3D Whole‐body skin imaging for automated melanoma detection

Abstract

Background Existing artificial intelligence for melanoma detection has relied on analysing images of lesions of clinical interest, which may lead to missed melanomas. Tools analysing the entire skin surface are lacking. Objectives To determine if melanoma can be distinguished from other skin lesions using data from automated analysis of 3D‐images. Methods Single‐centre, retrospective, observational convenience sample of patients diagnosed with melanoma at a tertiary care cancer hospital. Eligible participants were those with a whole‐body 3D‐image captured within 90 days prior to the diagnostic skin biopsy. 3D‐images were obtained as standard of care using VECTRA WB360 Whole Body 3‐dimensional Imaging System (Canfield Scientific). Automated data from image processing (i.e. lesion size, colour, border) for all eligible participants were exported from VECTRA DermaGraphix research software for analysis. The main outcome was the area under the receiver operating characteristic curve (AUC). Results A total of 35 patients contributed 23,538 automatically identified skin lesions >2 mm in largest diameter (102–3021 lesions per participant). All were White patients and 23 (66%) were males. The median (range) age was 64 years (26–89). There were 49 lesions of melanoma and 22,489 lesions that were not melanoma. The AUC for the prediction model was 0.94 (95% CI: 0.92–0.96). Considering all lesions in a patient‐level analysis, 14 (28%) melanoma lesions had the highest predicted score or were in the 99th percentile among all lesions for an individual patient. Conclusions In this proof‐of‐concept pilot study, we demonstrated that automated analysis of whole‐body 3D‐images using simple image processing techniques can discriminate melanoma from other skin lesions with high accuracy. Further studies with larger, higher quality, and more representative 3D‐imaging datasets would be needed to improve and validate these results.

Performance of Commercial Dermatoscopic Systems That Incorporate Artificial Intelligence for the Identification of Melanoma in General Practice: A Systematic Review

“…Three articles [35,37,38] reported 3D TBP in clinical settings. Two of these studies [35,37] had small participant numbers, ranging from n = 6 to 10 participants with MM and n = 55 to 65 participants with an otherwise benign diagnosis.…”

“…Of these two studies, one study [37] reported an AUROC value of 0.92. One study [38] followed a different methodology and did not report values for sensitivity, specificity and accuracy. However, the AUROC was reported (0.9399) and was included (Table 2).…”

Melanoma is not just one disease, but many

“…Several papers of this issue highlight new and established technologies to improve medical care. [3][4][5][6] Still, we are all aware that certain grey zones will remain.…”

“…Fundamental for achieving treatment precision is diagnostic accuracy. Several papers of this issue highlight new and established technologies to improve medical care 3–6 . Still, we are all aware that certain grey zones will remain.…”

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

“…To date, a limited number of AI models in dermatology have been applied to TBP or wide-field photography ( 12 , 13 ). TBP for skin cancer monitoring provides the advantage of objectively capturing the entire skin surface and ability to compare sequential images between appointments.…”