loading page

Automated Detection of Laryngeal Carcinoma in Laryngoscopic Images from a Multicenter Database using a Convolutional Neural Network
  • +11
  • Peikai Yan,
  • Shaohua Li,
  • Zhou Zhou,
  • Qian Liu,
  • Jiahui Wu,
  • Qingyi Ren,
  • Qiuhuan Chen,
  • Zhipeng Chen,
  • Ze Chen,
  • Shao-hua Chen,
  • Austin Scholp,
  • Jack J Jiang,
  • Jing Kang,
  • Pingjiang Ge
Peikai Yan
Guangdong Provincial People's Hospital

Corresponding Author:[email protected]

Author Profile
Shaohua Li
Zhongshan Hospital of Traditional Chinese Medicine
Author Profile
Zhou Zhou
Shenzhen People’s Hospital
Author Profile
Qian Liu
Shenzhen People’s Hospital
Author Profile
Jiahui Wu
Guangdong Provincial People's Hospital
Author Profile
Qingyi Ren
Guangdong Provincial People's Hospital
Author Profile
Qiuhuan Chen
Zhaoqing Gaoyao People’s Hospital
Author Profile
Zhipeng Chen
The Second People’s Hospital of Longgang District
Author Profile
Ze Chen
Gaozhou People’s Hospital
Author Profile
Shao-hua Chen
Guangdong general Hospital &Guangdong Academy of Medical Science
Author Profile
Austin Scholp
University of Wisconsin-Madison School of Medicine and Public Health
Author Profile
Jack J Jiang
University of Wisconsin-Madison School of Medicine and Public Health
Author Profile
Jing Kang
Guangdong Provincial People's Hospital
Author Profile
Pingjiang Ge
Guangdong General Hospital
Author Profile

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.
26 Aug 2021Submitted to Clinical Otolaryngology
06 Sep 2021Submission Checks Completed
06 Sep 2021Assigned to Editor
28 Sep 2021Reviewer(s) Assigned
22 Nov 2021Review(s) Completed, Editorial Evaluation Pending
27 Nov 2021Editorial Decision: Revise Major
10 Jan 20221st Revision Received
17 Jan 2022Submission Checks Completed
17 Jan 2022Assigned to Editor
07 Feb 2022Reviewer(s) Assigned
30 Mar 2022Review(s) Completed, Editorial Evaluation Pending
17 Apr 2022Editorial Decision: Revise Minor
15 May 20222nd Revision Received
18 May 2022Submission Checks Completed
18 May 2022Assigned to Editor
22 Jun 2022Review(s) Completed, Editorial Evaluation Pending
26 Jun 2022Editorial Decision: Revise Minor
10 Jul 20223rd Revision Received
13 Jul 2022Submission Checks Completed
13 Jul 2022Assigned to Editor
25 Jul 2022Review(s) Completed, Editorial Evaluation Pending
29 Jul 2022Editorial Decision: Revise Minor
08 Aug 20224th Revision Received
11 Aug 2022Submission Checks Completed
11 Aug 2022Assigned to Editor
09 Sep 2022Review(s) Completed, Editorial Evaluation Pending
01 Oct 2022Editorial Decision: Revise Minor
08 Oct 20225th Revision Received
10 Oct 2022Submission Checks Completed
10 Oct 2022Assigned to Editor
28 Oct 2022Review(s) Completed, Editorial Evaluation Pending
20 Nov 2022Editorial Decision: Revise Minor
21 Nov 20226th Revision Received
24 Nov 2022Submission Checks Completed
24 Nov 2022Assigned to Editor
05 Dec 2022Review(s) Completed, Editorial Evaluation Pending
31 Dec 2022Editorial Decision: Accept