Deep convolutional neural network-based classification of cancer cells on cytological pleural effusion images.
Deep convolutional neural network-based classification of cancer cells on cytological pleural effusion images.
复制标题
DOI：
10.1038/s41379-021-00987-4
复制
发表时间：
2022-05
期刊：
影响因子：
7.5
通讯作者：
Wu, Chunyan
中科院分区：
文献类型：
--
作者：
Xie, Xiaofeng;Fu, Chi-Cheng;Lv, Lei;Ye, Qiuyi;Yu, Yue;Fang, Qu;Zhang, Liping;Hou, Likun;Wu, Chunyan
肺癌是全球癌症相关死亡的主要原因之一。细胞学检查在肺癌患者的初步评估和诊断中起着重要作用。但由于细胞病理学家的主观性和诊断水平的地域性，液基细胞学诊断的一致性不高，导致一定比例的误诊和漏诊。在这项研究中，我们通过深度卷积神经网络（DCNN）执行了一种弱监督深度学习方法，用于肺细胞学图像中良性和恶性细胞的分类。以上海市肺科医院胸腔积液细胞学标本中的404例肺癌细胞为研究对象，分别选取266例、78例和60例作为训练集、验证集和测试集。所提出的方法进行了评估60肺癌胸腔积液标本的全载玻片图像（WSIs）。本研究表明，该方法对良、恶性病变（或正常）的准确性、敏感性和特异性分别为91.67%、87.50%和94.44%。受试者工作特征（ROC）曲线下面积（AUC）为0.9526（95%置信区间（CI）：0.9019-9.9909）。相比之下，高级和初级细胞病理学家的平均准确率分别为98.34%和83.34%。所提出的深度学习方法将是有用的，并且可以在未来帮助具有不同经验水平的病理学家在细胞学胸腔积液图像上诊断癌细胞。
Lung cancer is one of the leading causes of cancer-related death worldwide. Cytology plays an important role in the initial evaluation and diagnosis of patients with lung cancer. However, due to the subjectivity of cytopathologists and the region-dependent diagnostic levels, the low consistency of liquid-based cytological diagnosis results in certain proportions of misdiagnoses and missed diagnoses. In this study, we performed a weakly supervised deep learning method for the classification of benign and malignant cells in lung cytological images through a deep convolutional neural network (DCNN). A total of 404 cases of lung cancer cells in effusion cytology specimens from Shanghai Pulmonary Hospital were investigated, in which 266, 78, and 60 cases were used as the training, validation and test sets, respectively. The proposed method was evaluated on 60 whole-slide images (WSIs) of lung cancer pleural effusion specimens. This study showed that the method had an accuracy, sensitivity, and specificity respectively of 91.67%, 87.50% and 94.44% in classifying malignant and benign lesions (or normal). The area under the receiver operating characteristic (ROC) curve (AUC) was 0.9526 (95% confidence interval (CI): 0.9019–9.9909). In contrast, the average accuracies of senior and junior cytopathologists were 98.34% and 83.34%, respectively. The proposed deep learning method will be useful and may assist pathologists with different levels of experience in the diagnosis of cancer cells on cytological pleural effusion images in the future.
登录
查看更多内容
影响因子：
82.9
作者：
AbdulJabbar K;Raza SEA;Rosenthal R;Jamal-Hanjani M;Veeriah S;Akarca A;Lund T;Moore DA;Salgado R;Al Bakir M;Zapata L;Hiley CT;Officer L;Sereno M;Smith CR;Loi S;Hackshaw A;Marafioti T;Quezada SA;McGranahan N;Le Quesne J;TRACERx Consortium;Swanton C;Yuan Y
通讯作者：
Yuan Y
DOI：
10.1007/s11548-018-1835-2
发表时间：
2018-12
影响因子：
3
作者：
Antonio VAA;Ono N;Saito A;Sato T;Altaf-Ul-Amin M;Kanaya S
通讯作者：
Kanaya S
影响因子：
4.6
作者：
Kanavati, Fahdi;Toyokawa, Gouji;Tsuneki, Masayuki
通讯作者：
Tsuneki, Masayuki
影响因子：
--
作者：
Humphries, Matthew P.;Hynes, Sean;Buckley, Niamh E.
通讯作者：
Buckley, Niamh E.
影响因子：
1.3
作者：
DIBONITO, L;COLAUTTI, I;VIELH, P
通讯作者：
VIELH, P