Abstract
Objectives
The aim of this study was two-fold: (1) to develop and externally validate a multiparameter MR-based machine learning model to predict the pathological complete response (pCR) in locally advanced rectal cancer (LARC) patients after neoadjuvant chemoradiotherapy (nCRT), and (2) to compare different classifiers’ discriminative performance for pCR prediction.
Methods
This retrospective study includes 151 LARC patients divided into internal (centre A, n = 100) and external validation set (centre B, n = 51). The clinical and MR radiomics features were derived to construct clinical, radiomics, and clinical-radiomics model. Random forest (RF), support vector machine (SVM), logistic regression (LR), K-nearest neighbor (KNN), naive Bayes (NB), and extreme gradient boosting (XGBoost) were used as classifiers. The predictive performance was assessed using the receiver operating characteristic (ROC) curve.
Results
Eleven radiomics and four clinical features were chosen as pCR-related signatures. In the radiomics model, the RF algorithm achieved 74.0% accuracy (an AUC of 0.863) and 84.4% (an AUC of 0.829) in the internal and external validation sets. In the clinical-radiomics model, RF algorithm exhibited high and stable predictive performance in the internal and external validation datasets with an AUC of 0.906 (87.3% sensitivity, 73.7% specificity, 76.0% accuracy) and 0.872 (77.3% sensitivity, 88.2% specificity, 86.3% accuracy), respectively. RF showed a better predictive performance than the other classifiers in the external validation datasets of three models.
Conclusions
The multiparametric clinical-radiomics model combined with RF algorithm is optimal for predicting pCR in the internal and external sets, and might help improve clinical stratifying management of LARC patients.
Key Points
• A two-centre study showed that radiomics analysis of pre- and post-nCRT multiparameter MR images could predict pCR in patients with LARC.
• The combined model was superior to the clinical and radiomics model in predicting pCR in locally advanced rectal cancer.
• The RF classifier performed best in the current study.
Similar content being viewed by others
Abbreviations
- AUC:
-
Area under the ROC curve
- CEA:
-
Carcinoembryonic antigen
- DL:
-
Deep learning
- DWI:
-
Diffusion-weighted imaging
- KNN:
-
K-nearest neighbor
- LARC:
-
Locally advanced rectal cancer
- LASSO:
-
Least absolute shrinkage and selection operator
- LoG:
-
Laplacian of Gaussian
- LR:
-
Logistic regression
- ML:
-
Machine learning
- NB:
-
Naive Bayes
- nCRT:
-
Neoadjuvant chemoradiotherapy
- pCR:
-
Pathologic complete response
- pN:
-
Pathologic N stage
- pT:
-
Pathologic N stage
- RF:
-
Random forest
- SVM:
-
Support vector machine
- T2WI:
-
T2-weighted imaging
- TME:
-
Total mesorectal excision
- TRG:
-
Tumour regression grade
- VOI:
-
Volume of interest
- XGBoost:
-
Extreme gradient boosting
References
Cardoso R, Guo F, Heisser T et al (2021) Colorectal cancer incidence, mortality, and stage distribution in European countries in the colorectal cancer screening era: an international population-based study. Lancet Oncol 22:1002–1013
Araghi M, Soerjomataram I, Jenkins M et al (2019) Global trends in colorectal cancer mortality: projections to the year 2035. Int J Cancer 144:2992–3000
Siegel RL, Miller KD, Fuchs HE, Jemal A (2022) Cancer statistics, 2022. CA Cancer J Clin 72:7–33
Oronsky B, Reid T, Larson C, Knox SJ (2020) Locally advanced rectal cancer: the past, present, and future. Semin Oncol 47:85–92
Polanco PM, Mokdad AA, Zhu H, Choti MA, Huerta S (2018) Association of adjuvant chemotherapy with overall survival in patients with rectal cancer and pathologic complete response following neoadjuvant chemotherapy and resection. JAMA Oncol 4:938–943
Maas M, Nelemans PJ, Valentini V et al (2010) Long-term outcome in patients with a pathological complete response after chemoradiation for rectal cancer: a pooled analysis of individual patient data. Lancet Oncol 11:835–844
Martin S, Heneghan H, Winter D (2012) Systematic review and meta-analysis of outcomes following pathological complete response to neoadjuvant chemoradiotherapy for rectal cancer. J Br Surg 99:918–928
Smith JJ, Strombom P, Chow OS et al (2019) Assessment of a watch-and-wait strategy for rectal cancer in patients with a complete response after neoadjuvant therapy. JAMA Oncol 5:e185896
Dossa F, Chesney TR, Acuna SA, Baxter NN (2017) A watch-and-wait approach for locally advanced rectal cancer after a clinical complete response following neoadjuvant chemoradiation: a systematic review and meta-analysis. Lancet Gastroenterol Hepatol 2:501–513
van der Valk MJ, Hilling DE, Bastiaannet E et al (2018) Long-term outcomes of clinical complete responders after neoadjuvant treatment for rectal cancer in the International Watch & Wait Database (IWWD): an international multicentre registry study. Lancet 391:2537–2545
Roh MS, Colangelo LH, O’Connell MJ et al (2009) Preoperative multimodality therapy improves disease-free survival in patients with carcinoma of the rectum: NSABP R-03. J Clin Oncol 27:5124
Al-Sukhni E, Attwood K, Mattson DM, Gabriel E, Nurkin SJ (2016) Predictors of pathologic complete response following neoadjuvant chemoradiotherapy for rectal cancer. Ann Surg Oncol 23:1177–1186
Meng X, Xia W, Xie P et al (2019) Preoperative radiomic signature based on multiparametric magnetic resonance imaging for noninvasive evaluation of biological characteristics in rectal cancer. Eur Radiol 29:3200–3209
Huang CM, Huang MY, Huang CW et al (2020) Machine learning for predicting pathological complete response in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy. Sci Rep 10:12555
Zhao X, Xie P, Wang M et al (2020) Deep learning-based fully automated detection and segmentation of lymph nodes on multiparametric-mri for rectal cancer: a multicentre study. EBioMedicine 56:102780
Liang M, Cai Z, Zhang H et al (2019) Machine learning-based analysis of rectal cancer MRI radiomics for prediction of metachronous liver metastasis. Acad Radiol 26:1495–1504
Jin C, Yu H, Ke J et al (2021) Predicting treatment response from longitudinal images using multi-task deep learning. Nat Commun 12:1851
Cui Y, Yang X, Shi Z et al (2019) Radiomics analysis of multiparametric MRI for prediction of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Eur Radiol 29:1211–1220
Nie K, Shi L, Chen Q et al (2016) Rectal cancer: assessment of neoadjuvant chemoradiation outcome based on radiomics of multiparametric MRI. Clin Cancer Res 22:5256–5264
Yi X, Pei Q, Zhang Y et al (2019) MRI-based radiomics predicts tumor response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Front Oncol 9:552
Petresc B, Lebovici A, Caraiani C, Feier D, Graur F, Buruian M (2020) Pre-treatment T2-WI based radiomics features for prediction of locally advanced rectal cancer non-response to neoadjuvant chemoradiotherapy: a preliminary study. Cancers (Basel) 12:1894
Liu Z, Zhang XY, Shi YJ et al (2017) Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer. Clin Cancer Res 23:7253–7262
Ho SY, Phua K, Wong L, Bin Goh WW (2020) Extensions of the external validation for checking learned model interpretability and generalizability. Patterns (N Y) 1:100129
Orlhac F, Lecler A, Savatovski J et al (2021) How can we combat multicenter variability in MR radiomics? Validation of a correction procedure. Eur Radiol 31:2272–2280
Da-Ano R, Visvikis D, Hatt M (2020) Harmonization strategies for multicenter radiomics investigations. Phys Med Biol 65:24tr02
Kociołek M, Strzelecki M, Obuchowicz R (2020) Does image normalization and intensity resolution impact texture classification? Comput Med Imaging Graph 81:101716
Kotsiantis S, Zaharakis I, Pintelas P (2006) Machine learning: a review of classification and combining techniques. Artif Intell Rev 26:159–190
Shaish H, Aukerman A, Vanguri R et al (2020) Radiomics of MRI for pretreatment prediction of pathologic complete response, tumor regression grade, and neoadjuvant rectal score in patients with locally advanced rectal cancer undergoing neoadjuvant chemoradiation: an international multicenter study. Eur Radiol 30:6263–6273
van Griethuysen JJM, Lambregts DMJ, Trebeschi S et al (2020) Radiomics performs comparable to morphologic assessment by expert radiologists for prediction of response to neoadjuvant chemoradiotherapy on baseline staging MRI in rectal cancer. Abdom Radiol (NY) 45:632–643
Deist TM, Dankers F, Valdes G et al (2018) Machine learning algorithms for outcome prediction in (chemo)radiotherapy: an empirical comparison of classifiers. Med Phys 45:3449–3459
Nyúl LG, Udupa JK, Zhang X (2000) New variants of a method of MRI scale standardization. IEEE Trans Med Imaging 19:143–150
Zhang X, Zhong L, Zhang B et al (2019) The effects of volume of interest delineation on MRI-based radiomics analysis: evaluation with two disease groups. Cancer Imaging 19:89
Johnson WE, Li C, Rabinovic A (2007) Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics 8:118–127
Shi L, Zhang Y, Nie K et al (2019) Machine learning for prediction of chemoradiation therapy response in rectal cancer using pre-treatment and mid-radiation multi-parametric MRI. Magn Reson Imaging 61:33–40
Antunes JT, Ofshteyn A, Bera K et al (2020) Radiomic features of primary rectal cancers on baseline T2-weighted MRI are associated with pathologic complete response to neoadjuvant chemoradiation: a multisite study. J Magn Reson Imaging 52:1531–1541
Bulens P, Couwenberg A, Intven M et al (2020) Predicting the tumor response to chemoradiotherapy for rectal cancer: model development and external validation using MRI radiomics. Radiother Oncol 142:246–252
Buch K, Kuno H, Qureshi MM, Li B, Sakai O (2018) Quantitative variations in texture analysis features dependent on MRI scanning parameters: a phantom model. J Appl Clin Med Phys 19:253–264
Ford J, Dogan N, Young L, Yang F (2018) Quantitative radiomics: impact of pulse sequence parameter selection on MRI-based textural features of the brain. Contrast Media Mol Imaging:2018:1729071
Guillemaud R, Brady M (1997) Estimating the bias field of MR images. IEEE Trans Med Imaging 16:238–251
Khatami A, Khosravi A, Nguyen T, Lim CP, Nahavandi S (2017) Medical image analysis using wavelet transform and deep belief networks. Exp Syst Appl 86:190–198
Li L, Mao F, Qian W, Clarke LP (1997) Wavelet transform for directional feature extraction in medical imaging. Proceedings of international conference on image processing. IEEE, pp 500-503
Kuo L-J, Liu M-C, Jian JJ-M et al (2007) Is final TNM staging a predictor for survival in locally advanced rectal cancer after preoperative chemoradiation therapy? Ann Surg Oncol 14:2766–2772
Wallin U, Rothenberger D, Lowry A, Luepker R, Mellgren A (2013) CEA–a predictor for pathologic complete response after neoadjuvant therapy for rectal cancer. Dis Colon Rectum 56:859–868
Huang C-M, Huang C-W, Ma C-J et al (2020) Predictive value of FOLFOX-based regimen, long interval, hemoglobin levels and clinical negative nodal status, and postchemoradiotherapy CEA levels for pathological complete response in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy. J Oncol 2020:9437684
Gambacorta MA, Masciocchi C, Chiloiro G et al (2021) Timing to achieve the highest rate of pCR after preoperative radiochemotherapy in rectal cancer: a pooled analysis of 3085 patients from 7 randomized trials. Radiother Oncol 154:154–160
Allegra CJ, Yothers G, O’Connell MJ et al (2015) Neoadjuvant 5-FU or capecitabine plus radiation with or without oxaliplatin in rectal cancer patients: a phase III randomized clinical trial. J Natl Cancer Inst 107:djv248
Huang C-M, Huang M-Y, Huang C-W et al (2020) Machine learning for predicting pathological complete response in patients with locally advanced rectal cancer after neoadjuvant chemoradiotherapy. Sci Rep 10:1–10
Ali J, Khan R, Ahmad N, Maqsood I (2012) Random forests and decision trees. Int J Comput Sci Issues (IJCSI) 9:272
Guo L, Ma Y, Cukic B, Singh H (2004) Robust prediction of fault-proneness by random forests. 15th international symposium on software reliability engineering. IEEE, pp 417-428
Razzak MI, Naz S, Zaib A (2018) Deep learning for medical image processing: overview, challenges and the future. In: Dey N, Ashour AS, Borra S, (eds) Classification in BioApps: automation of decision making. Springer International Publishing, Cham, pp 323–350
Funding
This study has received funding from the Youth Talent Project of The Second Affiliated Hospital of Guangzhou University of Chinese Medicine (Grant Number ZY2022YL05).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Xian Liu Ph.D., M.D., and Wei Yang Ph.D., M.D.
Conflict of interest
One of the authors (Kan Deng) is an employee of Philips Healthineers. The remaining authors declare no relationships with any companies whose products or services may be related to the subject matter of the article.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Informed consent
Written informed consent was not required for this study because of the retrospective nature of the study.
Ethical approval
Institutional review board approval was obtained.
Methodology
• retrospective
• diagnostic or prognostic study
• performed at two institutions
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wei, Q., Chen, Z., Tang, Y. et al. External validation and comparison of MR-based radiomics models for predicting pathological complete response in locally advanced rectal cancer: a two-centre, multi-vendor study. Eur Radiol 33, 1906–1917 (2023). https://doi.org/10.1007/s00330-022-09204-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-022-09204-5