Abstract
Purpose
To investigate the treatment response prediction feasibility and accuracy of an integrated model combining computed tomography (CT) radiomic features and dosimetric parameters for patients with esophageal cancer (EC) who underwent concurrent chemoradiation (CRT) using machine learning.
Methods
The radiomic features and dosimetric parameters of 94 EC patients were extracted and modeled using Support Vector Classification (SVM) and Extreme Gradient Boosting algorithm (XGBoost). The 94-sample dataset was randomly divided into a 70-sample training subset and a 24-sample independent test set while keeping the class proportions intact via stratification. A receiver operating characteristic (ROC) curve was used to assess the performance of models using radiomic features alone and using combined radiomic features and dosimetric parameters.
Results
A total of 42 radiomic features and 18 dosimetric parameters plus the patients’ characteristic parameters were extracted for these 94 cases (58 responders and 36 non-responders). XGBoost plus principal component analysis (PCA) achieved an accuracy and area under the curve of 0.708 and 0.541, respectively, for models with radiomic features combined with dosimetric parameters, and 0.689 and 0.479, respectively, for radiomic features alone. Image features of GlobalMean X.333.1, Coarseness, Skewness, and GlobalStd contributed most to the model. The dosimetric parameters of gross tumor volume (GTV) homogeneity index (HI), Cord Dmax, Prescription dose, Heart-Dmean, and Heart-V50 also had a strong contribution to the model.
Conclusions
The model with radiomic features combined with dosimetric parameters is promising and outperforms that with radiomic features alone in predicting the treatment response of patients with EC who underwent CRT.
Key Points
• The model with radiomic features combined with dosimetric parameters is promising in predicting the treatment response of patients with EC who underwent CRT.
• The model with radiomic features combined with dosimetric parameters (prediction accuracy of 0.708 and AUC of 0.689) outperforms that with radiomic features alone (best prediction accuracy of 0.625 and AUC of 0.412).
• The image features of GlobalMean X.333.1, Coarseness, Skewness, and GlobalStd contributed most to the treatment response prediction model. The dosimetric parameters of GTV HI, Cord Dmax, Prescription dose, Heart-Dmean, and Heart-V50 also had a strong contribution to the model.
Similar content being viewed by others
Abbreviations
- 3DCRT:
-
Three-dimensional conformal radiotherapy
- AUC:
-
Area under curve
- CRT:
-
Chemoradiation
- CT:
-
Computed tomography
- EC:
-
Esophageal cancer
- FDG-PET:
-
Fluorodeoxyglucose positron emission tomography
- GLCM:
-
Gray-level co-occurrence matrix
- GTV:
-
Gross tumor volume
- HI:
-
Homogeneity index
- ID:
-
Intensity direct
- IMRT:
-
Intensity-modulated radiotherapy
- NID:
-
Neighbor intensity difference
- NR:
-
Non-responsive
- OARs:
-
Organs at risk
- OS:
-
Overall survival; CR: complete response
- PCA:
-
Principal component analysis
- RBF:
-
Radial basis function
- ROC:
-
Receiver operating characteristic
- RS:
-
Responsive
- SCC:
-
Squamous cell carcinoma
- SVM:
-
Support vector classification
- TPS:
-
Treatment planning system
- VMAT:
-
Volumetric-modulated arc therapy
- XGBoost:
-
Extreme Gradient Boosting algorithm
References
Torre LA, Bray F, Siegel RL, Ferlay J, Lortet-Tieulent J, Jemal A (2015) Global cancer statistics, 2012. CA Cancer J Clin 65:87–108
Wheeler JB, Reed CE (2012) Epidemiology of esophageal cancer. Surg Clin North Am 92:1077–1087
Kumagai K, Rouvelas I, Tsai JA et al (2014) Meta-analysis of postoperative morbidity and perioperative mortality in patients receiving neoadjuvant chemotherapy or chemoradiotherapy for resectable oesophageal and gastro-oesophageal junctional cancers. Br J Surg 101:321–338
Li M, Zhang X, Zhao F, Luo Y, Kong L, Yu J (2016) Involved-field radiotherapy for esophageal squamous cell carcinoma: theory and practice. Radiat Oncol 11:18
Minsky BD, Neuberg D, Kelsen DP et al (1999) Final report of intergroup trial 0122 (ECOG PE-289, RTOG 90-12): phase II trial of neoadjuvant chemotherapy plus concurrent chemotherapy and high-dose radiation for squamous cell carcinoma of the esophagus. Int J Radiat Oncol Biol Phys 43:517–523
Minsky BD, Pajak TF, Ginsberg RJ et al (2002) INT 0123 (radiation therapy oncology group 94-05) phase III trial of combined-modality therapy for esophageal cancer: high-dose versus standard-dose radiation therapy. J Clin Oncol 20:1167–1174
Ajani JA (2008) Gastroesophageal cancers: progress and problems. J Natl Compr Canc Netw 6:813–814
Luo Y, Mao Q, Wang X, Yu J, Li M (2017) Radiotherapy for esophageal carcinoma: dose, response and survival. Cancer Manag Res 10:13–21
Li JC, Liu D, Chen MQ et al (2012) Different radiation treatment in esophageal carcinoma: a clinical comparative study. J BUON 17:512–516
Chen YJ, Liu A, Han C et al (2007) Helical tomotherapy for radiotherapy in esophageal cancer: a preferred plan with better conformal target coverage and more homogeneous dose distribution. Med Dosim 32:166–171
Tong DK, Law S, Kwong DL, Chan KW, Lam AK, Wong KH (2010) Histological regression of squamous esophageal carcinoma assessed by percentage of residual viable cells after neoadjuvant chemoradiation is an important prognostic factor. Ann Surg Oncol 17:2184–2192
Chao YK, Chan SC, Liu YH et al (2009) Pretreatment T3–4 stage is an adverse prognostic factor in patients with esophageal squamous cell carcinoma who achieve pathological complete response following preoperative chemoradiotherapy. Ann Surg 249:392–396
Hammoud ZT, Kesler KA, Ferguson MK et al (2006) Survival outcomes of resected patients who demonstrate a pathologic complete response after neoadjuvant chemoradiation therapy for locally advanced esophageal cancer. Dis Esophagus 19:69–72
Muijs CT, Beukema JC, Pruim J et al (2010) A systematic review on the role of FDG-PET/CT in tumour delineation and radiotherapy planning in patients with esophageal cancer. Radiother Oncol 97:165–171
Foley KG, Hills RK, Berthon B et al (2018) Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal cancer. Eur Radiol 28(1):428–436
Miles KA, Lee TY, Goh V et al (2012) Experimental Cancer Medicine Centre Imaging Network Group. Current status and guidelines for the assessment of tumour vascular support with dynamic contrast-enhanced computed tomography. Eur Radiol 22:1430–1441
Djuric-Stefanovic A, Micev M, Stojanovic-Rundic S, Pesko P, Dj S (2015) Absolute CT perfusion parameter values after the neoadjuvant chemoradiotherapy of the squamous cell esophageal carcinoma correlate with the histopathologic tumor regression grade. Eur J Radiol 84:2477–2484
Desborders P, Ruan S, Modzelewski R et al (2017) Predictive value of initial FDG-PET features for treatment response and survival in esophageal cancer patients treated with chemo-radiation therapy using a random forest classifier. PLoS One 12:e0173208
Tixier F, Rest CC, Hatt M et al (2011) Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in esophageal cancer. J Nucl Med 52:369–378
Ganeshan B, Skogen K, Pressney I, Coutroubis D, Miles K (2012) Tumour heterogeneity in esophageal cancer assessed by CT texture analysis: preliminary evidence of an association with tumour metabolism, stage, and survival. Clin Radiol 67:157–164
Hou Z, Ren W, Li S et al (2017) Radiomic analysis in contrast-enhanced CT: predict treatment response to chemoradiotherapy in esophageal carcinoma. Oncotarget 8:104444–104454
Jin X, Yi J, Zhou Y, Yan H, Han C, Xie C (2013) CRT combined with a sequential VMAT boost in the treatment of upper thoracic esophageal cancer. J Appl Clin Med Phys 14:153–161
Wu Z, Xie C, Hu M et al (2014) Dosimetric benefits of IMRT and VMAT in the treatment of middle thoracic esophageal cancer: is the conformal radiotherapy still an alternative option? J Appl Clin Med Phys 15:93–101
Zhang L, Fried DV, Fave XJ, Hunter LA, Yang J, Court LE (2015) IBEX: an open infrastructure software platform to facilitate collaborative work in radiomics. Med Phys 42:1341–1353
Blaas J, Botha CP, Post FH (2008) Extensions of parallel coordinates for interactive exploration of large multi-timepoint data sets. IEEE Trans Vis Comput Graph 14:1436–1443
Burges CJC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2:121–167
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. AcmSigkdd international conference on Knowledge Discovery & Data Mining, pp 785–94
Minka TP (2001) Automatic choice of dimensionality for PCA. In: Advances in neural information processing systems, pp 598–604
Ganeshan B, Skogen K, Pressney I, Coutroubis D, Miles K (2012) Tumour heterogeneity in oesophageal cancer assessed by CT texture analysis: preliminary evidence of an association with tumour metabolism, stage, and survival. Clin Radiol 67:157–164
Yip C, Davnall F, Kozarski R, Landau DB et al (2015) Assessment of changes in tumor heterogeneity following neoadjuvant chemotherapy in primary esophageal cancer. Dis Esophagus 28:172–179
Lloyd S, Chang BW (2014) Current strategies in chemoradiation for esophageal cancer. J Gastrointest Oncol 5:156–165
O'Sullivan KE, Hurley ET, Hurley JP (2015) Understanding complete pathologic response in oesophageal cancer: implications for management and survival. Gastroenterol Res Pract 2015(2015):518281
Funding
This study has received funding by National Natural Science Foundation of China (11675122).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Congying Xie.
Conflict of interest
The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors has significant statistical expertise: Cong Liu.
Informed consent
Written informed consent was waived by the Institutional Review Board.
Ethical approval
Institutional Review Board approval was obtained.
Methodology
• retrospective
• observational
• performed at one institution
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jin, X., Zheng, X., Chen, D. et al. Prediction of response after chemoradiation for esophageal cancer using a combination of dosimetry and CT radiomics. Eur Radiol 29, 6080–6088 (2019). https://doi.org/10.1007/s00330-019-06193-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-019-06193-w