Radiomics performs comparable to morphologic assessment by expert radiologists for prediction of response to neoadjuvant chemoradiotherapy on baseline staging MRI in rectal cancer
- 99 Downloads
To compare the performance of advanced radiomics analysis to morphological assessment by expert radiologists to predict a good or complete response to chemoradiotherapy in rectal cancer using baseline staging MRI.
Materials and methods
We retrospectively assessed the primary staging MRIs [prior to chemoradiotherapy (CRT)] of 133 rectal cancer patients from 2 centers. First, two expert radiologists subjectively estimated the likelihood of achieving a “complete response” (ypT0) and “good response” (TRG 1–2), using a 5-point score (based on TN-stage, MRF/EMVI-status, size/signal/shape). Next, tumor volumes were segmented on high b value DWI (semi-automated, corrected by 2 non-expert and 2-expert readers, resulting in 5 segmentations), copied to the remaining sequences after which a total of 2505 radiomic features were extracted from T2W, low and high b value DWI and ADC. Stability of features for noise due to inter-reader and inter-scanner and protocol variations was assessed using intraclass correlation (ICC) and the Kruskal–Wallis test. Using data from center 1 (n = 86; training set), top 9 features were selected using minimum Redundancy Maximum Relevance and combined in a logistic regression model. Finally, diagnostic performance of the fitted models was assessed on data from center 2 (n = 47; validation set) and compared to the performance of the radiologists.
The Radiomic models resulted in AUCs of 0.69–0.79 (with similar results for the segmentations performed by expert/non-expert readers) to predict response, results similar to the morphologic prediction by the expert radiologists (AUC 0.67–0.83). Radiomics using semi-automatically generated segmentations (without manual input) did not result in significant predictive performance.
Radiomics could predict response to therapy with comparable diagnostic performance as expert radiologists, regardless of whether image segmentation was performed by non-expert or expert readers, indicating that expert input is not required in order for the radiomics workflow to produce significant predictive performance.
KeywordsRectal cancer Magnetic resonance imaging Response prediction Radiomics Texture analysis
This work was supported by the Dutch Cancer Society (KWF) (Grant No. 2016-2/10611).
Compliance with ethical standards
Conflict of interest
Dr. Aerts declares stock options in Sphera and Genospace, all other authors declare no conflict of interest.
- 3.van der Valk MJM, Hilling DE, Bastiaannet E, Meershoek-Klein Kranenbarg E, Beets GL, Figueiredo NL, 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 391:2537–45. https://doi.org/10.1016/s0140-6736(18)31078-x.CrossRefGoogle Scholar
- 4.Verseveld M, De Graaf EJR, Verhoef C, van Meerten E, Punt CJA, de Hingh IHJT, et al. (2015) Chemoradiation therapy for rectal cancer in the distal rectum followed by organ-sparing transanal endoscopic microsurgery (CARTS study). Br J Surg 102:853–60. https://doi.org/10.1002/bjs.9809.CrossRefGoogle Scholar
- 5.Bujko K, Richter P, Smith FM, Polkowski W, Szczepkowski M, Rutkowski A, et al. (2013) Preoperative radiotherapy and local excision of rectal cancer with immediate radical re-operation for poor responders: a prospective multicentre study. Radiother Oncol 106:198–205. https://doi.org/10.1016/j.radonc.2012.12.005.CrossRefGoogle Scholar
- 6.Rombouts AJM, Al-Najami I, Abbott NL, Appelt A, Baatrup G, Bach S, et al. (2017) Can we Save the rectum by watchful waiting or T rans A nal microsurgery following (chemo) R adiotherapy versus T otal mesorectal excision for early RE ctal C ancer (STAR-TREC study)?: protocol for a multicentre, randomised feasibility study. BMJ Open 7:e019474. https://doi.org/10.1136/bmjopen-2017-019474.CrossRefGoogle Scholar
- 8.Curvo-Semedo L, Lambregts DMJ, Maas M, Thywissen T, Mehsen RT, Lammering G, et al. (2011) Rectal Cancer: Assessment of Complete Response to Preoperative Combined Radiation Therapy with Chemotherapy—Conventional MR Volumetry versus Diffusion-weighted MR Imaging. Radiology 260:734–43. https://doi.org/10.1148/radiol.11102467.CrossRefGoogle Scholar
- 9.Lambregts DM, Rao SX, Sassen S, Martens MH, Heijnen LA, Buijsen J, et al. (2015) MRI and Diffusion-weighted MRI Volumetry for Identification of Complete Tumor Responders After Preoperative Chemoradiotherapy in Patients With Rectal Cancer: A Bi-institutional Validation Study. Ann Surg 262:1034–9. https://doi.org/10.1097/sla.0000000000000909.CrossRefGoogle Scholar
- 11.Hötker AM, Tarlinton L, Mazaheri Y, Woo KM, Gönen M, Saltz LB, et al. (2016) Multiparametric MRI in the assessment of response of rectal cancer to neoadjuvant chemoradiotherapy: A comparison of morphological, volumetric and functional MRI parameters. Eur Radiol:1–10. https://doi.org/10.1007/s00330-016-4283-9.CrossRefGoogle Scholar
- 17.Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, et al. (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006. https://doi.org/10.1038/ncomms5006.
- 18.Liu Z, Zhang X-Y, Shi Y-J, Wang L, Zhu H-T, Tang Z-C, et al. (2017) Radiomics Analysis for Evaluation of Pathological Complete Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer. Clin Cancer Res:clincanres.1038.2017. https://doi.org/10.1158/1078-0432.ccr-17-1038.CrossRefGoogle Scholar
- 19.Cui Y, Yang X, Shi Z, Yang Z, Du X, Zhao 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 29:1211–20. https://doi.org/10.1007/s00330-018-5683-9.CrossRefGoogle Scholar
- 20.Cusumano D, Dinapoli N, Luca Boldrini ·, Chiloiro G, Gatta · Roberto, Masciocchi C, et al. (2018) Fractal-based radiomic approach to predict complete pathological response after chemo-radiotherapy in rectal cancer. Radiol Med 123:286–95. https://doi.org/10.1007/s11547-017-0838-3.CrossRefGoogle Scholar
- 22.van Heeswijk MM, Lambregts DMJ, van Griethuysen JJM, Oei S, Rao S-X, de Graaff CAM, et al. (2016) Automated and Semiautomated Segmentation of Rectal Tumor Volumes on Diffusion-Weighted MRI: Can It Replace Manual Volumetry? Int J Radiat Oncol 94:824–31. https://doi.org/10.1016/j.ijrobp.2015.12.017.CrossRefGoogle Scholar
- 24.Shamonin DP, Bron EE, Lelieveldt BPF, Smits M, Klein S, Staring M, et al. (2014) Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer’s disease for the Alzheimer’s Disease Neuroimaging Initiative. https://doi.org/10.3389/fninf.2013.00050.
- 27.Pedregosa FABIANPEDREGOSA F, Michel V, Grisel OLIVIERGRISEL O, Blondel M, Prettenhofer P, Weiss R, et al. (2011). Scikit-learn: Machine Learning in Python. vol. 12.Google Scholar
- 33.Huang Y -q., Liang C -s. C -h., He L, Tian J, Liang C -s. C -h., Chen X, et al. (2016) Development and Validation of a Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Colorectal Cancer SUPPLEMENT. J Clin Oncol:JCO659128. https://doi.org/10.1200/jco.2015.65.9128.CrossRefGoogle Scholar
- 35.Maas M, Lambregts DM, Nelemans PJ, Heijnen LA, Martens MH, Leijtens JW, et al. (2015) Assessment of Clinical Complete Response After Chemoradiation for Rectal Cancer with Digital Rectal Examination, Endoscopy, and MRI: Selection for Organ-Saving Treatment. Ann Surg Oncol 22:3873–80. https://doi.org/10.1245/s10434-015-4687-9.CrossRefGoogle Scholar