Study of three-dimensional dose distribution based-deep learning in predicting distant metastasis in head and neck cancer
Cai Jiajun1, Li Yongbao2, Xiao Fan1, Qi Mengke1, Lu Xingyu1, Zhou Linghong1, Song Ting1
1School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China; 2State Key Laboratory of Oncology in South China, Sun Yat-sen University Cancer Center, Guangzhou 510060, China
Abstract：Objective To investigate the role of three-dimensional dose distribution-based deep learning model in predicting distant metastasis of head and neck cancer. Methods Radiotherapy and clinical follow-up data of 237 patients with head and neck cancer undergoing intensity-modulated radiotherapy (IMRT) from 4 different institutions were collected. Among them, 131 patients from HGJ and CHUS institutions were used as the training set, 65 patients from CHUM institution as the validation set, and 41 patients from HMR institution as the test set. Three-dimensional dose distribution and GTV contours of 131 patients in the training set were input into the DM-DOSE model for training and then validated with validation set data. Finally, the independent test set data were used for evaluation. The evaluation content included the area under receiver operating characteristic curve (AUC), balanced accuracy, sensitivity, specificity, concordance index and Kaplan-Meier survival curve analysis. Results In terms of prognostic prediction of distant metastasis of head and neck cancer, the DM-DOSE model based on three-dimensional dose distribution and GTV contours achieved the optimal prognostic prediction performance, with an AUC of 0.924, and could significantly distinguish patients with high and low risk of distant metastasis (log-rank test, P<0.001). Conclusion Three-dimensional dose distribution has good predictive value for distant metastasis in head and neck cancer patients treated with IMRT, and the constructed prediction model can effectively predict distant metastasis.
Cai Jiajun,Li Yongbao,Xiao Fan et al. Study of three-dimensional dose distribution based-deep learning in predicting distant metastasis in head and neck cancer[J]. Chinese Journal of Radiation Oncology, 2023, 32(5): 422-429.
[1] Vigneswaran N, Williams MD.Epidemiologic trends in head and neck cancer and aids in diagnosis[J]. Oral Maxillofac Surg Clin North Am, 2014,26(2):123-141. DOI: 10.1016/j.coms.2014.01.001. [2] Sung H, Ferlay J, Siegel RL, et al.Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021,71(3):209-249. DOI: 10.3322/caac.21660. [3] Lacas B, Bourhis J, Overgaard J, et al.Role of radiotherapy fractionation in head and neck cancers (MARCH): an updated meta-analysis[J]. Lancet Oncol, 2017,18(9):1221-1237. DOI: 10.1016/S1470-2045(17)30458-8. [4] Chow L.Head and Neck Cancer[J]. N Engl J Med, 2020,382(1):60-72. DOI: 10.1056/NEJMra1715715. [5] Vallières M, Kay-Rivest E, Perrin LJ, et al.Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer[J]. Sci Rep, 2017,7(1):10117. DOI: 10.1038/s41598-017-10371-5. [6] Diamant A, Chatterjee A, Vallières M, et al.Deep learning in head & neck cancer outcome prediction[J]. Sci Rep, 2019,9(1):2764. DOI: 10.1038/s41598-019-39206-1. [7] Pang S, Field M, Dowling J, et al.Training radiomics-based CNNs for clinical outcome prediction: challenges, strategies and findings[J]. Artif Intell Med, 2022,123:102230. DOI: 10.1016/j.artmed.2021.102230. [8] Caudell JJ, Ward MC, Riaz N, et al.Volume, dose, and fractionation considerations for IMRT-based reirradiation in head and neck cancer: a multi-institution analysis[J]. Int J Radiat Oncol Biol Phys, 2018,100(3):606-617. DOI: 10.1016/j.ijrobp.2017.11.036. [9] Wu A, Li Y, Qi M, et al.Dosiomics improves prediction of locoregional recurrence for intensity modulated radiotherapy treated head and neck cancer cases[J]. Oral Oncol, 2020,104:104625. DOI: 10.1016/j.oraloncology.2020.104625. [10] Han K, Joung JF, Han M, et al. Locoregional recurrence prediction using a deep neural network of radiological and radiotherapy images[J]. J Pers Med, 2022,12(2)DOI: 10.3390/jpm12020143. [11] Esteva A, Kuprel B, Novoa RA, et al.Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017,542(7639):115-118. DOI: 10.1038/nature21056. [12] Hosny A, Parmar C, Coroller TP, et al.Deep learning for lung cancer prognostication: a retrospective multi-cohort radiomics study[J]. PLoS Med, 2018,15(11):e1002711. DOI: 10.1371/journal.pmed.1002711. [13] Martin Vallières, Emily Kay-Rivest, Léo Jean Perrin, et al. (2017). Data from Head-Neck-PET-CT[DB/OL]// The Cancer Imaging Archive.[2021-9-27]. http://wiki.cancerimagingarchive.net/display/Public/Head-Neck- PET-CT. DOI: 10.7937/K9/TCIA.2017.8oje5q00. [14] Hara K, Kataoka H, Satoh Y.Can spatiotemporal 3D CNNS retrace the history of 2D CNNS and imagenet?[C]//Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE conference on Computer Vision and Pattern Recognition, 2018: 6546-6555. [15] Lin T Y, Goyal P, Girshick R, et al.Focal loss for dense object detection[C]//Proceedings of the IEEE international conference on computer vision. Venice: IEEE International Conference on Computer Vision, 2017: 2980-2988. [16] Perkins NJ, Schisterman EF.The inconsistency of "optimal" cutpoints obtained using two criteria based on the receiver operating characteristic curve[J]. Am J Epidemiol, 2006,163(7):670-675. DOI: 10.1093/aje/kwj063. [17] Kaplan EL, Meier P.Nonparametric estimation from incomplete observations[J]. Am Statist Associat J, 1958, 53(282): 457-481. DOI: 10.1007/978-1-4612-4380-9_25. [18] da Cruz HF, Pfahringer B, Martensen T, et al. Using interpretability approaches to update "black-box" clinical prediction models: an external validation study in nephrology[J]. Artif Intell Med, 2021,111:101982. DOI: 10.1016/j.artmed.2020.101982. [19] Ferrari V, Cattari N, Fontana U, et al.Errata to "Parallax free registration for augmented reality optical see-through displays in the peripersonal space"[1] (DOI: 10.1109/TVCG.2020.3021534)[J]. IEEE Trans Vis Comput Graph, 2022,28(8):3069. DOI: 10.1109/TVCG.2022.3176417.
2023, Vol. 32 
