Automated Detection of Laryngeal Carcinoma in Laryngoscopic Images from a Multicenter Database using a Convolutional Neural Network

Abstract

OBJECTIVE Little is known about the efficacy of using artificial intelligence to identify laryngeal carcinoma from images of vocal lesions taken in different hospitals with multiple laryngoscope systems. This multicenter study was aimed to establish an artificial intelligence system and provide a reliable auxiliary tool to screen for laryngeal carcinoma. Study Design: Multicentre case-control study Setting: Six tertiary care centers Participants: The laryngoscopy images were collected from 2179 patients with vocal lesions. Outcome Measures: An automatic detection system of laryngeal carcinoma was established based on Faster R-CNN, which was used to distinguish vocal malignant and benign lesions in 2179 laryngoscopy images acquired from 6 hospitals with 5 types of laryngoscopy systems. Pathology was the gold standard to identify malignant and benign vocal lesions. Results: Among 89 cases of the malignant group, the classifier was able to evaluate the laryngeal carcinoma in 66 patients (74.16%, sensitivity), while the classifier was able to assess the benign laryngeal lesion in 503 cases among 640 cases of the benign group (78.59%, specificity). Furthermore, the CNN-based classifier achieved an overall accuracy of 78.05% with a 95.63% negative prediction for the testing dataset. Conclusion: This automatic diagnostic system has the potential to assist clinical laryngeal carcinoma diagnosis, which may improve and standardize the diagnostic capacity of endoscopists using different laryngoscopes.

Convolutional neural network-based vocal cord tumor classification technique for home-based self-prescreening purpose

“…In addition, Cho et al reported the following two related papers: in one study, they applied four CNN models (six-layer CNN, VGG16, Inception-V3 and Xception) to laryngoscopic vocal fold images to classify the image into abnormal and normal [ 15 ], and in the other study, they applied four CNN models (VGG16, Inception-V3, MobileNet-V2 and EfficientNet-B0) to classify laryngeal diseases (cysts, nodules, polyps, leukoplakia, papillomas, Reinke’s edema, granulomas, palsies and normal) [ 16 ]; You et al applied 13 CNN models (AlexNet, four VGG models, three ResNet models, three DenseNet models, Inception-V3, and the proposed) to classify laryngeal leukoplakia (inflammatory keratosis, mild/moderate/severe dysplasia, and squamous cell carcinoma) using white-light endoscopy images [ 17 ]; Eggert et al applied DenseNet models to classify hyperspectral images of laryngeal, hypopharyngeal, and oropharyngeal mucosa into abnormal and normal [ 18 ]. Moreover, Hu et al applied Mask R-CNN with ResNet-50 backbone to two types of laryngoscopic imaging (narrow-band imaging and white-light imaging) for automated real-time segmentation and classification of vocal cord leukoplakia to classify the lesions into surgical and non-surgical groups [ 19 ]; Yan et al applied the Faster R-CNN model to laryngoscopic images of vocal lesions to screen for laryngeal carcinoma [ 20 ]; Kim et al applied the Mask R-CNN model to laryngoscopic images for real-time segmentation of laryngeal mass around the vocal cord [ 21 ]; Cen et al applied three CNN models (Faster R-CNN, Yolo V3, and SSD) to detect laryngeal tumors in endoscopic images (vocal fold, tumor, surgical tools, and other laryngeal tissues) [ 22 ]; Azam et al applied up to nine Yolo models to laryngoscopic video for real-time detection of laryngeal squamous cell carcinoma in both white-light and narrow-band imaging [ 23 ]. Among these previous studies on vocal area disease detection, eight [ 11 – 18 ] used AI models for classification and, therefore, were not able to provide information about the tumor-suspicious positions in the image.…”

“…Among these previous studies on vocal area disease detection, eight [ 11 – 18 ] used AI models for classification and, therefore, were not able to provide information about the tumor-suspicious positions in the image. Similar to the current study, five other studies [ 19 – 23 ] used AI models for object detection that can provide tumor-suspicious positions around the vocal cords; however, they commonly used only single-group disease images, such as vocal cord leukoplakia [ 19 ], laryngeal carcinoma [ 20 , 23 ], laryngeal mass [ 21 ], and cancer [ 22 ].…”