.jpg?format=webp&width=780)
A deep convolutional neural network (DCNN) model was constructed and validated for the detection of nasopharyngeal carcinoma (NPC) using archived nasopharyngoscopic images. The model, based on the You Only Look Once (YOLOv5) architecture, analyzed 3,501 images in 69.35 seconds. The DCNN model demonstrated high precision, recall, accuracy, and F1 score in detecting NPCs on both white light imaging (WLI) and narrow band imaging (NBI). The diagnostic performance of the DCNN model was significantly better than that of two junior otolaryngologists. The results suggest that the DCNN model can assist junior endoscopists in improving their diagnostic accuracy and reducing missed diagnoses of NPC.
Like
Save
Share