Deep convolutional neural network-based classification of cancer cells on cytological pleural effusion images

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.

Automated summary

Lung cancer is a leading cause of cancer-related deaths globally. Cytology plays a crucial role in the initial evaluation and diagnosis of lung cancer patients. However, due to the subjective nature of cytopathologists and regional variations in diagnostic levels, liquid-based cytological diagnosis results have low consistency, leading to misdiagnoses and missed diagnoses. In this study, a weakly supervised deep learning method using a deep convolutional neural network (DCNN) was performed for the classification of benign and malignant cells in lung cytological images. The results showed high accuracy, sensitivity, and specificity in classifying malignant and benign lesions using the proposed method. In comparison, senior and junior cytopathologists had higher and lower average accuracies, respectively. Moreover, the proposed deep learning method is expected to assist pathologists with different levels of experience in the diagnosis of cancer cells in cytological pleural effusion images in the future.