文献速递骨软组织肉瘤与黑色素瘤

深度学习在头对头皮肤镜黑色素瘤图像分类任务中优于157名皮肤科医生中的136名

Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task.
PubMed 文献 · Eur J Cancer · 2019-04-10

本研究用12,378张开源皮肤镜图像训练卷积神经网络(CNN),并用100张图像将其与德国12所大学医院的157名皮肤科医生进行头对头比较。在平均灵敏度74.1%时,CNN平均特异度为86.5%(范围70.8%-91.3%);在平均特异度60%时,CNN平均灵敏度为87.5%(范围80%-95%)。CNN在平均特异度和灵敏度上优于157名皮肤科医生中的136名及所有经验层级。

要点

  • CNN仅用开源图像训练,在100张图像测试中优于157名皮肤科医生中的136名。
  • 皮肤科医生平均灵敏度74.1%、平均特异度60%;CNN在同等灵敏度下特异度86.5%。
  • CNN在同等特异度60%下平均灵敏度87.5%,高于皮肤科医生的74.1%。

核心结论

  • 仅用开源图像训练的CNN在平均特异度和灵敏度上优于157名皮肤科医生中的136名及所有经验层级(从住院医师到主任医师)。

研究设计与样本

  • 用增强深度学习方法以12,378张开源皮肤镜图像训练卷积神经网络(CNN)。
  • 用100张图像将CNN与德国12所大学医院的157名皮肤科医生进行头对头比较,以灵敏度、特异度和受试者工作特征衡量表现。

主要发现

  • 皮肤科医生使用皮肤镜图像的平均灵敏度为74.1%(范围40.0%-100%),平均特异度为60%(范围21.3%-91.3%)。
  • 在平均灵敏度74.1%时,CNN平均特异度为86.5%(范围70.8%-91.3%)。
  • 在平均特异度60%时,CNN平均灵敏度为87.5%(范围80%-95%)。
  • 皮肤科医生中主任医师在平均灵敏度73.3%时平均特异度最高,为69.2%;在同等特异度69.2%下,CNN平均灵敏度为84.5%。

局限性

  • 原文未报告局限性。

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: Recent studies have successfully demonstrated the use of deep-learning algorithms for dermatologist-level classification of suspicious lesions by the use of excessive proprietary image databases and limited numbers of dermatologists. For the first time, the performance of a deep-learning algorithm trained by open-source images exclusively is compared to a large number of dermatologists covering all levels within the clinical hierarchy. METHODS: We used methods from enhanced deep learning to train a convolutional neural network (CNN) with 12,378 open-source dermoscopic images. We used 100 images to compare the performance of the CNN to that of the 157 dermatologists from 12 university hospitals in Germany. Outperformance of dermatologists by the deep neural network was measured in terms of sensitivity, specificity and receiver operating characteristics. FINDINGS: The mean sensitivity and specificity achieved by the dermatologists with dermoscopic images was 74.1% (range 40.0%-100%) and 60% (range 21.3%-91.3%), respectively. At a mean sensitivity of 74.1%, the CNN exhibited a mean specificity of 86.5% (range 70.8%-91.3%). At a mean specificity of 60%, a mean sensitivity of 87.5% (range 80%-95%) was achieved by our algorithm. Among the dermatologists, the chief physicians showed the highest mean specificity of 69.2% at a mean sensitivity of 73.3%. With the same high specificity of 69.2%, the CNN had a mean sensitivity of 84.5%. INTERPRETATION: A CNN trained by open-source images exclusively outperformed 136 of the 157 dermatologists and all the different levels of experience (from junior to chief physicians) in terms of average specificity and sensitivity.

来源:Eur J Cancer,查看原文。版权归原作者所有。

引用

  1. Brinker TJ, Hekler A, Enk AH, et al. Deep learning outperformed 136 of 157 dermatologists in a head-to-head dermoscopic melanoma image classification task. Eur J Cancer. 2019. PMID: 30981091. doi:10.1016/j.ejca.2019.04.001

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。