Lun M Wong1, Ann D King2, Qi Yong H Ai1, W K Jacky Lam3, Darren M C Poon4, Brigette B Y Ma4, K C Allen Chan3, Frankie K F Mo4. 1. Department of Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR. 2. Department of Imaging and Interventional Radiology, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR. king2015@cuhk.edu.hk. 3. Department of Chemical Pathology, State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR. 4. Department of Clinical Oncology, State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Hong Kong, Hong Kong SAR.
Abstract
OBJECTIVES: A convolutional neural network (CNN) was adapted to automatically detect early-stage nasopharyngeal carcinoma (NPC) and discriminate it from benign hyperplasia on a non-contrast-enhanced MRI sequence for potential use in NPC screening programs. METHODS: We retrospectively analyzed 412 patients who underwent T2-weighted MRI, 203 of whom had biopsy-proven primary NPC confined to the nasopharynx (stage T1) and 209 had benign hyperplasia without NPC. Thirteen patients were sampled randomly to monitor the training process. We applied the Residual Attention Network architecture, adapted for three-dimensional MR images, and incorporated a slice-attention mechanism, to produce a CNN score of 0-1 for NPC probability. Threefold cross-validation was performed in 399 patients. CNN scores between the NPC and benign hyperplasia groups were compared using Student's t test. Receiver operating characteristic with the area under the curve (AUC) was performed to identify the optimal CNN score threshold. RESULTS: In each fold, significant differences were observed in the CNN scores between the NPC and benign hyperplasia groups (p < .01). The AUCs ranged from 0.95 to 0.97 with no significant differences between the folds (p = .35 to .92). The combined AUC from all three folds (n = 399) was 0.96, with an optimal CNN score threshold of > 0.71, producing a sensitivity, specificity, and accuracy of 92.4%, 90.6%, and 91.5%, respectively, for NPC detection. CONCLUSION: Our CNN method applied to T2-weighted MRI could discriminate between malignant and benign tissues in the nasopharynx, suggesting that it as a promising approach for the automated detection of early-stage NPC. KEY POINTS: • The convolutional neural network (CNN)-based algorithm could automatically discriminate between malignant and benign diseases using T2-weighted fat-suppressed MR images. • The CNN-based algorithm had an accuracy of 91.5% with an area under the receiver operator characteristic curve of 0.96 for discriminating early-stage T1 nasopharyngeal carcinoma from benign hyperplasia. • The CNN-based algorithm had a sensitivity of 92.4% and specificity of 90.6% for detecting early-stage nasopharyngeal carcinoma.
OBJECTIVES: A convolutional neural network (CNN) was adapted to automatically detect early-stage nasopharyngeal carcinoma (NPC) and discriminate it from benign hyperplasia on a non-contrast-enhanced MRI sequence for potential use in NPC screening programs. METHODS: We retrospectively analyzed 412 patients who underwent T2-weighted MRI, 203 of whom had biopsy-proven primary NPC confined to the nasopharynx (stage T1) and 209 had benign hyperplasia without NPC. Thirteen patients were sampled randomly to monitor the training process. We applied the Residual Attention Network architecture, adapted for three-dimensional MR images, and incorporated a slice-attention mechanism, to produce a CNN score of 0-1 for NPC probability. Threefold cross-validation was performed in 399 patients. CNN scores between the NPC and benign hyperplasia groups were compared using Student's t test. Receiver operating characteristic with the area under the curve (AUC) was performed to identify the optimal CNN score threshold. RESULTS: In each fold, significant differences were observed in the CNN scores between the NPC and benign hyperplasia groups (p < .01). The AUCs ranged from 0.95 to 0.97 with no significant differences between the folds (p = .35 to .92). The combined AUC from all three folds (n = 399) was 0.96, with an optimal CNN score threshold of > 0.71, producing a sensitivity, specificity, and accuracy of 92.4%, 90.6%, and 91.5%, respectively, for NPC detection. CONCLUSION: Our CNN method applied to T2-weighted MRI could discriminate between malignant and benign tissues in the nasopharynx, suggesting that it as a promising approach for the automated detection of early-stage NPC. KEY POINTS: • The convolutional neural network (CNN)-based algorithm could automatically discriminate between malignant and benign diseases using T2-weighted fat-suppressed MR images. • The CNN-based algorithm had an accuracy of 91.5% with an area under the receiver operator characteristic curve of 0.96 for discriminating early-stage T1 nasopharyngeal carcinoma from benign hyperplasia. • The CNN-based algorithm had a sensitivity of 92.4% and specificity of 90.6% for detecting early-stage nasopharyngeal carcinoma.
Entities:
Keywords:
Computational neural network; Deep learning; Early detection of cancer; Hyperplasia; Nasopharyngeal carcinoma
Authors: Ianto Lin Xi; Yijun Zhao; Robin Wang; Marcello Chang; Subhanik Purkayastha; Ken Chang; Raymond Y Huang; Alvin C Silva; Martin Vallières; Peiman Habibollahi; Yong Fan; Beiji Zou; Terence P Gade; Paul J Zhang; Michael C Soulen; Zishu Zhang; Harrison X Bai; S William Stavropoulos Journal: Clin Cancer Res Date: 2020-01-14 Impact factor: 12.531
Authors: Sree Harsha Tirumani; Ata A Rahnemai-Azar; Jonathan D Pierce; Keval D Parikh; Sooyoung S Martin; Robert Gilkeson; Nikhil H Ramaiya Journal: Abdom Radiol (NY) Date: 2021-01-04
Authors: Wai Tong Ng; Barton But; Horace C W Choi; Remco de Bree; Anne W M Lee; Victor H F Lee; Fernando López; Antti A Mäkitie; Juan P Rodrigo; Nabil F Saba; Raymond K Y Tsang; Alfio Ferlito Journal: Cancer Manag Res Date: 2022-01-26 Impact factor: 3.989