Fig. 2

Workflow and architecture of LPAIDS. a Procedure for detecting LPC from laryngoscopy videos. The WLI and NBI laryngoscopy video frames were extracted from laryngoscopy videos. After screening and annotation by highly experienced laryngoscopists, the images were fed into the model to localize the area with possible tumours; the diagnoses were based on the shape and size of the tumour area. Three pre-trained convolutional neural network models (model W, model N, and LPAIDS, based on U-Net) were developed to obtain the feature vectors from the WLI, NBI, and all images, respectively. b The detailed neural network architecture of LPAIDS based on U-Net. LPAIDS: Laryngopharyngeal Artificial Intelligence Diagnostic System; LPC: laryngopharyngeal cancer; NBI: narrow-band imaging; WLI: white-light imaging