Share：
Share this content in WeChat
X
[Chinese][PDF]71575
• Clinical Article •
The value of T2WI sequence-based radiomics in predicting recurrence of acute pancreatitis
HU Yuntao  HUANG Xiaohua  LIU Nian  TANG Lingling 

Cite this article as: Hu YT, Huang XH, Liu N, et al. The value of T2WI sequence-based radiomics in predicting recurrence of acute pancreatitis[J]. Chin J Magn Reson Imaging, 2021, 12(10): 12-15, 21. DOI:10.12015/issn.1674-8034.2021.10.003.


[Abstract] Objective To explore the value of MRI T2WI sequence radiomics in predicting the recurrence of acute pancreatitis (AP). Materials andMethods One hundred and forty-seven cases of AP in the Affiliated Hospital of North Sichuan Medical College from January 2014 to December 2015 were retrospectively analyzed, including 102 cases of primary AP and 45 cases of recurrent acute pancreatitis (RAP). They were randomly divided into a training group and a validation group in a 7∶3 ratio, 102 cases in training group (AP 70 cases, RAP 32 cases) and 45 cases in verification group (AP 32 cases, RAP 13 cases). Clinical characteristics of the two groups were also collected (age, sex, calculus, hyperlipidemia, history of alcohol consumption, complications, severity). IBEX software was used to outline the three dimensional surrounding pancreas parenchyma and extract texture features, including gray level co-occurrence matrix, gray level run length matrix, histogram and shape. Single factor analysis and least absolute shrinkage and selection operator (LASSO) were used for feature screening. Logistics regression was used to establish the radiomics model and clinical model for predicting AP recurrence. The predictive power of the model was evaluated by the area under the ROC curve (AUC).Results The radiomics model based on eight texture features (information measurement correction, clustering trend, correlation, dissimilarity, entropy, run nonuniformity, skewness, and volume) has a high diagnostic efficiency for predicting AP recurrence.In the training group, the AUC of AP recurrence predicted by radiomics model was 0.870 (95% CI:0.791—0.949), the sensitivity and specificity were 0.903 and 0.831 respectively. The AUC in the validation group was 0.836 (95% CI:0.718—0.954), the sensitivity and specificity were 0.786 and 0.774 respectively. The AUC for predicting AP recurrence based on the clinical model of hyperlipidemia is 0.634 (95% CI:0.550—0.717), the sensitivity and specificity were 0.689 and 0.578 respectively.Conclusions Based on MRI T2WI sequence radiomics model can predict AP recurrence. Information measurement correction, clustering trend, correlation, dissimilarity, entropy, run nonuniformity, skewness and volume are significant predictors of RAP.
[Keywords] radiomics；magnetic resonance imaging；T2 weighted imaging；acute pancreatitis；recurrence

HU Yuntao1   HUANG Xiaohua1*   LIU Nian1   TANG Lingling1, 2  

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

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

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

Conflicts of interest   None.

ACKNOWLEDGMENTS Sichuan Science and Technology Program (No.2020088); the Science and Technology Project of the Health Planning Committee of Sichuan (No.19PJ203); Bureau of Science & Technology and Intellectual Property Nanchong City (No.19SXHZ0429, No.19SXHZ0255).
Received  2021-04-22
Accepted  2021-06-16
DOI: 10.12015/issn.1674-8034.2021.10.003
Cite this article as: Hu YT, Huang XH, Liu N, et al. The value of T2WI sequence-based radiomics in predicting recurrence of acute pancreatitis[J]. Chin J Magn Reson Imaging, 2021, 12(10): 12-15, 21. DOI:10.12015/issn.1674-8034.2021.10.003.

[1]
Ji JT, Zhang D, Xin L, et al.Research progress in diagnosis and treatment of recurrent acute pancreatitis[J].Chin J Pancreatol, 2016, 16(3): 203-205. DOI: 10.3760/cma.j.issn.1674-1935.2016.03.016.
[2]
Lankisch PG, Apte M, Banks PA. Acute pancreatitis[J]. Lancet, 2015, 386(9988) :85-96. DOI: 10.1016/S0140-6736(14)60649-8.
[3]
Sankaran SJ, Xiao AY, Wu LM, et al. Frequency of progression from acute to chronic pancreatitis and risk factors: a meta-analysis[J]. Gastroenterology, 2015, 149(6) :1490-1500. DOI: 10.1053/j.gastro.2015.07.066.
[4]
Barkin JA, Freeman ML, Barkin JS. Is It Acute Pancreatitis or Recurrent Acute Pancreatitis Leading to Chronic Pancreatitis that Increases Pancreatic Cancer Risk?[J]. Gastroenterology, 2018, 155(4): 1279-1280. DOI: 10.1053/j.gastro.2018.09.023.
[5]
Nasief H, Zheng C, Schott D, et al. A machine learning based delta-radiomics process for early prediction of treatment response of pancreatic cancer[J]. NPJ Precis Oncol, 2019, 3(1): 25. DOI: 10.1038/s41698-019-0096-z.
[6]
Sadr-Azodi O, Oskarsson V, Discacciati A, et al. Pancreatic Cancer Following Acute Pancreatitis: A Population-based Matched Cohort Study[J]. Am J Gastroenterol, 2018, 113(11): 1711-1719. DOI: 10.1038/s41395-018-0255-9.
[7]
Xu Y, Lu L, E LN, et al. Application of Radiomics in Predicting the Malignancy of Pulmonary Nodules in Different Sizes[J]. AJR Am J Roentgenol, 2019, 213(6): 1213-1220. DOI: 10.2214/AJR.19.21490.
[8]
Song L, Zhu ZC, Jiang L, et al. Preliminary value of CT radiomics in predicting anaplastic lymphoma kinase fusion gene expression in lung adenocarcinoma[J]. Chin J Radiol, 2019, 53(11): 963-964. DOI: 10.3760/cma.j.issn.1005-1201.2019.11.007.
[9]
Hosny A, Parmar C, Quackenbush J, et al. Artificial intelligence in radiology[J]. Nat Rev Cancer, 2018, 18(8): 500-510. DOI: 10.1038/s41568-018-0016-5.
[10]
Banks PA, Bollen TL, Dervenis C, et al. Classification of acute pancreatitis--2012: revision of the Atlanta classification and definitions by international consensus[J]. Gut, 2013, 62(1): 102-111. DOI: 10.1136/gutjnl-2012-302779.
[11]
Guda NM, Trikudanathan G, Freeman ML. Idiopathic recurrent acute pancreatitis[J]. Lancet Gastroenterol Hepatol, 2018, 3(10): 720-728. DOI: 10.1016/S2468-1253(18)30211-5.
[12]
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.
[13]
Lin Q, Ji YF, Chen Y, et al. Radiomics model of contrast-enhanced MRI for early prediction of acute pancreatitis severity[J]. J Magn Reson Imaging, 2020, 51(2): 397-406. DOI: 10.1002/jmri.26798.
[14]
Chen Y, Chen TW, Wu CQ, et al. Radiomics model of contrast-enhanced computed tomography for predicting the recurrence of acute pancreatitis[J]. Eur Radiol, 2019, 29(8): 4408-4417. DOI: 10.1007/s00330-018-5824-1.
[15]
Yadav D, Pitchumoni CS. Issues in hyperlipidemic pancreatitis[J]. J Clin Gastroenterol, 2003, 36(1): 54-62. DOI: 10.1097/00004836-200301000-00016.
[16]
Peng L, Peng Y, Pu YQ, et al. Analyses of clinical characteristics and risk factors of 671 cases of recurrent acute pancreatitis[J]. J Prac Med, 2019, 35(18): 2924-2928. DOI: 10.3969/j.issn.1006-5725.2019.18.020.
[17]
Fonseca SE, Guerrero-Lozano R. Acute pancreatitis and recurrent acute pancreatitis: an exploration of clinical and etiologic factors and outcomes[J]. J Pediatr (Rio J), 2019, 95(6): 713-719. DOI: 10.1016/j.jped.2018.06.011.
[18]
Heyn C, Sue-Chue-Lam D, Jhaveri K, et al. MRI of the pancreas: problem solving tool[J]. J Magn Reson Imaging, 2012, 36(5): 1037-1051. DOI: 10.1002/jmri.23708.
[19]
Tirkes T, Menias CO, Sandrasegaran K. MR imaging techniques for pancreas[J]. Radiol Clin North Am, 2012, 50(3): 379-393. DOI: 10.1016/j.rcl.2012.03.003.

PREV MR texture analysis of paravertebral fat infiltration in patients with chronic low back pain based on IDEAL-IQ sequence
NEXT A neural network radiomics model for diagnosing lymph node metastasis in cervical cancer
  


LINK


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