Machine Learning Methods for Prediction of Dose Distribution and Response to Treatmentin Tumor Precision Radiotherapy: A Review
Liu Guocai1,2#*, Gu Dongdong1,3, Liu Jinguang1,4
1(College of Electrical and Information Engineering, Hunan University, Changsha 410082, China) 2(National Engineering Research Center for Robot Visual Perception and Control Technology, Changsha 410082, China) 3(Shanghai United Imaging Intelligence Co.,Ltd., Shanghai 200032, China) 4(School of Computational Science and Electronics, Hu′nan Institute of Engineering, Xiangtan 411104, Hunan, China)
Abstract：Intensity modulated radiation therapy (IMRT) is a main technology for tumor treatment in clinics. In order to design a clinically acceptable and executable IMRT plan, key factors including radiotherapy dose calculation, dose distribution prediction and optimization evaluation are required to carefully consider. Meanwhile, it also needs to predict and evaluate the outcome, toxicity and side effects of radiotherapy and chemotherapy. This article reviewed machine learning methods based on the images for dose distribution prediction and responses to the tumor radiotherapy and chemotherapy, including deep learning methods for dose prediction as well as deep learning, radiomics, logistic regression methods for outcome prediction of IMRT, stereotactic body radiotherapy (SBRT), volumetric arc modulated radiation therapy (VMAT). Finally, the future research directions and research contents were proposed.
刘国才, 顾冬冬, 刘劲光. 肿瘤精确放射治疗剂量分布和疗效预测的机器学习方法综述[J]. 中国生物医学工程学报, 2022, 41(6): 744-758.
Liu Guocai, Gu Dongdong, Liu Jinguang. Machine Learning Methods for Prediction of Dose Distribution and Response to Treatmentin Tumor Precision Radiotherapy: A Review. Chinese Journal of Biomedical Engineering, 2022, 41(6): 744-758.
[1] Zheng Rongshou, Zhang Siwei,Zeng Hongmei, et al. Cancer incidence and mortality in China, 2016 [J]. Journal of the National Cancer Center, 2022, 2 (1): 1-9. [2] Siegel RL, Miller KD,Fuchs HE, et al. Cancer statistics, 2022 [J]. CA: A Cancer Journal for Clinicians, 2022, 72(1): 7-33. [3] Sung Hyuna, 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: A Cancer Journal for Clinicians, 2021, 71(3):209-249. [4] Bernier J, Hall EJ, Giaccia A. Radiation oncology: a century of achievements [J]. Nature Reviews Cancer, 2004, 4(9): 737-747. [5] Barragán-Montero A, Bibal A, Dastarac MH, et al. Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency [J]. Phys Med Biol, 2022,67: 11TR01. [6] Chen Zihang, Lin Li, Wu Chenfei, et al. Artificial intelligence for assisting cancer diagnosis and treatment in the era of precision medicine [J]. Cancer Communications, 2021, 41:1100-1115. [7] Momin S, Fu Yabo, Lei Yang, et al. Knowledge-based radiation treatment planning: A data-driven method survey [J]. Journal of Applied Clinical Medical Physics, 2021, 22: 16-44. [8] Wang Mingqing, Zhang Qilin, Lam S, et al. A review on application of deep learning algorithms in external beam radiotherapy automated treatment planning [J]. Frontiers in Oncology, 2020, 10: 580919). [9] Sahiner B, Pezeshk A, Hadjiiski LM, et al. Deep learning in medical imaging and radiation therapy [J]. Medical Physics, 2019, 46(1): e1-e36. [10] Wang Chunhao, Zhu Xiaofeng, Julian CH, et al. Artificial intelligence in radiotherapy treatment planning: present and future [J]. Technology in Cancer Research & Treatment, 2019, 18: 1-11. [11] 刘国才, 顾冬冬, 刘骁, 等. 用于肿瘤调强放射治疗影像分析与转换的深度学习方法 [J]. 中国生物医学工程学报, 2022, 41(2):224-237. [12] Yi X, Walia E, Babyn P. Generative adversarial network in medical imaging: a review [J]. Medical Image Analysis, 2019, 58(101552): 1-20. [13] Ge Yaorong, Wu QJ. Knowledge-based planning for intensity-modulated radiation therapy: a review of data-driven approaches [J]. Medical Physics, 2019, 46(6): 2760-2765. [14] Eriksson O,Zhang Tianfang. Robust automated radiation therapy treatment planning using scenario-specific dose prediction and robust dose mimicking [J]. Medical Physics, 2022, 49(6): 3564-3573. [15] Neph R, Lv Qihui, Huang Yangsibo, et al. DeepMC: a deep learning method for efficient Monte Carlo beamlet dose calculation by predictive denoising in magnetic resonance-guided radiotherapy [J]. Physics in Medicine & Biology, 2021, 66(3) 035022. [16] Liu Shuolin, Zhang Jingjing, Li Teng, et al. Technical Note: cacascade 3D U-Net for dose prediction in radiotherapy [J]. Medical Physics, 2021, 48(9):5574-5582. [17] Gronberg MP, Gay SS, Netherton TJ,et al. Technical Note: dose prediction for head and neck radiotherapy using a three-dimensional dense dilated U-net architecture [J]. Medical Physics, 2021,48(9):5567-5573. [18] Chen Xinyuan, Men Kuo, Zhu Ji,et al. DVHnet: a deep learning-based prediction of patient-specific dose volume histograms for radiotherapy planning [J]. Medical Physics, 2021, 48(6):2705-2713. [19] Tsekas G, Bol GH, Raaymakers BQ, et al. DeepDose: a robust deep learning-based dose engine for abdominal tumors in a 1.5 T MRI radiotherapy system [J]. Physics in Medicine & Biology, 2021, 66(6):065017:1-8. [20] Shadab M, Yang Lei, Wang Tonghe, et al. Learning-based dose prediction for pancreatic stereotactic body radiation therapy using dual pyramid adversarial network [J]. Physics in Medicine & Biology, 2021, 66(105006):1-17. [21] Nguyen D, Long T, Jia X, et al. A feasibility study for predicting optimal radiation therapy dose distributions of prostate cancer patients from patient anatomy using deep learning [J]. Scientific Reports, 2019, 9(1): 1-10. [22] Nguyen D, Jia X, Sher D, et al. 3D radiotherapy dose prediction on head and neck cancer patients with a hierarchically densely connected U-net deep learning architecture [J]. Physics in Medicine & Biology, 2019, 64(6): 065020. [23] Barragán-Montero AM, Nguyen D, Lu W, et al. Three-dimensional dose prediction for lung IMRT patients with deep neural networks: robust learning from heterogeneous beam configurations [J]. Medical Physics, 2019, 46(8): 3679-3691. [24] Nguyen D, Barkousaraie AS, Shen Chenyang, et al. Generating pareto optimal dose distributions for radiation therapy treatment planning [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Shenzhen: Springer-Cham, 2019: 59-67. [25] Chen Xinyuan, Men Kuo, Li Yexiong, et al. A feasibility study on an automated method to generate patient-specific dose distributions for radiotherapy using deep learning [J]. Medical Physics, 2019, 46(1): 56-64. [26] Kearney V, Chan JW, Haaf S, et al. DoseNet: a volumetric dose prediction algorithm using 3D fully-convolutional neural networks [J]. Physics in Medicine & Biology, 2018, 63(23): 235022. [27] Campbell WG, Miften M, Olsen L, et al. Neural network dose models for knowledge-based planning in pancreatic SBRT [J]. Medical Physics, 2017, 44(12): 6148-6158. [28] Mashayekhi M, Tapia IR, Balagopal A, et al. Site-agnostic 3D dose distribution prediction with deep learning neural networks[J]. Medical Physics, 2022, 49(3):1391-1406. [29] Mahmood R, Babier A, McNiven A, et al. Automated treatment planning in radiation therapy using generative adversarial networks [C]// Proceedings of the 3rd Machine Learning for Healthcare Conference. Palo Alto: PMLR, 2018: 484-499. [30] Babier A, Mahmood R, McNiven AL, et al. Knowledge-based automated planning with three-dimensional generative adversarial networks [J]. Medical Physics, 2020, 47(2): 297-306. [31] Zhan Bo, Xiao Jianghong, Cao Chongyang, et al. Multi-constraint generative adversarial network for dose prediction in radiotherapy [J]. Medical Image Analysis, 2022,77:102339. [32] Momin S, Lei Yang, Wang Tonghe, et al. Learning-based dose prediction for pancreatic stereotactic body radiation therapy using dual pyramid adversarial network [J]. Physics in Medicine & Biology, 2021, 66:125019. [33] Mentzel F, Kröninger K, Lerch M, et al. Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks [J]. Medical Physics, 2022, 49(5):3389-3404. [34] Fan Jiawei, Wang Jiazhou, Chen Zhi, et al. Automatic treatment planning based on three-dimensional dose distribution predicted from deep learning technique [J]. Medical Physics, 2019, 46(1): 370-381. [35] Petersson K, Nilsson P, Engström P, et al. Evaluation of dual-arc VMAT radiotherapy treatment plans automatically generated via dose mimicking [J]. Acta Oncologica, 2016, 55(4): 523-525. [36] Wieser HP, Cisternas E, Wahl N, et al. Development of the opensource dose calculation and optimization toolkit matRad [J]. Medical Physics, 2017, 44(6):2556-2568. [37] Pota M, Scalco E, Sanguineti G, et al. Early prediction of radiotherapy-induced parotid shrinkage and toxicity based on CT radiomics and fuzzy classification [J]. Artificial Intelligence in Medicine, 2017, 81: 41-53. [38] MD Anderson Cancer Center. Investigation of radiomic signatures for local recurrence using primary tumor texture analysis in oropharyngeal head and neck cancer patients [J]. Scientific Reports, 2018, 8:1524. [39] Cunliffe A, Armato IIISG, Castillo R, et al. Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development [J]. International Journal of Radiation Oncology Biology Physics, 2015, 91(5): 1048-1056. [40] Li Qian, Kim J, Balagurunathan Y, et al. Imaging features from pretreatment CT scans are associated with clinical outcomes in nonsmall cell lung cancer patients treated with stereotactic body radiotherapy [J]. Medical Physics, 2017, 44(8): 4341-4349. [41] Mattonen SA, Palma A, Johnson C, et al. Detection of local cancer recurrence after stereotactic ablative radiation therapy for lung cancer: physician performance versus radiomic assessment [J]. International Journal of Radiation Oncology Biology Physics, 2016, 94(5): 1121-1128. [42] Klement RJ, Allgäuer M, Appold S, et al. Support vector machine-based prediction of local tumor control after stereotactic body radiation therapy for early-stage non-small cell lung cancer [J]. International Journal of Radiation Oncology Biology Physics, 2014, 88(3): 732-738. [43] Gnep K, Fargeas A, Gutiérrez-Carvajal RE, et al. Haralick textural features on T2-weighted MRI are associated with biochemical recurrence following radiotherapy for peripheral zone prostate cancer [J]. Journal of Magnetic Resonance Imaging, 2017, 45(1): 103-117. [44] Cui Yi, Tha KK, Terasaka S, et al. Prognostic imaging biomarkers in glioblastoma: development and independent validation on the basis of multiregion and quantitative analysis of MR images [J]. Radiology, 2016, 278(2): 546-553. [45] Bogowicz M, Leijenaar RT, Tanadini-Lang S, et al. Post-radiochemotherapy PET radiomics in head and neck cancer-the influence of radiomics implementation on the reproducibility of local control tumor models [J]. Radiotherapy Oncology, 2017, 125(3): 385-391. [46] Bogowicz M, Riesterer O, Ikenberg K, et al. Computed tomography radiomics predicts HPV status and local tumor control after definitive radiochemotherapy in head and neck squamous cell carcinoma [J]. International Journal of Oncology Biology Physics, 2017, 99(4): 921-928. [47] Dong Xinzhe, Xing Ligang, Wu Peipei, et al. Three-dimensional positron emission tomography image texture analysis of esophageal squamous cell carcinoma: relationship between tumor 18F-fluorodeoxyglucose uptake heterogeneity, maximum standardized uptake value, and tumor stage [J]. Nuclear Medicine Communications, 2013, 34(1): 40-46. [48] Yip SS, Coroller TP, Sanford NN, et al. Relationship between the temporal changes in positron-emission-tomography-imaging-based textural features and pathologic response and survival in esophageal cancer patients [J]. Frontiers in Oncology, 2016, 6: 72. [49] Aerts HJ, Velazquez ER, Leijenaar RT, et al. Decoding tumor phenotype by noninvasive imaging using a quantitative radiomics approach [J]. Nature Communications, 2014, 5(1): 1-9. [50] Aerts HJ, Grossmann P, Tan Y, et al. Defining a radiomic response phenotype: a pilot study using targeted therapy in NSCLC [J]. Scientific Reports, 2016, 6(1): 1-10. [51] Cook GJ, Yip C, Siddique M, et al. Are pretreatment 18F-FDG PET tumor textural features in non-small cell lung cancer associated with response and survival after chemoradiotherapy? [J]. Journal of Nuclear Medicine, 2013, 54(1): 19-26. [52] Carvalho S, Leijenaar R, Troost E, et al. Early variation of FDG-PET radiomics features in NSCLC is related to overall survival-the “delta radiomics” concept [J]. Radiotherapy Oncology, 2016, 118: S20-S21. [53] Fave X, Zhang Lifei, Yang Jinzhong, et al. Delta-radiomics features for the prediction of patient outcomes in non-small cell lung cancer [J]. Scientific Reports, 2017, 7(1): 1-11. [54] Veduruparthi BK, Mukherjee J, Das PP, et al. Novel radiomic feature for survival prediction of lung cancer patients using low-dose CBCT images [OL]. https://arxiv.org/pdf/2003.03537.pdf, 2003-03-07/2020-11-16. [55] Coroller TP, Grossmann P, Hou Y, et al. CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma [J]. Radiotherapy Oncology, 2015, 114(3): 345-350. [56] Rao SX, Lambregts DM, Schnerr RS, et al. CT texture analysis in colorectal liver metastases: a better way than size and volume measurements to assess response to chemotherapy? [J]. United European Gastroenterology Journal, 2016, 4(2): 257-263. [57] Nie Ke, Shi Liming, Chen Qin, et al. Rectal cancer: assessment of neoadjuvant chemoradiation outcome based on radiomics of multiparametric MRI [J]. Clinical Cancer Research, 2016, 22(21): 5256-5264. [58] Zhen Xin, Chen Jiawei, Zhong Zichun, et al. Deep convolutional neural network with transfer learning for rectum toxicity prediction in cervical cancer radiotherapy: a feasibility study [J]. Physics in Medicine Biology, 2017, 62(21): 8246. [59] Dohopolski M, Wang K, Morgan H, et al. Use of deep learning to predict the need for aggressive nutritional supplementation during head and neck radiotherapy [J]. Radiotherapy and Oncology, 2022, 171: 129-138. [60] Wei L, Owen D, Rosen B, et al. A deep survival interpretable radiomics model of hepatocellular carcinoma patients [J]. Physica Medica, 2021, 82: 295-305. [61] Lao Jiangwei, Chen Yinsheng, Li Zhicheng, et al. A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme [J]. Scientific Reports, 2017, 7(1): 1-8. [62] Chen Antong, Saouaf J, Zhou Bo, et al. A deep learning-facilitated radiomics solution for the prediction of lung lesion shrinkage in non-small cell lung cancer trials [C]// 2020 IEEE 17th International Symposium on Biomedical Imaging. Iowa City: IEEE, 2020: 678-682. [63] Peng Jie, Kang Shuai, Ning Zhengyuan, et al. Residual convolutional neural network for predicting response of transarterial chemoembolization in hepatocellular carcinoma from CT imaging [J]. European Radiology, 2020, 30(1): 413-424. [64] Le WT, Vorontsov E, Romero FP, et al. Cross-institutional outcome prediction for head and neck cancer patients using self-attention neural networks [J]. Scientific Reports, 2022, 12(1): 1-17. [65] Wang R, Guo J, Zhou Z, et al. Locoregional recurrence prediction in head & neck cancer based on multi-modality and multi-view feature expansion[J]. Physics in Medicine & Biology, 2022, 67: 125004. [66] Anaka S, Kadoya N, Sugai Y, et al. A deep learning-based radiomics approach to predict head and neck tumor regression for adaptive radiotherapy [J]. Scientific Reports, 2022, 12(1): 1-13. [67] Peng Hao, Dong Di, Fang Mengjie, et al. Prognostic value of deep learning PET/CT-based radiomics: potential role for future individual induction chemotherapy in advanced nasopharyngeal carcinoma [J]. Clinical Cancer Research, 2019, 25(14): 4271-4279. [68] Ypsilantis PP, Siddique M, Sohn HM, et al. Predicting response to neoadjuvant chemotherapy with PET imaging using convolutional neural networks [J]. PLoS ONE, 2015, 10(9): e0137036. [69] Hu Yihuai, Xie Chenyi, Yang Hong, et al. Computed tomography-based deep-learning prediction of neoadjuvant chemoradiotherapy treatment response in esophageal squamous cell carcinoma [J]. Radiotherapy Oncology, 2021, 154: 6-13. [70] Watson M, Baimas-George M, Murphy K, et al. Use of deep learning to predict tumor response to neoadjuvant therapy in pancreatic adenocarcinoma: pure and hybrid modelling [J]. HPB, 2020, 22: S38. [71] Wang Li, Wang Lihui, Chen Qijian, et al. Convolutional restricted boltzmann machine based-radiomics for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer [OL]. https://arxiv.org/pdf/1905.13312.pdf, 2019-05-23/ 2020-11-16. [72] Ravichandran K, Braman N, Janowczyk A, et al. A deep learning classifier for prediction of pathological complete response to neoadjuvant chemotherapy from baseline breast DCE-MRI [C]//SPIE Medical Imaging. Houston: SPIE, 2018: 105750C. [73] Huynh BQ, Antropova N, Giger ML. Comparison of breast DCE-MRI contrast time points for predicting response to neoadjuvant chemotherapy using deep convolutional neural network features with transfer learning [C]// SPIE Medical Imaging. Orlando: SPIE, 2017: 101340U. [74] Jiang Meng, Li Changli, Luo Xiaomao, et al. Ultrasound-based deep learning radiomics in the assessment of pathological complete response to neoadjuvant chemotherapy in locally advanced breast cancer [J]. European Journal of Cancer, 2021, 147: 95-105. [75] Duanmu H, Huang PB, Brahmavar S, et al. Prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer using deep learning with integrative imaging, molecular and demographic data [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Lima: Springer-Cham, 2020: 242-252. [76] Qu Yuhong, Zhu Haitao, Cao Kun, et al. Prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer using a deep learning (DL) method [J]. Thoracic Cancer, 2020, 11(3): 651-658. [77] Bibault JE, Giraud P, Housset M, et al. Deep learning and radiomics predict complete response after neo-adjuvant chemoradiation for locally advanced rectal cancer [J]. Scientific Reports, 2018, 8(1): 1-8. [78] Braman N, Adoui ME, Vulchi M, et al. Deep learning-based prediction of response to HER2-targeted neoadjuvant chemotherapy from pre-treatment dynamic breast MRI: a multi-institutional validation study [OL]. https://arxiv.org/pdf/2001.08570.pdf, 2020-06-22/2020-11-16. [79] Zhang Xiaoyan, Wang Lin, Zhu Haitao, et al. Predicting rectal cancer response to neoadjuvant chemoradiotherapy using deep learning of diffusion kurtosis MRI [J]. Radiology, 2020, 296(1): 56-64. [80] Zhu Haibin, Xu Da, Ye Meng, et al. Deep learning-assisted magnetic resonance imaging prediction of tumor response to chemotherapy in patients with colorectal liver metastases [J]. International Journal of Cancer, 2021, 148(7): 1717-1730. [81] Fu Jie, Zhong Xinran, Li Ning, et al. Deep learning-based radiomic features for improving neoadjuvant chemoradiation response prediction in locally advanced rectal cancer [J]. Physics in Medicine Biology, 2020, 65(7): 075001. [82] Jang B-S, Lim YJ, Song C, et al. Image-based deep learning model for predicting pathological response in rectal cancer using post-chemoradiotherapy magnetic resonance imaging [J]. Radiotherapy Oncology, 2021, 161: 183-190. [83] Jin C, YuH, Ke J, et al. Predicting treatment response from longitudinal images using multi-task deep learning [J]. Nature Communications, 2021, 12(1): 1-11. [84] Cha KH, Hadjiiski L, Chan H-P, et al. Bladder cancer treatment response assessment in CT using radiomics with deep-learning [J]. Scientific Reports, 2017, 7(1): 1-12.
