Lun M Wong1, Qi Yong H Ai1, Darren M C Poon2, Macy Tong2, Brigette B Y Ma2, Edwin P Hui2, Lin Shi1, Ann D King1. 1. Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong, China. 2. Department of Clinical Oncology, State Key Laboratory of Translational Oncology, The Chinese University of Hong Kong, Prince of Wales Hospital, Hong Kong, China.
Abstract
BACKGROUND: Convolutional neural networks (CNNs) have the potential to automatically delineate primary nasopharyngeal carcinoma (NPC) on magnetic resonance imaging (MRI), but currently, the literature lacks a module to introduce valuable pre-computed features into a CNN. In addition, most CNNs for primary NPC delineation have focused on contrast-enhanced MRI. To enable the use of CNNs in clinical applications where it would be desirable to avoid contrast agents, such as cancer screening or intra-treatment monitoring, we aim to develop a CNN algorithm with a positional-textural fully-connected attention (FCA) module that can automatically delineate primary NPCs on contrast-free MRI. METHODS: This retrospective study was performed in 404 patients with NPC who had undergone staging MRI. A proposed CNN algorithm incorporated with our positional-textural FCA module (Aproposed ) was trained on manually delineated tumours (M1st ) to automatically delineate primary NPCs on non-contrast-enhanced T2-weighted fat-suppressed (NE-T2W-FS) images. The performance of Aproposed , three well-established CNNs, Unet (Aunet ), Attention-Unet (Aatt ) and Dense-Unet (Adense ), and a second manual delineation repeated to evaluate human variability (M 2 nd ) were measured by comparing to the reference standard M 1 st to obtain the Dice similarity coefficient (DSC) and average surface distance (ASD). The Wilcoxon rank test was used to compare the performance of Aproposed against Aunet , Aatt , Adense and M 2 nd . RESULTS: Aproposed showed a median DSC of 0.79 (0.10) and ASD of 0.66 (0.84) mm. It performed better than the well-established networks Aunet [DSC =0.75 (0.12) and ASD =1.22 (1.73) mm], Aatt [DSC =0.75 (0.10) and ASD =0.96 (1.16) mm] and Adense [DSC =0.71 (0.14) and ASD =1.67 (1.92) mm] (all P<0.01), but slightly worse when compared to M 2 nd [DSC =0.81 (0.07) and ASD =0.56 (0.80) mm] (P<0.001). CONCLUSIONS: The proposed CNN algorithm has potential to accurately delineate primary NPCs on non-contrast-enhanced MRI. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.
BACKGROUND: Convolutional neural networks (CNNs) have the potential to automatically delineate primary nasopharyngeal carcinoma (NPC) on magnetic resonance imaging (MRI), but currently, the literature lacks a module to introduce valuable pre-computed features into a CNN. In addition, most CNNs for primary NPC delineation have focused on contrast-enhanced MRI. To enable the use of CNNs in clinical applications where it would be desirable to avoid contrast agents, such as cancer screening or intra-treatment monitoring, we aim to develop a CNN algorithm with a positional-textural fully-connected attention (FCA) module that can automatically delineate primary NPCs on contrast-free MRI. METHODS: This retrospective study was performed in 404 patients with NPC who had undergone staging MRI. A proposed CNN algorithm incorporated with our positional-textural FCA module (Aproposed ) was trained on manually delineated tumours (M1st ) to automatically delineate primary NPCs on non-contrast-enhanced T2-weighted fat-suppressed (NE-T2W-FS) images. The performance of Aproposed , three well-established CNNs, Unet (Aunet ), Attention-Unet (Aatt ) and Dense-Unet (Adense ), and a second manual delineation repeated to evaluate human variability (M 2 nd ) were measured by comparing to the reference standard M 1 st to obtain the Dice similarity coefficient (DSC) and average surface distance (ASD). The Wilcoxon rank test was used to compare the performance of Aproposed against Aunet , Aatt , Adense and M 2 nd . RESULTS: Aproposed showed a median DSC of 0.79 (0.10) and ASD of 0.66 (0.84) mm. It performed better than the well-established networks Aunet [DSC =0.75 (0.12) and ASD =1.22 (1.73) mm], Aatt [DSC =0.75 (0.10) and ASD =0.96 (1.16) mm] and Adense [DSC =0.71 (0.14) and ASD =1.67 (1.92) mm] (all P<0.01), but slightly worse when compared to M 2 nd [DSC =0.81 (0.07) and ASD =0.56 (0.80) mm] (P<0.001). CONCLUSIONS: The proposed CNN algorithm has potential to accurately delineate primary NPCs on non-contrast-enhanced MRI. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.
Entities:
Keywords:
Texture; convolutional neural network (CNN); head and neck; magnetic resonance imaging (MRI); nasopharyngeal carcinomas (NPCs)
Authors: A D King; A C Vlantis; T W C Yuen; B K H Law; K S Bhatia; B C Y Zee; J K S Woo; A T C Chan; K C A Chan; A T Ahuja Journal: AJNR Am J Neuroradiol Date: 2015-08-27 Impact factor: 3.825
Authors: Paul A Yushkevich; Joseph Piven; Heather Cody Hazlett; Rachel Gimpel Smith; Sean Ho; James C Gee; Guido Gerig Journal: Neuroimage Date: 2006-03-20 Impact factor: 6.556
Authors: K C Allen Chan; John K S Woo; Ann King; Benny C Y Zee; W K Jacky Lam; Stephen L Chan; Sam W I Chu; Constance Mak; Irene O L Tse; Samantha Y M Leung; Gloria Chan; Edwin P Hui; Brigette B Y Ma; Rossa W K Chiu; Sing-Fai Leung; Andrew C van Hasselt; Anthony T C Chan; Y M Dennis Lo Journal: N Engl J Med Date: 2017-08-10 Impact factor: 91.245
Authors: A D King; J K S Woo; Q Y Ai; J S M Chan; W K J Lam; I O L Tse; K S Bhatia; B C Y Zee; E P Hui; B B Y Ma; R W K Chiu; A C van Hasselt; A T C Chan; Y M D Lo; K C A Chan Journal: Ann Oncol Date: 2019-06-01 Impact factor: 32.976
Authors: A D King; J K S Woo; Q-Y Ai; F K F Mo; T Y So; W K J Lam; I O L Tse; A C Vlantis; K W N Yip; E P Hui; B B Y Ma; R W K Chiu; A T C Chan; Y M D Lo; K C A Chan Journal: AJNR Am J Neuroradiol Date: 2020-03 Impact factor: 3.825
Authors: Wenya Linda Bi; Ahmed Hosny; Matthew B Schabath; Maryellen L Giger; Nicolai J Birkbak; Alireza Mehrtash; Tavis Allison; Omar Arnaout; Christopher Abbosh; Ian F Dunn; Raymond H Mak; Rulla M Tamimi; Clare M Tempany; Charles Swanton; Udo Hoffmann; Lawrence H Schwartz; Robert J Gillies; Raymond Y Huang; Hugo J W L Aerts Journal: CA Cancer J Clin Date: 2019-02-05 Impact factor: 508.702