Convolutional neural networks can accurately distinguish four histologic growth patterns of lung adenocarcinoma in digital slides
Convolutional neural networks can accurately distinguish four histologic growth patterns of lung adenocarcinoma in digital slides
复制标题
DOI：
10.1038/s41598-018-37638-9
复制
发表时间：
2019-02-06
影响因子：
4.6
通讯作者：
Knudsen, Beatrice S.
中科院分区：
文献类型：
--
作者：
Gertych, Arkadiusz;Swiderska-Chadaj, Zaneta;Knudsen, Beatrice S.
在肺腺癌（LAC）的诊断检查过程中，病理学家评估不同的组织学肿瘤生长模式。多个切片上每种模式的百分比具有预后意义。为了帮助量化生长模式，我们构建了一个配备卷积神经网络（CNN）和软投票的管道作为决策函数，以识别实体，微乳头，腺泡和筛状生长模式以及非肿瘤区域。原发性LAC的载玻片来自Cedars-Sinai医学中心（CSMC）、华沙军事医学研究所和TCGA门户网站。使用从78个载玻片（MIMW和CSMC）中提取的19，924个图像块训练的几个CNN模型在来自三个研究中心的128个测试载玻片上通过F1评分和准确性进行了评估，其中使用病理学家的手动肿瘤注释。最好的CNN产生的F1分数分别为0.91（实体）、0.76（微乳头）、0.74（腺泡）、0.6（筛状）和0.96（非肿瘤）。五种组织分类的总体准确率为89.24%。由于上级载玻片质量，CSMC集基于载玻片的准确度（88.5%）显著优于（p < 2.3E-4）MIMW（84.2%）和TCGA（84%）集的准确度。我们的模型可以与病理学家并肩工作，以准确量化具有混合LAC模式的肿瘤中生长模式的百分比。
During the diagnostic workup of lung adenocarcinomas (LAC), pathologists evaluate distinct histological tumor growth patterns. The percentage of each pattern on multiple slides bears prognostic significance. To assist with the quantification of growth patterns, we constructed a pipeline equipped with a convolutional neural network (CNN) and soft-voting as the decision function to recognize solid, micropapillary, acinar, and cribriform growth patterns, and non-tumor areas. Slides of primary LAC were obtained from Cedars-Sinai Medical Center (CSMC), the Military Institute of Medicine in Warsaw and the TCGA portal. Several CNN models trained with 19,924 image tiles extracted from 78 slides (MIMW and CSMC) were evaluated on 128 test slides from the three sites by F1-score and accuracy using manual tumor annotations by pathologist. The best CNN yielded F1-scores of 0.91 (solid), 0.76 (micropapillary), 0.74 (acinar), 0.6 (cribriform), and 0.96 (non-tumor) respectively. The overall accuracy of distinguishing the five tissue classes was 89.24%. Slide-based accuracy in the CSMC set (88.5%) was significantly better (p < 2.3E-4) than the accuracy in the MIMW (84.2%) and TCGA (84%) sets due to superior slide quality. Our model can work side-by-side with a pathologist to accurately quantify the percentages of growth patterns in tumors with mixed LAC patterns.