深度学习在组织病理学黑色素瘤图像分类中优于11位病理学家
该研究将695个病灶(350痣/345黑色素瘤)的H&E切片数字化并随机裁剪,用595张图像训练卷积神经网络(CNN),另100张用于测试。CNN在11次测试中平均敏感度/特异度/准确率为76%/60%/68%,11位病理学家为51.8%/66.5%/59.2%,CNN分类显著更优(p=0.016)。
要点
- CNN分类裁剪的黑色素瘤图像平均敏感度76%、特异度60%、准确率68%。
- 11位病理学家平均敏感度51.8%、特异度66.5%、准确率59.2%。
- CNN分类性能显著优于病理学家(p=0.016)。
核心结论
- 在图像信息有限的条件下,CNN在组织病理学黑色素瘤图像分类中优于11位病理学家,有望辅助人类诊断。
研究设计与样本
- 共695个病灶(350痣/345黑色素瘤)由专家病理学家按现行指南分类,仅H&E切片数字化后随机裁剪。
- 595张图像用于训练CNN,另100张用于测试,并与11位病理学家比较。
- 预设三个McNemar检验比较CNN测试运行的敏感度、特异度和准确率,显著性水平p<0.05。
主要发现
- CNN在11次测试运行中平均敏感度/特异度/准确率为76%/60%/68%。
- 11位病理学家平均敏感度/特异度/准确率为51.8%/66.5%/59.2%。
- CNN分类裁剪图像显著优于病理学家(p=0.016)。
临床怎么用
- CNN可能作为辅助工具帮助病理学家诊断黑色素瘤,尤其在图像信息有限时。
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: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports on 25-26% of discordance for classifying a benign nevus versus malignant melanoma. A recent study indicated the potential of deep learning to lower these discordances. However, the performance of deep learning in classifying histopathologic melanoma images was never compared directly to human experts. The aim of this study is to perform such a first direct comparison. METHODS: A total of 695 lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi/345 melanoma). Only the haematoxylin & eosin (H&E) slides of these lesions were digitalised via a slide scanner and then randomly cropped. A total of 595 of the resulting images were used to train a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison to 11 histopathologists. Three combined McNemar tests comparing the results of the CNNs test runs in terms of sensitivity, specificity and accuracy were predefined to test for significance (p < 0.05). FINDINGS: The CNN achieved a mean sensitivity/specificity/accuracy of 76%/60%/68% over 11 test runs. In comparison, the 11 pathologists achieved a mean sensitivity/specificity/accuracy of 51.8%/66.5%/59.2%. Thus, the CNN was significantly (p = 0.016) superior in classifying the cropped images. INTERPRETATION: With limited image information available, a CNN was able to outperform 11 histopathologists in the classification of histopathological melanoma images and thus shows promise to assist human melanoma diagnoses.
引用
- Hekler A, Utikal JS, Enk AH, et al. Deep learning outperformed 11 pathologists in the classification of histopathological melanoma images. Eur J Cancer. 2019. PMID: 31325876. doi:10.1016/j.ejca.2019.06.012
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。