Share：
Share this content in WeChat
X
[Chinese][PDF]62016
• Clinical Article •
Prediction of lymph node metastasis of pancreatic ductal adenocarcinoma based on radiomics model of T1WI arterial phase
LIU Zhuoyu  HUANG Xiaohua  CHEN Yuwei  HU Yuntao  TANG Lingling  LIU Nian 

Cite this article as: Liu ZY, Huang XH, Chen YW, et al. Prediction of lymph node metastasis of pancreatic ductal adenocarcinoma based on radiomics model of T1WI arterial phase[J]. Chin J Magn Reson Imaging, 2022, 13(8): 30-35. DOI:10.12015/issn.1674-8034.2022.08.006.


[Abstract] Objective To evaluate the predictive value of pancreatic TIWI arterial phase radiomics model for lymph node metastasis in pancreatic ductal adenocarcinoma (PDAC). Methods and Materials: The MRI images and clinicopathological information of 121 patients with PDAC confirmed by pathology and preoperative enhancement MRI were analyzed retrospectively from March 2016 to March 2022. According to the pathological report of postoperative lymph nodes, 44 cases were positive and 77 cases were negative. The patients were randomly divided into training group (n=83) and validation group (n=38) according to 7∶3. Two physicians manually delineated the three-dimensional region of interest (3D-ROI) of pancreatic masses on T1WI arterial phase images and extracted features. Single factor analysis (Student's t test and Mann-Whitney U test) and the least absolute shrinkage and selection operator were used to screen the optimal features. Three prediction models were established based on decision tree, support vector machine and logical regression machine learning methods, respectively. The prediction performance of the model was evaluated by using the area under the receiver operating characteristic curve (AUC), the Hosmer-Lemesow test and the calibration plot were performed for the goodness of fit test of the model.Results There was no significant difference in clinicopathological characteristics (age, sex, tumor location, histological grade, CA199, T stage) between lymph node metastasis positive group and negative group, training group and validation group (P＞0.05). A total of 1223 features were extracted based on 3D-ROI. After dimensionality reduction, five optimal features for predicting lymph node metastasis were obtained and then the model was established. In the training group, the AUC of support vector machine model, decision tree model and logical regression model were 0.882 [95% (confidence interval, CI): 0.797-0.968], 0.842 (95% CI: 0.755-0.930) and 0.813 (95% CI: 0.710-0.915) respectively. In the validation group, the AUC of the three models were 0.726 (95% CI: 0.546-0.906), 0.753 (95% CI: 0.606-0.899), 0.702 (95% CI: 0.522-0.883). Delong test showed that there was no significant difference between the three models (P＞0.05). Three models were analyzed using the Hosmer-Lemesow test and performed well (P＞0.05).Conclusions The radiomics model based on T1WI arterial phase images has a certain value in predicting lymph node metastasis in PDAC.
[Keywords] magnetic resonance imaging；radiomics；pancreatic ductal adenocarcinoma；lymph node metastasis

LIU Zhuoyu   HUANG Xiaohua*   CHEN Yuwei   HU Yuntao   TANG Lingling   LIU Nian  

Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong 637000, China

Huang XH, E-mail: 15082797553@163.com

Conflicts of interest   None.

ACKNOWLEDGMENTS Nanchong City-School Science and Technology Strategic Cooperation Project (No. 20SXQT0303).
Received  2022-04-29
Accepted  2022-07-29
DOI: 10.12015/issn.1674-8034.2022.08.006
Cite this article as: Liu ZY, Huang XH, Chen YW, et al. Prediction of lymph node metastasis of pancreatic ductal adenocarcinoma based on radiomics model of T1WI arterial phase[J]. Chin J Magn Reson Imaging, 2022, 13(8): 30-35. DOI:10.12015/issn.1674-8034.2022.08.006.

[1]
Siegel RL, Miller KD, Jemal A. Cancer statistics, 2019[J]. CA Cancer J Clin. 2019, 69(1): 7-34. DOI: 10.3322/caac.21551.
[2]
Chu LC, Goggins MG, Fishman EK. Diagnosis and detection of pancreatic cancer[J]. Cancer J, 2017, 23(6): 333-342. DOI: 10.1097/PPO.0000000000000290.
[3]
Komo T, Murakami Y, Kondo N, et al. Prognostic impact of Para-aortic lymph node micrometastasis in pancreatic ductal adenocarcinoma[J]. Ann Surg Oncol, 2016, 23(6): 2019-2027. DOI: 10.1245/s10434-016-5120-8.
[4]
Khorana AA, Mangu PB, Berlin J, et al. Potentially curable pancreatic cancer: American society of clinical oncology clinical practice guideline update[J]. J Clin Oncol, 2017, 35(20): 2324-2328. DOI: 10.1200/JCO.2017.72.4948.
[5]
Wang Z, Liu DJ, Huo YM, et al. Impact of lymph node metastasis on survival of patients with pancreatic cancer[J]. Chin J Hepatobiliary Surg, 2016(10): 672-676. DOI: 10.3760/cma.j.issn.1007-8118.2016.10.007.
[6]
Fowler KJ. CT assessment of pancreatic cancer: what are the gaps in predicting surgical outcomes?[J]. Radiology, 2018, 289(3): 719-720. DOI: 10.1148/radiol.2018181912.
[7]
Hanada K, Amano H, Abe T. Early diagnosis of pancreatic cancer: current trends and concerns[J]. Ann Gastroenterol Surg, 2017, 1(1): 44-51. DOI: 10.1002/ags3.12004.
[8]
Shi ZW, Liu ZY. The challenges and solutions in radiomics study[J]. Chin J Radiol, 2022, 56(1): 9-11. DOI: 10.3760/cma.j.cn112149-20211111-00998.
[9]
Yip SSF, Aerts HJWL. Applications and limitations of radiomics[J]. Phys Med Biol, 2016, 61(13): R150-R166. DOI: 10.1088/0031-9155/61/13/R150.
[10]
Liu ZY, Tang LL, Huang XH, et al. Research progress of radiomics in evaluation of pancreatic tumors[J]. Int J Med Radiol, 2021, 44(6): 683-687. DOI: 10.19300/j.2021.Z18835.
[11]
He M, Xue HD, Jin ZY. Radiomics in pancreatic cancer: the state of art[J]. Chin J Radiol, 2020, 54(10): 1029-1032. DOI: 10.3760/cma.j.cn112149-20190903-00738.
[12]
Fang J, Huang XH, Liu N, et al. Research progress of radiomics in evaluation of curative effect of pancreatic cancer[J]. Chin J Magn Reson Imaging, 2021, 12(10): 105-108. DOI: 10.12015/issn.1674-8034.2021.10.027.
[13]
de la Pinta C. Radiomics in pancreatic cancer for oncologist: present and future[J]. Hepatobiliary Pancreat Dis Int, 2022, 21(4): 356-361. DOI: 10.1016/j.hbpd.2021.12.006.
[14]
Ebrahimian S, Singh R, Netaji A, et al. Characterization of benign and malignant pancreatic lesions with DECT quantitative metrics and radiomics[J]. Acad Radiol, 2022, 29(5): 705-713. DOI: 10.1016/j.acra.2021.07.008.
[15]
Bian Y, Guo SW, Jiang H, et al. Relationship between radiomics and risk of lymph node metastasis in pancreatic ductal adenocarcinoma[J]. Pancreas, 2019, 48(9): 1195-1203. DOI: 10.1097/MPA.0000000000001404.
[16]
Bian Y, Guo SW, Jiang H, et al. Radiomics nomogram for the preoperative prediction of lymph node metastasis in pancreatic ductal adenocarcinoma[J/OL]. Cancer Imaging, 2022 [2022-04-29]. https://cancerimagingjournal.biomedcentral.com/articles/10.1186/s40644-021-00443-1. DOI: 10.1186/s40644-021-00443-1.
[17]
Li K, Yao QD, Xiao JJ, et al. Contrast-enhanced CT radiomics for predicting lymph node metastasis in pancreatic ductal adenocarcinoma: a pilot study[J/OL]. Cancer Imaging, 2020 [2022-04-29]. https://cancerimagingjournal.biomedcentral.com/articles/10.1186/s40644-020-0288-3. DOI: 10.1186/s40644-020-0288-3.
[18]
Shi ZS, Ma CL, Huang XM, et al. Magnetic resonance imaging radiomics-based nomogram from primary tumor for pretreatment prediction of peripancreatic lymph node metastasis in pancreatic ductal adenocarcinoma: a multicenter study[J]. J Magn Reson Imaging, 2022, 55(3): 823-839. DOI: 10.1002/jmri.28048.
[19]
Wang SC, Parekh JR, Porembka MR, et al. A pilot study evaluating serum MMP7 as a preoperative prognostic marker for pancreatic ductal adenocarcinoma patients[J]. J Gastrointest Surg, 2016, 20(5): 899-904. DOI: 10.1007/s11605-015-3057-z.
[20]
Tao LY, Zhang LF, Peng Y, et al. Preoperative neutrophil-to-lymphocyte ratio and tumor-related factors to predict lymph node metastasis in patients with pancreatic ductal adenocarcinoma (PDAC)[J]. Oncotarget, 2016, 7(45): 74314-74324. DOI: 10.18632/oncotarget.11031.
[21]
Lee YN, Moon JH, Kim HK, et al. A triple approach for diagnostic assessment of endoscopic ultrasound-guided fine needle aspiration in pancreatic solid masses and lymph nodes[J]. Dig Dis Sci, 2014, 59(9): 2286-2293. DOI: 10.1007/s10620-014-3119-1.
[22]
Roche CJ, Hughes ML, Garvey CJ, et al. CT and pathologic assessment of prospective nodal staging in patients with ductal adenocarcinoma of the head of the pancreas[J]. AJR Am J Roentgenol, 2003, 180(2): 475-480. DOI: 10.2214/ajr.180.2.1800475.
[23]
Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: Extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[24]
Lafata KJ, Wang YQ, Konkel B, et al. Radiomics: a primer on high-throughput image phenotyping[J/OL]. Abdom Radiol (NY), 2021 [2022-04-29]. https://link.springer.com/article/10.1007/s00261-021-03254-x. DOI: 10.1007/s00261-021-03254-x.
[25]
Liang XY, Cai W, Liu XY, et al. A radiomics model that predicts lymph node status in pancreatic cancer to Guide clinical decision making: a retrospective study[J]. J Cancer, 2021, 12(20): 6050-6057. DOI: 10.7150/jca.61101.
[26]
Gao JH, Han F, Jin YY, et al. A radiomics nomogram for the preoperative prediction of lymph node metastasis in pancreatic ductal adenocarcinoma[J/OL]. Front Oncol, 2020 [2022-04-29]. https://www.frontiersin.org/articles/10.3389/fonc.2020.01654/full. DOI: 10.3389/fonc.2020.01654.
[27]
Zhu YD, Yu YX, Yang L. Radiomic model based on DCE-MRI for the preoperative prediction of SLN metastasis in breast cancer[J]. Int J Med Radiol, 2021, 44(6): 632-637. DOI: 10.19300/j.2021.L18812.
[28]
Meng YK, Zhang YC, Zhang CD, et al. To compare the predictive value of the radiomics siganature extrated from MRI plain or enhancement imaging for the survival of rectal cancer[J]. Chin J Radiol, 2018, 52(5): 349-355. DOI: 10.3760/cma.j.issn.1005-1201.2018.05.006.
[29]
Mayerhoefer ME, Materka A, Langs G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
[30]
Abbasian Ardakani A, Bureau NJ, Ciaccio EJ, et al. Interpretation of radiomics features-a pictorial review[J/OL]. Comput Methods Programs Biomed, 2022 [2022-04-29]. https://www.sciencedirect.com/science/article/abs/pii/S0169260721006830. DOI: 10.1016/j.cmpb.2021.106609.

PREV A comparative study of amide proton transfer weighted imaging and intravoxel incoherent motion imaging in the diagnosis of pathological grade of lung adenocarcinoma and its correlation with SUVmax
NEXT Value of different ADC to access complete response of rectal cancer after neoadjuvant therapy: A Meta analysis
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn