Deep learning model for tongue cancer diagnosis using endoscopic images.

Autor: Heo J; Department of Radiation Oncology, Ajou University School of Medicine, Suwon, Republic of Korea., Lim JH; Department of Radiation Oncology, Ajou University School of Medicine, Suwon, Republic of Korea., Lee HR; Department of Otolaryngology, Ajou University School of Medicine, 164 Worldcup-ro, Yeongtong-gu, Suwon, 16499, Republic of Korea., Jang JY; Department of Otolaryngology, Ajou University School of Medicine, 164 Worldcup-ro, Yeongtong-gu, Suwon, 16499, Republic of Korea., Shin YS; Department of Otolaryngology, Ajou University School of Medicine, 164 Worldcup-ro, Yeongtong-gu, Suwon, 16499, Republic of Korea., Kim D; Department of Otorhinolaryngology, Yonsei University, Seoul, Republic of Korea., Lim JY; Department of Otorhinolaryngology, Yonsei University, Seoul, Republic of Korea., Park YM; Department of Otorhinolaryngology, Yonsei University, Seoul, Republic of Korea., Koh YW; Department of Otorhinolaryngology, Yonsei University, Seoul, Republic of Korea., Ahn SH; Department of Otorhinolaryngology-Head and Neck Surgery, Seoul National University Hospital, Seoul, Republic of Korea., Chung EJ; Department of Otorhinolaryngology-Head and Neck Surgery, Seoul National University Hospital, Seoul, Republic of Korea., Lee DY; Department of Otorhinolaryngology-Head and Neck Surgery, Seoul National University Hospital, Seoul, Republic of Korea., Seok J; Department of Otorhinolaryngology-Head & Neck Surgery, National Cancer Center, Goyang, Republic of Korea., Kim CH; Department of Otolaryngology, Ajou University School of Medicine, 164 Worldcup-ro, Yeongtong-gu, Suwon, 16499, Republic of Korea. ostium@ajou.ac.kr.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2022 Apr 15; Vol. 12 (1), pp. 6281. Date of Electronic Publication: 2022 Apr 15.
DOI: 10.1038/s41598-022-10287-9
Abstrakt: In this study, we developed a deep learning model to identify patients with tongue cancer based on a validated dataset comprising oral endoscopic images. We retrospectively constructed a dataset of 12,400 verified endoscopic images from five university hospitals in South Korea, collected between 2010 and 2020 with the participation of otolaryngologists. To calculate the probability of malignancy using various convolutional neural network (CNN) architectures, several deep learning models were developed. Of the 12,400 total images, 5576 images related to the tongue were extracted. The CNN models showed a mean area under the receiver operating characteristic curve (AUROC) of 0.845 and a mean area under the precision-recall curve (AUPRC) of 0.892. The results indicate that the best model was DenseNet169 (AUROC 0.895 and AUPRC 0.918). The deep learning model, general physicians, and oncology specialists had sensitivities of 81.1%, 77.3%, and 91.7%; specificities of 86.8%, 75.0%, and 90.9%; and accuracies of 84.7%, 75.9%, and 91.2%, respectively. Meanwhile, fair agreement between the oncologist and the developed model was shown for cancer diagnosis (kappa value = 0.685). The deep learning model developed based on the verified endoscopic image dataset showed acceptable performance in tongue cancer diagnosis.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje