Enhanced prediction of preoperative mesenteric lymph node metastasis in colorectal cancer using machine learning with CT-based data

Abstract

The detection of lymph node (LN) involvement is fundamental for staging colorectal cancer (CRC) and aids in clinical decision-making. Traditionally, determining LN status predominantly relies heavily on histological examination of LN specimens, which can occasionally lead to overtreatment. This study aims to develop a clinical prediction model using machine learning algorithms to assess the risk of mesenteric LN metastasis preoperatively, based on computed tomography images and clinicopathological data from CRC patients. Our findings demonstrate that the predictive model based on XGBoost algorithms exhibited the optimal performance, with area under the curve values consistently stable across training (0.836, 95% confidence interval [CI]: 0.750–0.902) and validation (0.831, 95% CI: 0.688–0.927) cohorts. The model was further elucidated using SHapley Additive Explanation values, which ranked predictors in the XGBoost model by their importance, providing insights into the model&s’s decision-making process. Additionally, the force plot visualizes the contribution of each variable to the prediction for individual samples. The as-obtained model may have the potential to aid in clinical treatment planning, optimize the selection of surgical methods, and guide the decision-making process for adjuvant therapy before surgery.

Keywords

colorectal cancer / computed tomography / machine learning / mesenteric lymph node metastasis

References

[1] BrayF, Laversanne M, SungH, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024;74(3):229-263.

[2] ZhangC, ZhangL, XuT, et al. Mapping the spreading routes of lymphatic metastases in human colorectal cancer. Nat Commun. 2020;11(1):1993.

[3] LangmanG, PatelA, BowleyDM. Size and distribution of lymph nodes in rectal cancer resection specimens. Dis Colon Rectum. 2015;58(4):406-414.

[4] DekkerE, TanisPJ, VleugelsJLA, Kasi PM, WallaceMB. Colorectal cancer. Lancet. 2019;394(10207):1467-1480.

[5] NeradE, LahayeMJ, MaasM, et al. Diagnostic accuracy of CT for local staging of colon cancer: a systematic review and meta-analysis. Am J Roentgenol. 2016;207(5):984-995.

[6] ParkerAL, BowmanE, ZingoneA, et al. Extracellular matrix profiles determine risk and prognosis of the squamous cell carcinoma subtype of non-small cell lung carcinoma. Genome Med. 2022;14(1):126.

[7] GuoSL, SuLN, ZhaiYN, et al. The clinical value of hepatic extracellular volume fraction using routine multiphasic contrast-enhanced liver CT for staging liver fibrosis. Clin Radiol. 2017;72(3):242-246.

[8] GamaF, Rosmini S, BandulaS, et al. Extracellular volume fraction by computed tomography predicts long-term prognosis among patients with cardiac amyloidosis. JACC Cardiovasc Imaging. 2022;15(12):2082-2094.

[9] TagoK, Tsukada J, SudoN, et al. Comparison between CT volumetry and extracellular volume fraction using liver dynamic CT for the predictive ability of liver fibrosis in patients with hepatocellular carcinoma. Eur Radiol. 2022;32(11):7555-7565.

[10] LuoY, LiuL, LiuD, et al. Extracellular volume fraction determined by equilibrium contrast-enhanced CT for the prediction of the pathological complete response to neoadjuvant chemoradiotherapy for locally advanced rectal cancer. Eur Radiol. 2023;33(6):4042-4051.

[11] LiQ, BaoJ, ZhangY, et al. Predictive value of CT-based extracellular volume fraction in the preoperative pathologic grading of rectal adenocarcinoma: a preliminary study. Eur J Radiol. 2023;163:110811.

[12] DangY, DaiL, XuJ, ZhouW, XuY, JiG. tRNA-derived fragments are promising biomarkers for screening of early colorectal cancer. MedComm. 2023;4(3):e227.

[13] MitsalaA, Tsalikidis C, PitiakoudisM, SimopoulosC, Tsaroucha AK. Artificial intelligence in colorectal cancer screening, diagnosis and treatment. A new era. Curr Oncol. 2021;28(3):1581-1607.

[14] OsmanMH, Mohamed RH, SarhanHM, et al. Machine learning model for predicting postoperative survival of patients with colorectal cancer. Cancer Res Treat. 2022;54(2):517-524.

[15] FoerschS, Glasner C, WoerlAC, et al. Multistain deep learning for prediction of prognosis and therapy response in colorectal cancer. Nat Med. 2023;29(2):430-439.

[16] OmerogluS, GulmezS, UzunO, et al. Clinical significance of the histopathological metastatic largest lymph node size in colorectal cancer patients. Front Oncol. 2023;13:1120753.

[17] XuC, HuangQ, HuY, YeK, XuJ. A nomogram for predicting lymph nodes metastasis at the inferior mesenteric artery in rectal cancer: a retrospective case-control study. Updates Surg. 2024;76(2):513-520.

[18] GlasgowSC, BleierJIS, BurgartLJ, Finne CO, LowryAC. Meta-analysis of histopathological features of primary colorectal cancers that predict lymph node metastases. J Gastrointest Surg. 2012;16(5):1019-1028.

[19] HuangYM, HsuHH, LiuCK, et al. Histopathological and haemogram features correlate with prognosis in rectal cancer patients receiving neoadjuvant chemoradiation without pathological complete response. J Clin Med. 2022;11(17):4947.

[20] PengJ, ShengW, HuangD, et al. Perineural invasion in pT3N0 rectal cancer: the incidence and its prognostic effect. Cancer. 2011;117(7):1415-1421.

[21] SunQ, LiuT, LiuP, et al. Perineural and lymphovascular invasion predicts for poor prognosis in locally advanced rectal cancer after neoadjuvant chemoradiotherapy and surgery. J Cancer. 2019;10(10):2243-2249.

[22] KimPK, HongYJ, SakumaH, et al. Myocardial extracellular volume fraction and change in hematocrit level: MR evaluation by using T1 mapping in an experimental model of anemia. Radiology. 2018;288(1):93-98.

[23] GrandeM, MilitoG, AttinàGM, et al. Evaluation of clinical, laboratory and morphologic prognostic factors in colon cancer. World J Surg Oncol. 2008;6:98.

[24] BestMG, Wesseling P, WurdingerT. Tumor-educated platelets as a noninvasive biomarker source for cancer detection and progression monitoring. Cancer Res. 2018;78(13):3407-3412.

[25] WangYY, ZhouN, LiuH, et al. Circulating activated lymphocyte subsets as potential blood biomarkers of cancer progression. Cancer Med. 2020;9(14):5086-5094.

[26] GayLJ, Felding-Habermann B. Contribution of platelets to tumour metastasis. Nat Rev Cancer. 2011;11(2):123-134.

[27] LongY, WangT, GaoQ, ZhouC. Prognostic significance of pretreatment elevated platelet count in patients with colorectal cancer: a meta-analysis. Oncotarget. 2016;7(49):81849-81861.

[28] QianW, GeXX, WuJ, et al Prognostic evaluation of resectable colorectal cancer using platelet-associated indicators. Oncol Lett. 2019;18(1):571-580.

[29] KotechaK, SinglaA, TownendP, Merrett N. Association between neutrophil-lymphocyte ratio and lymph node metastasis in gastric cancer: a meta-analysis. Medicine. 2022;101(25):e29300.

[30] HołdakowskaA, Gerard JP, BujkoK. The importance of measuring baseline tumour volume (or alternatively tumour length along with its rectal circumferential extent) in the watch-and-wait strategy in rectal cancer: a review. Acta Oncol. 2022;61(9):1084-1092.

[31] JangirN, SinghA, JainP, Khemka S. The predictive value of depth of invasion and tumor size on risk of neck node metastasis in squamous cell carcinoma of the oral cavity: a prospective study. J Cancer Res Ther. 2022;18(4):977-983.

[32] ZhengX, WuM, ErL, et al. Risk factors for lymph node metastasis and prognosis in colorectal neuroendocrine tumours. Int J Colorectal Dis. 2022;37(2):421-428.

[33] YuY, HeZ, OuyangJ, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study. EBioMedicine. 2021;69:103460.

[34] BedrikovetskiS, Dudi-Venkata NN, KroonHM, et al. Artificial intelligence for pre-operative lymph node staging in colorectal cancer: a systematic review and meta-analysis. BMC Cancer. 2021;21(1):1058.

[35] SauerbreiW, Royston P, BinderH. Selection of important variables and determination of functional form for continuous predictors in multivariable model building. Stat Med. 2007;26(30):5512-5528.

[36] SaricaA, CerasaA, QuattroneA. Random forest algorithm for the classification of neuroimaging data in Alzheimer’s disease: a systematic review. Front Aging Neurosci. 2017;9:329.

[37] GohariK, Kazemnejad A, MohammadiM, et al. A Bayesian latent class extension of naive Bayesian classifier and its application to the classification of gastric cancer patients. BMC Med Res Methodol. 2023;23(1):190.

[38] ChenT, Guestrin C. XGBoost: a scalable tree boosting system. Paper presented at: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016; San Francisco, California, USA.

[39] YanJ, XuY, ChengQ, et al. LightGBM: accelerated genomically designed crop breeding through ensemble learning. Genome Biol. 2021;22(1):271.

[40] Bin ZhangZ, Srihari SN. Fast k-nearest neighbor classification using cluster-based trees. IEEE Trans Pattern Anal Mach Intell. 2004;26(4):525-528.

RIGHTS & PERMISSIONS

2024 The Author(s). MedComm - Future Medicine published by John Wiley & Sons Australia, Ltd on behalf of Sichuan International Medical Exchange & Promotion Association (SCIMEA).