Deep Learning and Radiomics predict complete response after neo-adjuvant chemoradiation for locally advanced rectal cancer

Jean-Emmanuel Bibault, Philippe Giraud, Martin Housset, Catherine Durdux, Julien Taieb, Anne Berger, Romain Coriat, Stanislas Chaussade, Bertrand Dousset, Bernard Nordlinger, Anita Burgun, Jean-Emmanuel Bibault, Philippe Giraud, Martin Housset, Catherine Durdux, Julien Taieb, Anne Berger, Romain Coriat, Stanislas Chaussade, Bertrand Dousset, Bernard Nordlinger, Anita Burgun

Abstract

Treatment of locally advanced rectal cancer involves chemoradiation, followed by total mesorectum excision. Complete response after chemoradiation is an accurate surrogate for long-term local control. Predicting complete response from pre-treatment features could represent a major step towards conservative treatment. Patients with a T2-4 N0-1 rectal adenocarcinoma treated between June 2010 and October 2016 with neo-adjuvant chemoradiation from three academic institutions were included. All clinical and treatment data was integrated in our clinical data warehouse, from which we extracted the features. Radiomics features were extracted from the tumor volume from the treatment planning CT Scan. A Deep Neural Network (DNN) was created to predict complete response, as a methodological proof-of-principle. The results were compared to a baseline Linear Regression model using only the TNM stage as a predictor and a second model created with Support Vector Machine on the same features used in the DNN. Ninety-five patients were included in the final analysis. There were 49 males (52%) and 46 females (48%). Median tumour size was 48 mm (15-130). Twenty-two patients (23%) had pathologic complete response after chemoradiation. One thousand six hundred eighty-three radiomics features were extracted. The DNN predicted complete response with an 80% accuracy, which was better than the Linear Regression model (69.5%) and the SVM model (71.58%). Our model correctly predicted complete response after neo-adjuvant rectal chemoradiotherapy in 80% of the patients of this multicenter cohort. Our results may help to identify patients who would benefit from a conservative treatment, rather than a radical resection.

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Heatmap of radiomics features correlated to complete response.
Figure 2
Figure 2
Kaplan-Meier curves for overall survival stratified on pathological complete response.
Figure 3
Figure 3
Global analysis pipeline.

References

    1. National Comprehensive Cancer Network. NCCN Clinical Practice Guidelines in Oncology. Available at: . (Accessed: 27th November 2017)
    1. Maas M, et al. Long-term outcome in patients with a pathological complete response after chemoradiation for rectal cancer: a pooled analysis of individual patient data. Lancet Oncol. 2010;11:835–844. doi: 10.1016/S1470-2045(10)70172-8.
    1. Habr-Gama, A. et al. Operative versus nonoperative treatment for stage 0 distal rectal cancer following chemoradiation therapy: long-term results. Ann. Surg. 240, 711–717; discussion 717–718 (2004).
    1. Bhangu, A. et al. Survival outcome of local excision versus radical resection of colon or rectal carcinoma: a Surveillance, Epidemiology, and End Results (SEER) population-based study. Ann. Surg. 258, 563–569; discussion 569–571 (2013).
    1. Habr-Gama A, et al. Local recurrence after complete clinical response and watch and wait in rectal cancer after neoadjuvant chemoradiation: impact of salvage therapy on local disease control. Int. J. Radiat. Oncol. Biol. Phys. 2014;88:822–828. doi: 10.1016/j.ijrobp.2013.12.012.
    1. Appelt AL, et al. High-dose chemoradiotherapy and watchful waiting for distal rectal cancer: a prospective observational study. Lancet Oncol. 2015;16:919–927. doi: 10.1016/S1470-2045(15)00120-5.
    1. Renehan AG, et al. Watch-and-wait approach versus surgical resection after chemoradiotherapy for patients with rectal cancer (the OnCoRe project): a propensity-score matched cohort analysis. Lancet Oncol. 2016;17:174–183. doi: 10.1016/S1470-2045(15)00467-2.
    1. Martens, M. H. et al. Long-term Outcome of an Organ Preservation Program After Neoadjuvant Treatment for Rectal Cancer. J. Natl. Cancer Inst. 108 (2016).
    1. Aerts HJWL. The Potential of Radiomic-Based Phenotyping in Precision Medicine: A Review. JAMA Oncol. 2016;2:1636–1642. doi: 10.1001/jamaoncol.2016.2631.
    1. Nie K, et al. Rectal Cancer: Assessment of Neoadjuvant Chemoradiation Outcome based on Radiomics of Multiparametric MRI. Clin. Cancer Res. Off. J. Am. Assoc. Cancer Res. 2016;22:5256–5264. doi: 10.1158/1078-0432.CCR-15-2997.
    1. Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI. Machine learning applications in cancer prognosis and prediction. Comput. Struct. Biotechnol. J. 2015;13:8–17. doi: 10.1016/j.csbj.2014.11.005.
    1. Kang J, Schwartz R, Flickinger J, Beriwal S. Machine Learning Approaches for Predicting Radiation Therapy Outcomes: A Clinician’s Perspective. Int. J. Radiat. Oncol. Biol. Phys. 2015;93:1127–1135. doi: 10.1016/j.ijrobp.2015.07.2286.
    1. Bibault J-E, Giraud P, Burgun A. Big Data and machine learning in radiation oncology: State of the art and future prospects. Cancer Lett. 2016;382:110–117. doi: 10.1016/j.canlet.2016.05.033.
    1. Machine Learning in Radiation Oncology - Theory and | Issam El Naqa | Springer.
    1. Esteva A, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115–118. doi: 10.1038/nature21056.
    1. Gulshan V, et al. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA. 2016;316:2402–2410. doi: 10.1001/jama.2016.17216.
    1. Miotto R, Li L, Kidd BA, Dudley JT. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records. Sci. Rep. 2016;6:26094. doi: 10.1038/srep26094.
    1. Oakden-Rayner L, et al. Precision Radiology: Predicting longevity using feature engineering and deep learning methods in a radiomics framework. Sci. Rep. 2017;7:1648. doi: 10.1038/s41598-017-01931-w.
    1. Escudié, J.-B. et al. Reviewing 741 patients records in two hours with FASTVISU. AMIA Annu. Symp. Proc. AMIA Symp. 2015, 553–559 (2015).
    1. Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2016;278:563–577. doi: 10.1148/radiol.2015151169.
    1. Lambin P, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat. Rev. Clin. Oncol. 2017;14:749–762. doi: 10.1038/nrclinonc.2017.141.
    1. Gan J, et al. MO-DE-207B-09: A Consistent Test for Radiomics Softwares. Med. Phys. 2016;43:3706. doi: 10.1118/1.4957258.
    1. Zhang L, et al. IBEX: an open infrastructure software platform to facilitate collaborative work in radiomics. Med. Phys. 2015;42:1341–1353. doi: 10.1118/1.4908210.
    1. Bibault, J.-E. Deep Radiomics Rectal Cancer: Code, parameters and scripts used for our study predicting pathologic complete response after neo-adjuvant chemoradiation for locally advanced rectal cancer (2017).
    1. Liu Zhenyu, Zhang Xiao-Yan, Shi Yan-Jie, Wang Lin, Zhu Hai-Tao, Tang Zhenchao, Wang Shuo, Li Xiao-Ting, Tian Jie, Sun Ying-Shi. Radiomics Analysis for Evaluation of Pathological Complete Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer. Clinical Cancer Research. 2017;23(23):7253–7262. doi: 10.1158/1078-0432.CCR-17-1038.
    1. Lovinfosse Pierre, Polus Marc, Van Daele Daniel, Martinive Philippe, Daenen Frédéric, Hatt Mathieu, Visvikis Dimitris, Koopmansch Benjamin, Lambert Frédéric, Coimbra Carla, Seidel Laurence, Albert Adelin, Delvenne Philippe, Hustinx Roland. FDG PET/CT radiomics for predicting the outcome of locally advanced rectal cancer. European Journal of Nuclear Medicine and Molecular Imaging. 2017;45(3):365–375. doi: 10.1007/s00259-017-3855-5.
    1. Kumar V, et al. Radiomics: the process and the challenges. Magn. Reson. Imaging. 2012;30:1234–1248. doi: 10.1016/j.mri.2012.06.010.
    1. Abernethy AP, et al. Rapid-learning system for cancer care. J. Clin. Oncol. Off. J. Am. Soc. Clin. Oncol. 2010;28:4268–4274. doi: 10.1200/JCO.2010.28.5478.
    1. Obermeyer Z, Lee TH. Lost in Thought - The Limits of the Human Mind and the Future of Medicine. N. Engl. J. Med. 2017;377:1209–1211. doi: 10.1056/NEJMp1705348.
    1. Applying machine learning to radiotherapy planning for head & neck cancer. DeepMind Available at: (Accessed: 17th May 2017).
    1. Beam AL, Kohane IS. Translating Artificial Intelligence Into Clinical Care. JAMA. 2016;316:2368–2369. doi: 10.1001/jama.2016.17217.
    1. Cabitza F, Rasoini R, Gensini GF. Unintended Consequences of Machine Learning in Medicine. JAMA. 2017;318:517–518. doi: 10.1001/jama.2017.7797.
    1. Rajpurkar, P. et al. CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning. (2017).
    1. Zapletal E, Rodon N, Grabar N, Degoulet P. Methodology of integration of a clinical data warehouse with a clinical information system: the HEGP case. Stud. Health Technol. Inform. 2010;160:193–197.
    1. Rance B, Canuel V, Countouris H, Laurent-Puig P, Burgun A. Integrating Heterogeneous Biomedical Data for Cancer Research: the CARPEM infrastructure. Appl. Clin. Inform. 2016;7:260–274. doi: 10.4338/ACI-2015-09-RA-0125.
    1. Varian Incorporated. Varian Developers Forum. CodePlex Available at: , (Accessed: 15th April 2017).
    1. Bibault, J.-E. Radiation Oncology Structures Ontology - Summary | NCBO BioPortal. Available at: . (Accessed: 15th April 2017).
    1. Bibault J-E, Zapletal E, Rance B, Giraud P, Burgun A. Labeling for Big Data in radiation oncology: The Radiation Oncology Structures ontology. PloS One. 2018;13:e0191263. doi: 10.1371/journal.pone.0191263.
    1. Bibault Jean-Emmanuel, Giraud Philippe, Burgun Anita, Zapletal Eric. Integrating Multimodal Radiation Therapy Data into i2b2. Applied Clinical Informatics. 2018;09(02):377–390. doi: 10.1055/s-0038-1651497.
    1. Grove O, et al. Quantitative computed tomographic descriptors associate tumor shape complexity and intratumor heterogeneity with prognosis in lung adenocarcinoma. PloS One. 2015;10:e0118261. doi: 10.1371/journal.pone.0118261.
    1. Parmar C, et al. Robust Radiomics feature quantification using semiautomatic volumetric segmentation. PloS One. 2014;9:e102107. doi: 10.1371/journal.pone.0102107.
    1. Shrout PE, Fleiss JL. Intraclass correlations: uses in assessing rater reliability. Psychol. Bull. 1979;86:420–428. doi: 10.1037/0033-2909.86.2.420.
    1. Wolak, M. ICC: Facilitating Estimation of the Intraclass Correlation Coefficient, (2015).
    1. Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJWL. Machine Learning methods for Quantitative Radiomic Biomarkers. Sci. Rep. 2015;5:13087. doi: 10.1038/srep13087.
    1. R Core Team. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. (2013).
    1. Wickham, H. ggplot2: Elegant Graphics for Data Analysis (2009).
    1. Therneau, T. M. & until 2009 T. L. (original S.- >R port and maintainer. survival: Survival Analysis. (2017).
    1. Kassambara, A., Kosinski, M., Biecek, P. & Fabian, S. survminer: Drawing Survival Curves using ‘ggplot2’ (2017).
    1. Martín Abadi et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. (2015).
    1. Nair, V. & Hinton, G. Rectified Linear Units Improve Restricted Boltzmann Machines. Proceedings of the 27th International Conference on Machine Learning (2010).
    1. Duchi J, Hazan E, Singer Y. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization. J. Mach. Learn. Res. 2011;12:2121–2159.
    1. Friedman, J., Hastie, T., Simon, N., Qian, J. & Tibshirani, R. glmnet: Lasso and Elastic-Net Regularized Generalized Linear Models. (2017).
    1. scikit-learn: machine learning in Python — scikit-learn 0.19.1 documentation. Available at: (Accessed: 27th April 2018).
    1. Robin, X. et al. pROC: Display and Analyze ROC Curves. (2018).

Source: PubMed

Patrocinadores e Colaboradores

Condições médicas

Intervenções de drogas

3
Se inscrever