Computer-aided diagnosis of laryngeal cancer via deep learning based on laryngoscopic images

Abstract

Objective: To develop a deep convolutional neural network (DCNN) that can automatically detect laryngeal cancer (LCA) in laryngoscopic images.

Methods: A DCNN-based diagnostic system was constructed and trained using 13,721 laryngoscopic images of LCA, precancerous laryngeal lesions (PRELCA), benign laryngeal tumors (BLT) and normal tissues (NORM) from 2 tertiary hospitals in China, including 2293 from 206 LCA subjects, 1807 from 203 PRELCA subjects, 6448 from 774 BLT subjects and 3191 from 633 NORM subjects. An independent test set of 1176 laryngoscopic images from other 3 tertiary hospitals in China, including 132 from 44 LCA subjects, 129 from 43 PRELCA subjects, 504 from 168 BLT subjects and 411 from 137 NORM subjects, was applied to the constructed DCNN to evaluate its performance against experienced endoscopists.

Results: The DCCN achieved a sensitivity of 0.731, a specificity of 0.922, an AUC of 0.922, and the overall accuracy of 0.867 for detecting LCA and PRELCA among all lesions and normal tissues. When compared to human experts in an independent test set, the DCCN' s performance on detection of LCA and PRELCA achieved a sensitivity of 0.720, a specificity of 0.948, an AUC of 0.953, and the overall accuracy of 0.897, which was comparable to that of an experienced human expert with 10-20 years of work experience. Moreover, the overall accuracy of DCNN for detection of LCA was 0.773, which was also comparable to that of an experienced human expert with 10-20 years of work experience and exceeded the experts with less than 10 years of work experience.

Conclusions: The DCNN has high sensitivity and specificity for automated detection of LCA and PRELCA from BLT and NORM in laryngoscopic images. This novel and effective approach facilitates earlier diagnosis of early LCA, resulting in improved clinical outcomes and reducing the burden of endoscopists.

Fig. 1

Overview of the deep learning architecture. Parameters pre-trained on the external ImageNet dataset are used to initialize the deep convolutional neural network, which is then fine-tuned on the target dataset.

Fig. 2

Illustration of the changes of the loss function value (A) and the classification accuracy (B) over the training and testing sets.

Fig. 3

The sensitivity-specificity curve for Urgent versus Non-urgent binary classification.

Fig. 4

Confusion matrix for 4-class categorization.

Fig. 5

Comparison between the deep learning algorithm and three human experts in Urgent versus Non-urgent binary classification. Expert 1: expert with 10–20 years of experience. Expert 2: expert with ~3 years of experience. Expert 3: expert with 3–10 years of experience.

Fig. 6

Four-class confusion matrices obtained by our DCNN model (A) and the three human experts (B-D). Expert 1: expert with 10–20 years of experience. Expert 2: expert with ~3 years of experience. Expert 3: expert with 3–10 years of experience.

Fig. 7

Representative attention maps obtained by the DCNN model on the classes of NORM, BLT, PRELCA and LCA from top to bottom respectively. Attention maps are displayed as heat maps overlay upon the original images, where warmer colors indicate higher saliency, i.e., higher contribution to the classification decision.