Computer-Aided Pathological Diagnosis of Nasopharyngeal Carcinoma Based on Deep Learning
Menée à partir de 1 970 images de lames histologiques de tissus provenant de 731 patients présentant une pathologie rhinopharyngée, cette étude évalue la performance d'un algorithme d'apprentissage automatique pour diagnostiquer un carcinome rhinopharyngé
The pathological diagnosis of nasopharyngeal carcinoma (NPC) by various different pathologists is often inefficient and inconsistent. We have therefore introduced a deep learning algorithm into this process and compared the performance of the model with that of three pathologists with different level of experience to demonstrate its clinical value. In this retrospective study, a total of 1,970 whole slide images (WSIs) of 731 cases were collected and divided into training, validation and testing sets. We trained Inception-v3, which is a state-of-the-art convolutional neural network (CNN), to classify images into three categories: chronic nasopharyngeal inflammation, lymphoid hyperplasia and NPC. The mean area under the curve (AUC) of the deep learning model is 0.936 based on the testing set and its AUCs for the three image categories are 0.905, 0.972 and 0.930, respectively. In the comparison with the three pathologists, the model outperforms the junior and intermediate pathologists, and has only a slightly lower performance than the senior pathologist when considered in terms of accuracy, specificity, sensitivity, AUC and consistency. To our knowledge, this is the first study about the application of deep learning to NPC pathological diagnosis. In clinical practice, the deep learning model can potentially assist pathologists by providing a second opinion on their NPC diagnoses.
The American Journal of Pathology , résumé, 2019