Laboratory for Investigative Dermatology, The Rockefeller University, New York, NY, USA.
The Center for Clinical and Translational Science, The Rockefeller University, New York, NY, USA.
Exp Dermatol. 2017 Jul;26(7):615-618. doi: 10.1111/exd.13250. Epub 2016 Dec 19.
We developed an automated approach for generating quantitative image analysis metrics (imaging biomarkers) that are then analysed with a set of 13 machine learning algorithms to generate an overall risk score that is called a Q-score. These methods were applied to a set of 120 "difficult" dermoscopy images of dysplastic nevi and melanomas that were subsequently excised/classified. This approach yielded 98% sensitivity and 36% specificity for melanoma detection, approaching sensitivity/specificity of expert lesion evaluation. Importantly, we found strong spectral dependence of many imaging biomarkers in blue or red colour channels, suggesting the need to optimize spectral evaluation of pigmented lesions.
我们开发了一种自动生成定量图像分析指标（成像生物标志物）的方法，然后使用一组 13 种机器学习算法对这些指标进行分析，生成一个称为 Q 分数的整体风险评分。这些方法应用于一组 120 张“困难”的发育不良痣和黑色素瘤的皮肤镜图像，这些图像随后被切除/分类。该方法对黑色素瘤检测的敏感性为 98%，特异性为 36%，接近专家病变评估的敏感性/特异性。重要的是，我们发现许多成像生物标志物在蓝色或红色颜色通道中具有很强的光谱依赖性，这表明需要优化对色素性病变的光谱评估。
