|Table of Contents|

The machine learning model based on MRI radiomics of mesenteric fat in rectal cancer for preoperative identification of T2 and T3 stage rectal cancer

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2023 20
Page:
3822-3827
Research Field:
Publishing date:

Info

Title:
The machine learning model based on MRI radiomics of mesenteric fat in rectal cancer for preoperative identification of T2 and T3 stage rectal cancer
Author(s):
DENG Bo1; 2; YANG Yanwei3; LIU Yuanqing1; DAI Hui1
1Department of Radiology;3Department of Orthopedic Magnetic Resonance,the First Affiliated Hospital of Soochow University,Jiangsu Suzhou 215006,China;2Department of Radiology,Shanghai Fifth Rehabilitation Hospital,Shanghai 201600,China.
Keywords:
mesenteric fat; machine learning; magnetic resonance imaging; radiomics
PACS:
R735.3
DOI:
10.3969/j.issn.1672-4992.2023.20.019
Abstract:
Objective：To establish and validate an MRI radiomics model based on mesenteric fat by comparing different machine learning algorithm models for preoperative identification of T2 and T3 stage rectal cancer.Methods:The data of 288 patients with T2 and T3 stage rectal cancer were retrospectively enrolled.Radiomics features were extracted from the region of interest (ROI) of the lesion in T2WI,apparent diffusion coefficient (ADC),and diffusion-weighted imaging (DWI) sequences,respectively.After dimensionality reduction using between-group consistency analysis (ICC) and Pearson correlation analysis,features were selected for each sequence using minimum absolute contraction and selection operator (LASSO) regression analysis.Then,seven different machine learning algorithms including:Logistic,Random Forest,K-nearest neighbor (KNN),Decision Tree,Naive Bayes model,support vector machine (SVM),and extreme gradient boosting (XGBoost) were used to construct different prediction models of the radiomics features screened out by LASSO regression.The performance of each model was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC),and the best machine learning model was combined with clinical data.Decision curve analysis (DCA) and calibration curve were performed to evaluate the clinical utility and calibration of the joint model.Results:The radiomics model based on Logistic algorithm performed the most stable,with AUC of 0.876 and 0.807 in the training and test sets,respectively.The joint model based on MRI report T staging and Logistic algorithm showed excellent discrimination,and the AUC of the training set and the test set was 0.921 and 0.889,respectively.The calibration plot and clinical decision curve showed good clinical calibration and clinical practicality.Conclusion:The MRI multi-sequence machine learning model based on mesenteric fat has good predictive performance in the preoperative identification of T2 and T3 stage rectal cancer.

References:

［1］ MARIANA-M,DONATO H,CAMPOS N,et al.Interobserver variability in MRI measurements of mesorectal invasion depth in rectal cancer［J］.Abdominal Radiology,2022,47（3）:907-914.
［2］ 胡飞翔,岳亚丽,彭卫军,等.DWI联合T2WI在鉴别T2和T3期直肠癌术前分期中的应用价值［J］.放射学实践,2021,36(4):507-513. HU FX,YUE YL PENG WJ,et al. The application value of DWI combined with T2WI in distinguishing preoperative staging of T2 and T3 stage rectal cancer ［J］ Practice in Radiology,2021,36 (4):507-513.
［3］ QIAN P,YI X,CHEN C,et al.Pre-treatment CT-based radiomics nomogram for predicting microsatellite instability status in colorectal cancer［J］.European Radiology,2022,32（1）:714-724.
［4］ LIU Z,ZHANG XY,SHI YJ,et al.Radiomics analysis for evaluation of pathological complete response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer［J］.Clin Cancer Res,2017,23(23):7253-7262.
［5］ YANG S,ZHANG J,ZHANG YD,et al.FeAture Explorer (FAE):A tool for developing and comparing radiomics models［J］.PLOS ONE,2020,15(8):e237587.
［6］ LANQING Y,LIU D,FANG X，et al.Rectal cancer:can T2WI histogram of the primary tumor help predict the existence of lymph node metastasis［J］.European Radiology,2019,29（12）:6469-6476.
［7］ 李梦蕾，张敬，淡一波，等.术前预测结直肠癌淋巴结转移的临床-影像组学列线图的建立和验证［J］.中国癌症杂志,2020,30（01）:49-56. LI ML,ZHANG J,DAN YB,et al.Establishment and validation of a clinical imaging omics column chart for preoperative prediction of lymph node metastasis in colorectal cancer ［J］ Chinese Journal of Cancer,2020,30(01):49-56.
［8］ 周振，沈浮，陆海迪，等.基于高分辨T2WI的影像组学中不同分割方法对直肠癌术前T分期的影响［J］.中国医学计算机成像杂志,2021,27（03）:225-230. ZHOU Z,SHEN F,LU HD,et al.The impact of different segmentation methods on preoperative T-staging of rectal cancer in imaging omics based on high-resolution T2WI ［J］ .Chinese Journal of Medical Computer Imaging,2021,27(03):225-230.
［9］ HAIDI L,YUAN Y,ZHOU Z,et al.Assessment of MRI-based radiomics in preoperative T staging of rectal cancer:Comparison between minimum and maximum delineation methods［J］.BioMed Research International,2021,2021：1-9.
［10］ ZHAO B,GABRIEL RA,VAIDA F,et al.Using machine learning to construct nomograms for patients with metastatic colon cancer［J］.Colorectal Disease,2020,22（8）:914-922.
［11］ TIBERMACINE H,ROUANET P,SBARRA M,et al.Radiomics modelling in rectal cancer to predict disease-free survival:evaluation of different approaches［J］.British Journal of Surgery,2021,108（10）:1243-1250.
［12］ MOU L,JIN YM,ZHANG YC,et al.Radiomics for predicting perineural invasion status in rectal cancer［J］.World Journal of Gastroenterology,2021,27（33）:5610-5621.
［13］ ALFONSO R,NARDONE V,GIACOBBE G,et al.Radiomics as a new frontier of imaging for cancer prognosis:A narrative review［J］.Diagnostics,2021,11（10）:1796-1809.
［14］ FRANCESCA C,GIANNINI V,GABELLONI M,et al.Radiomics and magnetic resonance imaging of rectal cancer:From engineering to clinical practice［J］.Diagnostics,2021,11（5）:756-767.
［15］VETRI-SUDAR J,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］.European Radiology,2022,32（2）:971-980.
［16］HIRAM SH,ANDREW A,RAMI V,et al.Radiomics of MRI for pretreatment prediction of pathologic complete response,tumor regression grade,and neoadjuvant rectal score in patients with locally advanced rectal cancer undergoing neoadjuvant chemoradiation:an international multicenter study.［J］.European Radiology,2020,11:6263-6273.
［17］ LIU L,LIU Y,XU L,et al.Application of texture analysis based on apparent diffusion coefficient maps in discriminating different stages of rectal cancer［J］.J Magn Reson Imaging,2017,45(6):1798-1808.
［18］ARNALDO S,VERDE F,ROMEO V,et al.Radiomics and machine learning applications in rectal cancer:Current update and future perspectives［J］.World Journal of Gastroenterology,2021,27（32）:5306-5321.

Memo

Memo:
-
Last Update: 1900-01-01