三维全身摄影识别与晚发侵袭性黑色素瘤风险相关的皮肤表型
本研究纳入117例年龄>50岁确诊黑色素瘤的高危个体,采用三维全身摄影(3D-TBP)、人工智能和无监督聚类分析,识别出四种皮肤表型模式。严重光损伤且痣少者发生多发性侵袭性黑色素瘤的风险显著升高(PPR 2.00,95%CI 1.06-3.77),而中等光损伤者侵袭性黑色素瘤风险与痣数量正相关。
要点
- 3D-TBP联合AI可自动识别与侵袭性黑色素瘤风险相关的四种皮肤表型模式
- 严重光损伤且痣少者多发性侵袭性黑色素瘤风险升高(PPR 2.00)
- 中等光损伤者侵袭性黑色素瘤风险与痣数量正相关,且好发于大痣部位
核心结论
- 在晚发侵袭性黑色素瘤高危人群中,3D-TBP表型分析识别出四种皮肤表型模式,严重光损伤且痣少者多发性侵袭性黑色素瘤风险显著升高。
研究设计与样本
- 研究纳入117例年龄>50岁确诊黑色素瘤的澳大利亚高危个体,接受3D-TBP检查,采用基于密度的空间聚类(DBSCAN)识别部位特异性光损伤和痣计数表型模式。
主要发现
- 四种表型模式:中度V颈光损伤伴少痣(中位38,IQR 27-72)28例(24%);中度泛发光损伤伴数颗痣(中位155,IQR 90-259)31例(26%);中度V颈光损伤伴多痣(中位204)20例(17%);严重泛发光损伤伴少痣(中位37,IQR 21-72)38例(32%)。
- 最轻表型者受侵袭性黑色素瘤影响的可能性最低(PPR 1.51,95%CI 1.01-2.26),最重表型者受多发性侵袭性黑色素瘤影响的可能性更高(PPR 2.00,95%CI 1.06-3.77)。
- 原位黑色素瘤的患病率在各表型模式间一致;中度光损伤表型者中黑色素瘤更常见于大痣(>5 mm)部位(P<0.05),而严重光损伤表型者中黑色素瘤独立于痣(>2 mm)。
- 无黑色素瘤的对照队列(n=114)中仅18例(15.8%)匹配高危表型模式。
关键数值与推荐
- 侵袭性黑色素瘤风险与表型模式相关:最轻表型PPR 1.51(95%CI 1.01-2.26),最重表型多发性侵袭性黑色素瘤PPR 2.00(95%CI 1.06-3.77)。
- 中度光损伤表型者中黑色素瘤更常见于大痣(>5 mm)部位(P<0.05);严重光损伤表型者中黑色素瘤独立于痣(>2 mm)。
临床怎么用
- 3D-TBP联合AI可自动识别皮肤表型模式,有助于对侵袭性黑色素瘤进行细致风险分层和个体化监测。
- 对于中等光损伤者,应重点关注痣数量及大痣部位;对于严重光损伤且痣少者,应警惕多发性侵袭性黑色素瘤风险。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: High naevus counts and ultraviolet photodamage are strong risk factors for melanoma. However, whole-of-body measures fail to capture variability across body sites. Three-dimensional total body photography (3D-TBP) and artificial intelligence (AI) allow us the opportunity to automate the extraction of site-specific distributions of naevi and photodamage. OBJECTIVES: To identify distinct phenotypic patterns associated with melanoma in a cohort of people at high risk of advanced melanoma, using combined 3D-TBP, AI and unsupervised clustering. METHODS: Participants with a history of melanoma (diagnosed aged > 50 years) underwent 3D-TBP. Site-specific photodamage and naevus counts were assessed using density-based spatial clustering of applications with noise to identify body site-dependent phenotypic patterns. Melanoma prevalence (none, single, multiple) relative to phenotypic pattern was evaluated using population prevalence ratios (PPRs). RESULTS: Analysis of 117 individuals found four phenotypic patterns of increasing severity: moderate V-neck photodamage with few naevi [median 38; interquartile range (IQR) 27-72] in 28 patients (24%); moderate generalized photodamage with several naevi (median 155; IQR 90-259) in 31 patients (26%); moderate V-neck photodamage with many naevi (median 204) in 20 patients (17%); and severe generalized photodamage with few naevi (median 37; IQR 21-72) naevi in 38 patients (32%). No individuals had severe photodamage and several-to-many naevi. Interpattern comparisons revealed that participants with the mildest phenotypic pattern were least likely to be affected by invasive melanomas [PPR 1.51, 95% confidence interval (CI) 1.01-2.26], whereas those with the most severe phenotypic pattern were more likely to be affected by multiple invasive melanomas (PPR 2.00, 95% CI 1.06-3.77). The prevalence of melanoma in situ was consistent across patterns. Melanoma was more likely at sites of large naevi (> 5 mm; P < 0.05) in those with moderate photodamage patterns but were independent of naevi (> 2 mm) in individuals with severe photodamage patterns. From a control cohort unaffected by melanoma (n = 114), only 18 (15.8%) matched with a high-risk phenotypic pattern. CONCLUSIONS: Three-dimensional TBP phenotyping of an older Australian cohort at high risk of invasive melanoma revealed four distinct phenotypic patterns associated with risk of the disease. Individuals with severe photodamage and relatively few naevi had a significantly higher risk of developing multiple invasive melanomas. For individuals with moderate photodamage, the risk of invasive melanoma was positively associated with the number of naevi. Thus, comprehensive phenotypes may be more predictive for the diagnosis and site of invasive melanoma, which may help with nuanced risk stratification and customized surveillance. Melanoma is a rare but serious type of skin cancer. Finding melanoma at an early stage means patients may have a better outcome. People at high risk of developing melanoma often have regular skin checks to look for signs of the disease. For example, moles and sun damage are associated with an increased risk of melanoma. Doctors visually assess the number of moles and sun damage to assess risk and decide how patients are monitored. In this study, we wanted to find out whether the location of moles and sun damage was associated with the risk of melanoma. Using 3D photography, we constructed digital avatars of people diagnosed with melanoma. The patients were all older than 50 years of age. We found four distinct patterns. The first pattern involved only a few moles with moderate sun damage. The second involved a few moles with severe sun damage. The third pattern was several moles with moderate generalized sun damage. Finally, the fourth pattern was lots of moles with moderate sun damage. No people had severe sun damage and lots of moles. We also found that a type of melanoma called ‘invasive melanoma’ was more common in people with a high number of moles and sun damage. However, rates of another type of melanoma called ‘non-invasive melanoma’ were not affected by the number of moles or amount of sun damage. For people with moderate sun damage, melanoma was more likely to occur in areas where there were higher numbers of large moles. But, in people with severe sun damage, the mole count at specific sites did not predict melanoma. Our findings suggest that sun damage and where moles are around the body might help doctors tailor how they assess the risk of melanoma in people. Distinctive patterns could be found automatically with 3D photography and AI, or recognized by an experienced doctor. This information could identify people and body sites at greatest risk for invasive melanoma. It would allow for screening and surveillance to be customized for an individual patient.
引用
- Kahler S, Primiero C, Mothershaw A, et al. Three dimensional total body photography identifies cutaneous phenotypes associated with late-onset invasive melanoma risk. Br J Dermatol. 2026. PMID: 41183492. doi:10.1093/bjd/ljaf440
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。