文献速递皮肤肿瘤

基于全切片图像深度学习的皮肤黑色素瘤风险评分分层

Risk score stratification of cutaneous melanoma patients based on whole slide images analysis by deep learning.
PubMed 文献 · J Eur Acad Dermatol Venereol · 2025-01-24

研究开发了弱监督深度学习模型SmartProg-MEL,从HE染色全切片图像预测I-III期皮肤黑色素瘤患者5年总生存并分配风险评分。模型在发现队列(n=342)训练验证,并在两个外部队列(n=161和n=63)测试,c-index为0.69-0.78,多因素分析中为独立且最强预后因素(HR=1.84,p<0.005),可将患者分为5年OS显著不同的低危和高危组。

要点

  • SmartProg-MEL从HE全切片图像自动预测黑色素瘤5年OS并分层风险。
  • 外部验证c-index为0.69和0.71,优于现有临床病理因素。
  • 多因素分析中模型为独立最强预后因素(HR=1.84,p<0.005)。

核心结论

  • 全自动SmartProg-MEL模型在预测5年OS和风险分层方面优于当前临床病理因素。
  • 将SmartProg-MEL纳入临床流程可能通过改善识别可从辅助治疗获益的患者来指导决策。

研究设计与样本

  • 研究设计弱监督深度学习模型SmartProg-MEL,从HE染色全切片图像提取形态特征预测5年OS并分配生存风险评分。
  • 模型在发现队列IHP-MEL-1(n=342)训练和验证,在两个外部独立数据集IHP-MEL-2(n=161)和TCGA队列(n=63)测试。
  • 性能与成熟预后因素比较,使用一致性指数(c-index)作为指标。

主要发现

  • 在发现队列,SmartProg-MEL预测5年OS的c-index在交叉验证数据为0.78,在交叉测试系列为0.72。
  • 在外部队列,模型在IHP-MEL-2和TCGA数据集的c-index分别为0.71和0.69。
  • 多因素分析中SmartProg-MEL为独立且最强预后因素(HR=1.84,p<0.005)。
  • 模型可将患者分为低危和高危两组,两组5年OS显著不同(IHP-MEL-1 p<0.001;IHP-MEL-2 p=0.01)。

临床怎么用

  • 模型可辅助识别可能从辅助治疗获益的皮肤黑色素瘤患者。
  • 基于HE全切片图像的自动风险评分可作为现有临床病理因素的补充。

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: There is a need to improve risk stratification of primary cutaneous melanomas to better guide adjuvant therapy. Taking into account that haematoxylin and eosin (HE)-stained tumour tissue contains a huge amount of clinically unexploited morphological informations, we developed a weakly-supervised deep-learning approach, SmartProg-MEL, to predict survival outcomes in stages I to III melanoma patients from HE-stained whole slide image (WSI). METHODS: We designed a deep neural network that extracts morphological features from WSI to predict 5-y overall survival (OS), and assign a survival risk score to each patient. The model was trained and validated on a discovery cohort of primary cutaneous melanomas (IHP-MEL-1, n = 342). Performance was tested on two external and independent datasets (IHP-MEL-2, n = 161; and TCGA cohort n = 63). It was compared with well-established prognostic factors. Concordance index (c-index) was used as a metric. RESULTS: On the discovery cohort, the SmartProg-MEL predicts the 5-y OS with a c-index of 0.78 on the cross-validation data and of 0.72 on the cross-testing series. In the external cohorts, the model achieved a c-index of 0.71 and 0.69 for the IHP-MEL-2 and TCGA dataset respectively. Furthermore, SmartProg-MEL was an independent and the most powerful prognostic factor in multivariate analysis (HR = 1.84, p-value < 0.005). Finally, the model was able to dichotomize patients in two groups-a low and a high-risk group-each associated with a significantly different 5-y OS (p-value < 0.001 for IHP-MEL-1 and p-value = 0.01 for IHP-MEL-2). CONCLUSIONS: The performance of our fully automated SmartProg-MEL model outperforms the current clinicopathological factors in terms of prediction of 5-y OS and risk stratification of cutaneous melanoma patients. Incorporation of SmartProg-MEL in the clinical workflow could guide the decision-making process by improving the identification of patients that may benefit from adjuvant therapy.

来源:J Eur Acad Dermatol Venereol,查看原文。版权归原作者所有。

引用

  1. Bossard C, Salhi Y, Khammari A, et al. Risk score stratification of cutaneous melanoma patients based on whole slide images analysis by deep learning. J Eur Acad Dermatol Venereol. 2025. PMID: 39853986. doi:10.1111/jdv.20538

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。