Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China.
Department of Obstetrics and Gynecology, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China.
J Clin Microbiol. 2021 Jan 21;59(2). doi: 10.1128/JCM.02236-20.
Bacterial vaginosis (BV) is caused by the excessive and imbalanced growth of bacteria in vagina, affecting 30 to 50% of women. Gram staining followed by Nugent scoring based on bacterial morphotypes under the microscope is considered the gold standard for BV diagnosis; this method is often labor-intensive and time-consuming, and results vary from person to person. We developed and optimized a convolutional neural network (CNN) model and evaluated its ability to automatically identify and classify three categories of Nugent scores from microscope images. The CNN model was first established with a panel of microscopic images with Nugent scores determined by experts. The model was trained by minimizing the cross-entropy loss function and optimized by using a momentum optimizer. The separate test sets of images collected from three hospitals were evaluated by the CNN model. The CNN model consisted of 25 convolutional layers, 2 pooling layers, and a fully connected layer. The model obtained 82.4% sensitivity and 96.6% specificity with the 5,815 validation images when altered vaginal flora and BV were considered the positive samples, which was better than the rates achieved by top-level technologists and obstetricians in China. The capability of our model for generalization was so strong that it exhibited 75.1% accuracy in three categories of Nugent scores on the independent test set of 1,082 images, which was 6.6% higher than the average of three technologists, who are hold bachelor's degrees in medicine and are qualified to make diagnostic decisions. When three technologists ran one specimen in triplicate, the precision of three categories of Nugent scores was 54.0%. One hundred three samples diagnosed by two technologists on different days showed a repeatability of 90.3%. The CNN model outperformed human health care practitioners in terms of accuracy and stability for three categories of Nugent score diagnosis. The deep learning model may offer translational applications in automating diagnosis of bacterial vaginosis with proper supporting hardware.
细菌性阴道病（BV）是由阴道内细菌过度和失衡生长引起的，影响 30%至 50%的女性。革兰氏染色后，根据显微镜下细菌形态学特征进行的 Nugent 评分被认为是 BV 诊断的金标准；这种方法通常劳动强度大，耗时，并且因人而异。我们开发并优化了卷积神经网络（CNN）模型，并评估了其从显微镜图像中自动识别和分类 Nugent 评分的三种类型的能力。该 CNN 模型首先使用由专家确定 Nugent 评分的显微镜图像面板建立。通过最小化交叉熵损失函数来训练模型，并使用动量优化器对其进行优化。该模型使用来自三所医院的单独测试集图像进行评估。CNN 模型由 25 个卷积层、2 个池化层和一个全连接层组成。当改变的阴道菌群和 BV 被认为是阳性样本时，该模型在 5815 张验证图像上获得了 82.4%的敏感性和 96.6%的特异性，这优于中国顶级技术专家和妇产科医生的水平。该模型的泛化能力非常强，在 1082 张独立测试图像的 Nugent 评分的三个类别中，其准确率为 75.1%，比具有医学学士学位且有资格做出诊断决策的三位技术专家的平均准确率高 6.6%。当三位技术专家对一个标本进行三次重复测试时，Nugent 评分的三个类别精度为 54.0%。两位技术专家在不同日期对 103 个样本的诊断具有 90.3%的重复性。在准确性和稳定性方面，CNN 模型优于人类医疗保健从业者，用于诊断 Nugent 评分的三个类别。深度学习模型在适当的硬件支持下，可能在自动化细菌性阴道病诊断方面具有转化应用。
