Share this content in WeChat
Clinical Article
MRI radiomics models in rectal cancer to predict pathological complete response of nCRT: Evaluation of different approaches
QIN Siyuan  LU Siyi  WANG Qizheng  ZHANG Enlong  WANG Yuxia  PENG Ran  WANG Hao  LANG Ning 

Cite this article as: Qin SY, Lu SY, Wang QZ, et al. MRI radiomics models in rectal cancer to predict pathological complete response of nCRT: Evaluation of different approaches[J]. Chin J Magn Reson Imaging, 2022, 13(11): 82-87, 114. DOI:10.12015/issn.1674-8034.2022.11.015.

[Abstract] Objective To explore the value of different pre-treatment MRI radiomics models in predicting the pathological complete response (pCR) of neoadjuvant chemoradiotherapy (nCRT) for locally advanced rectal cancer (LARC).Materials and Methods Seventy-six cases of patients diagnosed with LARC who underwent radical resection after nCRT in Peking University Third Hospital from January 2013 to December 2020 were retrospectively collected. According to the postoperative pathological results, they were divided into pCR group (n=38) and non-pCR group (n=38). The volume of interest (VOI) of lesion, rectal segment and of mesangial fat were segmented based on pre-treatment high-resolution T2WI sequence, and the radiomics features were extracted and screened. Classifiers including logistics regression (LR), quadratic discriminant analysis (QDA), support vector machine (SVM) were used to establish the radiomics models of lesions, rectal segments, mesangial fat, combine1 (lesions+mesangial fat), combine2 (rectal segments+mesangial fat), were used to evaluate the performance of different models and select the best model by using the receiver operating characteristic (ROC) curve. The 5-fold cross-validation was used for model testing, training, and selection.Results There were 6, 7, 7, 8, and 7 features used to establish the models of lesion, rectal segment, mesangial fat, combine1, and combine2, respectively. Among the 15 models, LR model based on lesion+mesangial fat features had the best performance. Its area under the curve (AUC), F1 score, sensitivity, specificity, accuracy and 95% confidence interval (CI) of the above indicators were 0.857 (0.647-1.000), 81.2% (59.5%-96.0%), 78.2% (36.7%-95.5%), 86.4% (47.0%-98.7%) and 82.3% (66.3%-95.7%), respectively.Conclusions Different pre-treatment MRI radiomics models can predict pCR after nCRT in LARC patients noninvasively, and the LR model based on lesion+mesangial fat featuresperforms the best.
[Keywords] locally advanced rectal cancer;magnetic resonance imaging;radiomics;neoadjuvant chemoradiotherapy;pathological complete response

QIN Siyuan1   LU Siyi2   WANG Qizheng1   ZHANG Enlong3   WANG Yuxia4   PENG Ran4   WANG Hao4   LANG Ning1*  

1 Department of Radiology, Peking University Third Hospital, Beijing 100191, China

2 Department of General Surgery, Peking University Third Hospital, Beijing 100191, China

3 Department of Radiology, Peking University International Hospital, Beijing 102206, China

4 Department of Radiotherapy, Cancer Center, Peking University Third Hospital, Beijing 100191, China

Lang N, E-mail:

Conflicts of interest   None.

Received  2022-07-06
Accepted  2022-11-07
DOI: 10.12015/issn.1674-8034.2022.11.015
Cite this article as: Qin SY, Lu SY, Wang QZ, et al. MRI radiomics models in rectal cancer to predict pathological complete response of nCRT: Evaluation of different approaches[J]. Chin J Magn Reson Imaging, 2022, 13(11): 82-87, 114.DOI:10.12015/issn.1674-8034.2022.11.015

Sung H, 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 Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.
Siegel RL, Miller KD, Fedewa SA, et al. Colorectal cancer statistics, 2017[J]. CA A Cancer J Clin, 2017, 67(3): 177-193. DOI: 10.3322/caac.21395.
Sauer R, Becker H, Hohenberger W, et al. Preoperative versus postoperative chemoradiotherapy for rectal cancer[J]. N Engl J Med, 2004, 351(17): 1731-1740. DOI: 10.1056/NEJMoa040694.
Zhang X, Ding R, Li JS, et al. Efficacy and safety of the "watch-and-wait" approach for rectal cancer with clinical complete response after neoadjuvant chemoradiotherapy: a meta-analysis[J]. Surg Endosc, 2022, 36(4): 2233-2244. DOI: 10.1007/s00464-021-08932-x.
Maas M, Nelemans PJ, Valentini V, et al. Long-term outcome in patients with a pathological complete response after chemoradiation for rectal cancer: a pooled analysis of individual patient data[J]. Lancet Oncol, 2010, 11(9): 835-844. DOI: 10.1016/S1470-2045(10)70172-8.
Polanco PM, Mokdad AA, Zhu H, et al. Association of adjuvant chemotherapy with overall survival in patients with rectal cancer and pathologic complete response following neoadjuvant chemotherapy and resection[J]. JAMA Oncol, 2018, 4(7): 938-943. DOI: 10.1001/jamaoncol.2018.0231.
Smith JJ, Strombom P, Chow OS, et al. Assessment of a Watch-and-Wait Strategy for Rectal Cancer in Patients With a Complete Response After Neoadjuvant Therapy[J/OL]. JAMA Oncol, 2019, 5(4): e185896 [2022-07-05]. DOI: 10.1001/jamaoncol.2018.5896.
Kachnic LA, Glynne-Jones R. Accomplishments in 2007 in the adjuvant treatment of rectal cancer[J]. Gastrointest Cancer Res, 2008, 2(3Suppl): S7-S12.
Gambacorta MA, Masciocchi C, Chiloiro G, et al. Timing to achieve the highest rate of pCR after preoperative radiochemotherapy in rectal cancer: a pooled analysis of 3085 patients from 7 randomized trials[J]. Radiother Oncol, 2021, 154: 154-160. DOI: 10.1016/j.radonc.2020.09.026.
Lambin P, Leijenaar R, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine[J]. Nat Rev Clin Oncol, 2017, 14(12): 749-762. DOI: 10.1038/nrclinonc.2017.141.
Zhou YR, Wu D, Yan S, et al. Feasibility of a clinical-radiomics model to predict the outcomes of acute ischemic stroke[J]. Korean J Radiol, 2022, 23(8): 811-820. DOI: 10.3348/kjr.2022.0160.
Chen QY, Zhang L, Liu SY, et al. Radiomics in precision medicine for gastric cancer: opportunities and challenges[J]. Eur Radiol, 2022, 32(9): 5852-5868. DOI: 10.1007/s00330-022-08704-8.
Zhang SY, Yu MR, Chen D, et al. Role of MRI-based radiomics in locally advanced rectal cancer (Review)[J/OL]. Oncol Rep, 2022, 47(2): 34 [2022-07-05]. DOI: 10.3892/or.2021.8245.
Caulo M, Panara V, Tortora D, et al. Data-driven grading of brain gliomas: a multiparametric MR imaging study[J]. Radiology, 2014, 272(2): 494-503. DOI: 10.1148/radiol.14132040.
Akinci D'Antonoli T, Farchione A, Lenkowicz J, et al. CT radiomics signature of tumor and peritumoral lung parenchyma to predict nonsmall cell lung cancer postsurgical recurrence risk[J]. Acad Radiol, 2020, 27(4): 497-507. DOI: 10.1016/j.acra.2019.05.019.
Trakarnsanga A, Gonen M, Shia J, et al. Comparison of tumor regression grade systems for locally advanced rectal cancer after multimodality treatment[J/OL]. J Natl Cancer Inst, 2014, 106(10): dju248 [2022-07-05]. DOI: 10.1093/jnci/dju248.
Li YL, Xu Y, Guo W, et al. Research progress in clinical predictors of pathological complete response in locally advanced rectal cancer after neoadjuvant radiochemotherapy[J]. Int J Surg, 2020, 47(8): 563-566. DOI: 10.3760/
Simson DK, Mitra S, Ahlawat P, et al. Prospective study of neoadjuvant chemoradiotherapy using intensity-modulated radiotherapy and 5 fluorouracil for locally advanced rectal cancer - toxicities and response assessment[J]. Cancer Manag Res, 2018, 10: 519-526. DOI: 10.2147/CMAR.S142076.
Liu WX, Li YQ, Zhu H, et al. The relationship between primary gross tumor volume and tumor response of locally advanced rectal cancer: pGTV as a more accurate tumor size indicator[J]. J Invest Surg, 2021, 34(2): 181-190. DOI: 10.1080/08941939.2019.1615153.
Liu M, Feng Y, Zhang Y, et al. Evaluation of Neutrophil-Lymphocyte Ratio and Platelet-Lymphocyte Ratio on Predicting Responsiveness to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer Patients[J/OL]. Biomed Res Int, 2022, 2022: 3839670 [2022-07-05]. DOI: 10.1155/2022/3839670.
Shin J, Seo N, Baek SE, et al. MRI radiomics model predicts pathologic complete response of rectal cancer following chemoradiotherapy[J]. Radiology, 2022, 303(2): 351-358. DOI: 10.1148/radiol.211986.
Nie K, Shi LM, Chen Q, et al. Rectal cancer: assessment of neoadjuvant chemoradiation outcome based on radiomics of multiparametric MRI[J]. Clin Cancer Res, 2016, 22(21): 5256-5264. DOI: 10.1158/1078-0432.CCR-15-2997.
Braman NM, Etesami M, Prasanna P, et al. Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI[J]. Breast Cancer Res, 2017, 19(1): 57. DOI: 10.1186/s13058-017-0846-1.
Jayaprakasam VS, Paroder V, Gibbs P, et al. MRI radiomics features of mesorectal fat can predict response to neoadjuvant chemoradiation therapy and tumor recurrence in patients with locally advanced rectal cancer[J]. Eur Radiol, 2022, 32(2): 971-980. DOI: 10.1007/s00330-021-08144-w.
Chen BY, Xie H, Li Y, et al. MRI-Based Radiomics Features to Predict Treatment Response to Neoadjuvant Chemotherapy in Locally Advanced Rectal Cancer: A Single Center, Prospective Study[J/OL]. Front Oncol, 2022, 12: 801743 [2022-07-05]. DOI: 10.3389/fonc.2022.801743.
Wang TT, She YL, Yang Y, et al. Radiomics for survival risk stratification of clinical and pathologic stage IA pure-solid non-small cell lung cancer[J]. Radiology, 2022, 302(2): 425-434. DOI: 10.1148/radiol.2021210109.
Neto NIP, Murari ASP, Oyama LM, et al. Peritumoural adipose tissue pro-inflammatory cytokines are associated with tumoural growth factors in cancer cachexia patients[J]. J Cachexia Sarcopenia Muscle, 2018, 9(6): 1101-1108. DOI: 10.1002/jcsm.12345.
Cao YH. Adipocyte and lipid metabolism in cancer drug resistance[J]. J Clin Invest, 2019, 129(8): 3006-3017. DOI: 10.1172/JCI127201.
Delli Pizzi A, Chiarelli AM, Chiacchiaretta P, et al. MRI-based clinical-radiomics model predicts tumor response before treatment in locally advanced rectal cancer[J/OL]. Sci Rep, 2021, 11(1): 5379 [2022-07-05]. DOI: 10.1038/s41598-021-84816-3.
Zhu C, Yu YM, Wang SH, et al. A novel clinical radiomics nomogram to identify Crohn's disease from intestinal tuberculosis[J]. J Inflamm Res, 2021, 14: 6511-6521. DOI: 10.2147/JIR.S344563.
Wang J, Chen JJ, Zhou RZ, et al. Machine learning-based multiparametric MRI radiomics for predicting poor responders after neoadjuvant chemoradiotherapy in rectal Cancer patients[J/OL]. BMC Cancer, 2022, 22(1): 420 [2022-07-05]. DOI: 10.1186/s12885-022-09518-z.

PREV Radiomics prediction model for the improved diagnosis of clinically significant prostate cancer on biparametric MRI
NEXT Evaluation of magnetic resonance DWI-ADC value in assessing the early efficacy of neoadjuvant chemotherapy for conventional osteosarcoma

Tel & Fax: +8610-67113815    E-mail: