and quality of life in populations with psoriasis and skin of color (SoC). The Varying Skin Tones in Body and Scalp Psoriasis: Guselkumab Efficacy and Safety trial (VISIBLE) is underway and uses strategies aimed at addressing this persistent gap.
Artificial intelligence (AI) in dermatology has high accuracy in classifying skin cancer, particularly in collaboration with dermatologists. Although clinical studies have evaluated AI tools on both single-timepoint lesion images and sequential imaging data, they lack reporting on clinical utility in real-world settings. We retrospectively evaluate performances of 2 AI models for lesion change and malignancy risk assessment.
AI image classification algorithms have shown promising results when applied to skin cancer detection. Most public skin cancer image datasets are comprised of dermoscopic photos and are limited by selection bias, lack of standardization, and lend themselves to development of algorithms that can only be used by skilled clinicians. The SLICE-3D (“Skin Lesion Image Crops Extracted from 3D TBP”) dataset described here addresses those concerns and contains images of over 400,000 distinct skin lesions from seven dermatologic centers from around the world. De-identified images were systematically extracted from sensitive 3D Total Body Photographs and are comparable in optical resolution to smartphone images. Algorithms trained on lower quality images could improve clinical workflows and detect skin cancers earlier if deployed in primary care or non-clinical settings, where photos are captured by non-expert physicians or patients. Such a tool could prompt individuals to visit a specialized dermatologist. This dataset circumvents many inherent limitations of prior datasets and may be used to build upon previous applications of skin imaging for cancer detection.
