A multiparameter MRI-radiomics and clinical nomogram to predict the positive circumferential resection margin of rectal carcinoma
Tóm tắt
To construct a predictive nomogram combining multi-parameter MRI-based radiomics and clinical information to evaluate the circumferential resection margin (CRM) of rectal carcinoma (RC). This single-center study retrospectively recruited 301 RC patients including 66 patients with positive CRM status (CRM +) and 235 patients with negative CRM status (CRM−). Patients were randomly divided into training set and testing set with a proportionate of 7:3. The multi-parameter MRI-radiomics features were calculated after tumor segmentation. After feature selection, the logistic models of T1WI (LM-T1WI), T2WI (LM-T2WI), DWI (LM-DWI), T1CE (LM-T1CE), and entire MRI examination (LM-MRI) were constructed in the training set and validated in the testing set. The predictive performance of these models was assessed according to the area under curve (AUCs). Moreover, an integrative nomogram containing MRI-radiomics and clinical information was developed to evaluate the CRM status of RC. The single sequence MRI-based radiomics analysis of LM-T1WI, T2WI, DWI, and T1CE showed similar AUCs in both the training (0.743–0.827) and testing set (0.779–0.808). While, the LM-MRI incorporated four sequences achieved a higher AUCs of 0.885 (95% CI, 0.834–0.925) in the training set and 0.855 (95% CI, 0.766–0.920) in the testing set. The MRI-radiomics and clinical nomogram combined MRI-radiomics and significant clinical characteristics of CEA, CA19-9, and CK19 accomplished a better performance in predicting the CRM status of RC with AUCs of 0.901 (95% CI 0.859–0.936). MRI-radiomics analysis helped to predict the CRM status of RC. And the combined MRI-radiomics and clinical nomogram achieved a better performance in prediction.
Tài liệu tham khảo
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. CA Cancer J Clin. 2021;71(3):209–49.
Videhult P, Smedh K, Lundin P, Kraaz W. Magnetic resonance imaging for preoperative staging of rectal cancer in clinical practice: high accuracy in predicting circumferential margin with clinical benefit. Colorectal Dis. 2007;9(5):412–9.
Agger E, Jörgren F, Lydrup ML, Buchwald P (2021) Circumferential resection margin is associated with distant metastasis after rectal cancer surgery: a nation-wide population-based study cohort. Ann Surg. 2023;277(2):e346–52.
Kelly SB, Mills SJ, Bradburn DM, Ratcliffe AA, Borowski DW. Effect of the circumferential resection margin on survival following rectal cancer surgery. Br J Surg. 2011;98(4):573–81.
Simpson GS, Eardley N, McNicol F, Healey P, Hughes M, Rooney PS. Circumferential resection margin (CRM) positivity after MRI assessment and adjuvant treatment in 189 patients undergoing rectal cancer resection. Int J Colorectal Dis. 2014;29(5):585–90.
Furey E, Jhaveri KS. Magnetic resonance imaging in rectal cancer. Magn Reson Imaging Clin N Am. 2014;22(2):165–90.
Iannicelli E, Di Renzo S, Ferri M, et al. Accuracy of high-resolution MRI with lumen distention in rectal cancer staging and circumferential margin involvement prediction. Korean J Radiol. 2014;15(1):37–44.
Dahlbäck C, Korsbakke K, Alshibiby Bergman T, Zaki J, Zackrisson S, Buchwald P. Accuracy of magnetic resonance imaging staging of tumour and nodal stage in rectal cancer treated by primary surgery: a population-based study. Colorectal Dis. 2022;24(9):1047–53.
Ma YQ, Wen Y, Liang H, Zhong JG, Pang PP. Magnetic resonance imaging-radiomics evaluation of response to chemotherapy for synchronous liver metastasis of colorectal cancer. World J Gastroenterol. 2021;27(38):6465–75.
Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures. They Are Data Radiol. 2016;278(2):563–77.
Jalil O, Afaq A, Ganeshan B, et al. Magnetic resonance based texture parameters as potential imaging biomarkers for predicting long-term survival in locally advanced rectal cancer treated by chemoradiotherapy. Colorectal Dis. 2017;19(4):349–62.
Al-Sukhni E, Attwood K, Gabriel E, Nurkin SJ. Predictors of circumferential resection margin involvement in surgically resected rectal cancer: a retrospective review of 23,464 patients in the US National Cancer Database. Int J Surg (London, England). 2016;28:112–7.
Liu Q, Luo D, Cai S, Li Q, Li X. Circumferential resection margin as a prognostic factor after rectal cancer surgery: A large population-based retrospective study. Cancer Med. 2018;7(8):3673–81.
Nozoe T, Rikimaru T, Mori E, Okuyama T, Takahashi I. Increase in both CEA and CA19-9 in sera is an independent prognostic indicator in colorectal carcinoma. J Surg Oncol. 2006;94(2):132–7.
Kim CG, Ahn JB, Jung M, et al. Preoperative serum carcinoembryonic antigen level as a prognostic factor for recurrence and survival after curative resection followed by adjuvant chemotherapy in stage III colon cancer. Ann Surg Oncol. 2017;24(1):227–35.
Uen YH, Lin SR, Wu DC, et al. Prognostic significance of multiple molecular markers for patients with stage II colorectal cancer undergoing curative resection. Ann Surg. 2007;246(6):1040–6.
Kim SH, Lee JM, Park HS, Eun HW, Han JK, Choi BI. Accuracy of MRI for predicting the circumferential resection margin, mesorectal fascia invasion, and tumor response to neoadjuvant chemoradiotherapy for locally advanced rectal cancer. J Magn Reson Imaging. 2009;29(5):1093–101.
Ma X, Li X, Xu L, et al. Characteristics and prognostic significance of preoperative magnetic resonance imaging-assessed circumferential margin in rectal cancer. Gastroenterol Res Pract. 2015;2015:410150.
Bond S, Joshi N, Petroudi S, Brady M. Estimating the mesorectal fascia in MRI. Inf Proc Med Imaging. 2007;20:650–61.
Stanzione A, Verde F, Romeo V, Boccadifuoco F, Mainenti PP, Maurea S. Radiomics and machine learning applications in rectal cancer: current update and future perspectives. World J Gastroenterol. 2021;27(32):5306–21.