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.
Objective
Little is known about the efficacy of using artificial intelligence (AI) to identify laryngeal carcinoma from images of vocal lesions taken in different hospitals with multiple laryngoscope systems. This multicentre study aimed to establish an AI system and provide a reliable auxiliary tool to screen for laryngeal carcinoma.
Study design
Multicentre case–control study.
Setting
Six tertiary care centres.
Participants
Laryngoscopy images were collected from 2179 patients with vocal fold lesions.
Outcome measures
An automatic detection system of laryngeal carcinoma was established and used to distinguish malignant and benign vocal lesions in 2179 laryngoscopy images acquired from 6 hospitals with 5 types of laryngoscopy systems. Pathological examination was the gold standard for identifying malignant and benign vocal lesions.
Results
Out of 89 cases in the malignant group, the classifier was able to correctly identify laryngeal carcinoma in 66 patients (74.16%, sensitivity). Out of 640 cases in the benign group, the classifier was able to accurately assess the laryngeal lesion in 503 cases (78.59%, specificity). Furthermore, the region‐based convolutional neural network (R‐CNN) classifier achieved an overall accuracy of 78.05%, with a 95.63% negative predictive value and a 32.51% positive predictive value for the testing data set.
Conclusion
This automatic diagnostic system has the potential to assist clinical laryngeal carcinoma diagnosis which may improve and standardise the diagnostic capacity of laryngologists using different laryngoscopes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.