TY - GEN
T1 - MRI-guided Automated Delineation of Gross Tumor Volume for Nasopharyngeal Carcinoma using Deep Learning
AU - Yue, Meiyan
AU - Dai, Zhenhui
AU - He, Jiahui
AU - Xie, Yaoqin
AU - Zaki, Nazar
AU - Qin, Wenjian
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported by the National Natural Science Foundation of China (No. 61901463and U20A20373), and the Shenzhen Science and Technology Program of China grant JCYJ20200109115420720; Youth Innovation Promotion Association of CAS 2022365. The authors would like to also acknowledge support from the United Arab Emirates University.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In this paper, we propose a novel deep learning-based automatic delineation method of nasopharynx gross tumor volume (GTVnx) by combing computed tomography (CT) and magnetic resonance imaging (MRI) modalities. The purpose of this study is to explore whether MRI can provide additional information to improve the accuracy of delineation on CT. The proposed model can adaptively leverage the high contrast information of MRI into the automated delineation of GTVnx on CT in nasopharyngeal carcinoma (NPC) radiotherapy. In this study, the dataset collected from 192 patients with NPC was used to verify the performance of the proposed method. The average Dice Similarity Coefficient, 95% Hausdorff Distance and Average Symmetric Surface Distance of the segmentation results predicted by the proposed model are 0.7181, 9.6637mm, and 2.8014mm, respectively, which outperformed that of the single-modal and the concatenation-based multi-modal segmentation models.
AB - In this paper, we propose a novel deep learning-based automatic delineation method of nasopharynx gross tumor volume (GTVnx) by combing computed tomography (CT) and magnetic resonance imaging (MRI) modalities. The purpose of this study is to explore whether MRI can provide additional information to improve the accuracy of delineation on CT. The proposed model can adaptively leverage the high contrast information of MRI into the automated delineation of GTVnx on CT in nasopharyngeal carcinoma (NPC) radiotherapy. In this study, the dataset collected from 192 patients with NPC was used to verify the performance of the proposed method. The average Dice Similarity Coefficient, 95% Hausdorff Distance and Average Symmetric Surface Distance of the segmentation results predicted by the proposed model are 0.7181, 9.6637mm, and 2.8014mm, respectively, which outperformed that of the single-modal and the concatenation-based multi-modal segmentation models.
KW - deep learning
KW - multi-modality
KW - nasopharyngeal carcinoma
KW - segmentation
UR - http://www.scopus.com/inward/record.url?scp=85137903041&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137903041&partnerID=8YFLogxK
U2 - 10.1109/CBMS55023.2022.00058
DO - 10.1109/CBMS55023.2022.00058
M3 - Conference contribution
AN - SCOPUS:85137903041
T3 - Proceedings - IEEE Symposium on Computer-Based Medical Systems
SP - 292
EP - 296
BT - Proceedings - 2022 IEEE 35th International Symposium on Computer-Based Medical Systems, CBMS 2022
A2 - Shen, Linlin
A2 - Gonzalez, Alejandro Rodriguez
A2 - Santosh, KC
A2 - Lai, Zhihui
A2 - Sicilia, Rosa
A2 - Almeida, Joao Rafael
A2 - Kane, Bridget
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 35th IEEE International Symposium on Computer-Based Medical Systems, CBMS 2022
Y2 - 21 July 2022 through 23 July 2022
ER -