融合色素性病变不对称性特征算法与卷积神经网络集成用于黑色素瘤检测
该研究基于国际皮肤成像协作组织2019数据集(6296例痣,1361例黑色素瘤),将反映病变颜色不对称的专家手工特征输入人工神经网络,并与7个先进卷积神经网络的集成结果进行平均融合。融合方法在黑色素瘤检测中达到曲线下面积0.942、敏感性92%、特异性82%,优于单独使用任一方法。
要点
- 融合专家不对称性特征与卷积神经网络集成可提升黑色素瘤检测性能。
- 融合模型AUC 0.942、敏感性92%、特异性82%。
- 将皮肤科医生的知识与深度学习结合具有临床转化潜力。
核心结论
- 融合皮肤科医生知识(颜色不对称特征)与卷积神经网络集成对黑色素瘤检测表现出高性能。
研究设计与样本
- 研究在国际皮肤成像协作组织2019数据集的子集(6296例痣,1361例黑色素瘤)上进行实验。
- 设计基于病变内颜色不对称的手工专家特征,输入人工神经网络分类痣与黑色素瘤。
- 与7个先进卷积神经网络的集成结果比较,并通过计算平均预测值融合两种方法。
主要发现
- 基于不对称性的人工神经网络达到曲线下面积0.873、敏感性90%、特异性67%。
- 卷积神经网络方法达到曲线下面积0.938、敏感性91%、特异性82%。
- 两种方法融合达到曲线下面积0.942、敏感性92%、特异性82%。
临床怎么用
- 将皮肤科医生日常使用的颜色不对称评估转化为手工特征,可与卷积神经网络集成融合用于黑色素瘤检测。
局限性
- 研究仅在国际皮肤成像协作组织2019数据集的一个子集上进行实验。
- 原文未报告外部验证或前瞻性临床验证结果。
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
Melanoma is still a major health problem worldwide. Early diagnosis is the first step toward reducing its mortality, but it remains a challenge even for experienced dermatologists. Although computer-aided systems have been developed to help diagnosis, the lack of insight into their predictions is still a significant limitation toward acceptance by the medical community. To tackle this issue, we designed handcrafted expert features representing color asymmetry within the lesions, which are parts of the approach used by dermatologists in their daily practice. These features are given to an artificial neural network classifying between nevi and melanoma. We compare our results with an ensemble of 7 state-of-the-art convolutional neural networks and merge the 2 approaches by computing the average prediction. Our experiments are done on a subset of the International Skin Imaging Collaboration 2019 dataset (6296 nevi, 1361 melanomas). The artificial neural network based on asymmetry achieved an area under the curve of 0.873, sensitivity of 90%, and specificity of 67%; the convolutional neural network approach achieved an area under the curve of 0.938, sensitivity of 91%, and specificity of 82%; and the fusion of both approaches achieved an area under the curve of 0.942, sensitivity of 92%, and specificity of 82%. Merging the knowledge of dermatologists with convolutional neural networks showed high performance for melanoma detection, encouraging collaboration between computer science and medical fields.
引用
- Collenne J, Monnier J, Iguernaissi R, et al. Fusion between an Algorithm Based on the Characterization of Melanocytic Lesions' Asymmetry with an Ensemble of Convolutional Neural Networks for Melanoma Detection. J Invest Dermatol. 2024. PMID: 38296020. doi:10.1016/j.jid.2023.09.289
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。