深度神经网络在黑色素瘤图像分类中优于皮肤科医生
本研究用4204张活检证实的黑色素瘤与痣图像训练卷积神经网络,另以804张图像测试并与德国九所大学医院皮肤科医生的评估比较。CNN的敏感度82.3%、特异度77.9%,均显著高于医生的67.2%和62.2%(p<0.001)。
要点
- CNN分类黑色素瘤的敏感度和特异度均显著高于皮肤科医生(p<0.001)。
- 医生对804张皮肤镜图像的敏感度为67.2%,特异度为62.2%。
- 该研究首次证明自动化皮肤镜图像分类显著优于各级皮肤科医生。
核心结论
- 自动化皮肤镜黑色素瘤图像分类首次被证明显著优于初级和认证皮肤科医生(p<0.001)。
研究设计与样本
- 比较研究,用4204张活检证实的黑色素瘤和痣图像(1:1)训练卷积神经网络。
- 另用804张活检证实的皮肤镜图像(1:1)随机呈现给德国九所大学医院的皮肤科医生评估。
主要发现
- 皮肤科医生分类病变的敏感度为67.2%(95%CI 62.6%-71.7%),特异度为62.2%(95%CI 57.6%-66.9%)。
- 训练后的CNN敏感度为82.3%(95%CI 78.3%-85.7%),特异度为77.9%(95%CI 73.8%-81.8%)。
- 三项McNemar检验均达到p<0.001的显著性水平,且两个亚组中该显著性水平均维持。
局限性
- 原文仅报告摘要,未涉及研究局限性信息。
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: Melanoma is the most dangerous type of skin cancer but is curable if detected early. Recent publications demonstrated that artificial intelligence is capable in classifying images of benign nevi and melanoma with dermatologist-level precision. However, a statistically significant improvement compared with dermatologist classification has not been reported to date. METHODS: For this comparative study, 4204 biopsy-proven images of melanoma and nevi (1:1) were used for the training of a convolutional neural network (CNN). New techniques of deep learning were integrated. For the experiment, an additional 804 biopsy-proven dermoscopic images of melanoma and nevi (1:1) were randomly presented to dermatologists of nine German university hospitals, who evaluated the quality of each image and stated their recommended treatment (19,296 recommendations in total). Three McNemar's tests comparing the results of the CNN's test runs in terms of sensitivity, specificity and overall correctness were predefined as the main outcomes. FINDINGS: The respective sensitivity and specificity of lesion classification by the dermatologists were 67.2% (95% confidence interval [CI]: 62.6%-71.7%) and 62.2% (95% CI: 57.6%-66.9%). In comparison, the trained CNN achieved a higher sensitivity of 82.3% (95% CI: 78.3%-85.7%) and a higher specificity of 77.9% (95% CI: 73.8%-81.8%). The three McNemar's tests in 2 × 2 tables all reached a significance level of p < 0.001. This significance level was sustained for both subgroups. INTERPRETATION: For the first time, automated dermoscopic melanoma image classification was shown to be significantly superior to both junior and board-certified dermatologists (p < 0.001).
引用
- Brinker TJ, Hekler A, Enk AH, et al. Deep neural networks are superior to dermatologists in melanoma image classification. Eur J Cancer. 2019. PMID: 31401469. doi:10.1016/j.ejca.2019.05.023
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。