Original Research

Radiomics model of contrast-enhanced MRI for early prediction of acute pancreatitis severity

Qiao Lin MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Medical Imaging and Department of Radiology, Gaoping District People's Hospital of Nanchong, Nanchong, Sichuan, China

Search for more papers by this author

Yi-fan JI MS,

Yi-fan JI MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Yong Chen MS,

Yong Chen MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Huan Sun MS,

Huan Sun MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Dan-dan Yang MS,

Dan-dan Yang MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Ai-li Chen MS,

Ai-li Chen MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Tian-wu Chen MD,

Tian-wu Chen MD

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Xiao Ming Zhang MD,

Corresponding Author

Xiao Ming Zhang MD

orcid.org/0000-0001-5327-8506

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Address reprint requests to: X.M.Z., Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, No. 63, Wenhua Road, Nanchong, Sichuan 637000, China. E-mail: [email protected], [email protected]Search for more papers by this author

Qiao Lin MS,

Qiao Lin MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Medical Imaging and Department of Radiology, Gaoping District People's Hospital of Nanchong, Nanchong, Sichuan, China

Search for more papers by this author

Yi-fan JI MS,

Yi-fan JI MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Yong Chen MS,

Yong Chen MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Huan Sun MS,

Huan Sun MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Dan-dan Yang MS,

Dan-dan Yang MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Ai-li Chen MS,

Ai-li Chen MS

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Tian-wu Chen MD,

Tian-wu Chen MD

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

Search for more papers by this author

Xiao Ming Zhang MD,

Corresponding Author

Xiao Ming Zhang MD

orcid.org/0000-0001-5327-8506

Sichuan Key Laboratory of Medical Imaging and Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, Sichuan, China

First published: 27 May 2019

https://doi.org/10.1002/jmri.26798

Citations: 47

The first two authors contributed equally to this work.

Contract grant sponsor: National Natural Science Foundation of China; Contract grant number: 81871440.

Share a link

Email
Wechat
Bluesky

Abstract

Background

Computed tomography (CT) or MR images may cause the severity of early acute pancreatitis (AP) to be underestimated. As an innovative image analysis method, radiomics may have potential clinical value in early prediction of AP severity.

Purpose

To develop a contrast-enhanced (CE) MRI-based radiomics model for the early prediction of AP severity.

Study Type

Retrospective.

Subjects

A total of 259 early AP patients were divided into two cohorts, a training cohort (99 nonsevere, 81 severe), and a validation cohort (43 nonsevere, 36 severe).

Field Strength/Sequence

3.0T, T₁-weighted CE-MRI.

Assessment

Radiomics features were extracted from the portal venous-phase images. The "Boruta" algorithm was used for feature selection and a support vector machine model was established with optimal features. The MR severity index (MRSI), the Acute Physiology and Chronic Health Evaluation (APACHE) II, and the bedside index for severity in acute pancreatitis (BISAP) were calculated to predict the severity of AP.

Statistical Tests

Independent t-test, Mann–Whitney U-test, chi-square test, Fisher's exact tests, Boruta algorithm, receiver operating characteristic analysis, DeLong test.

Results

Eleven potential features were chosen to develop the radiomics model. In the training cohort, the area under the curve (AUC) of the radiomics model, APACHE II, BISAP, and MRSI were 0.917, 0.750, 0.744, and 0.749, and the P value of AUC comparisons between the radiomics model and scoring systems were all less than 0.001. In the validation cohort, the AUC of the radiomics model, APACHE II, BISAP, and MRSI were 0.848, 0.725, 0.708, and 0.719, respectively, and the P value of AUC comparisons were 0.96 (radiomics vs. APACHE II), 0.40 (radiomics vs. BISAP), and 0.46 (radiomics vs. MRSI).

Data Conclusion

The radiomics model had good performance in the early prediction of AP severity.

Level of Evidence: 3

Technical Efficacy Stage: 2

J. Magn. Reson. Imaging 2020;51:397–406.

Supporting Information

References

1Frossard JL, Steer ML, Pastor CM. Acute pancreatitis. Lancet 2008; 371: 143–152.
10.1016/S0140-6736(08)60107-5
PubMed Web of Science® Google Scholar
2Forsmark CE, Swaroop VS, Wilcox CM. Acute pancreatitis. N Engl J Med 2016; 375: 1972–1981.
10.1056/NEJMra1505202
CAS PubMed Web of Science® Google Scholar
3Simoes M, Alves P, Esperto H, et al. Predicting acute pancreatitis severity: Comparison of prognostic scores. Gastroenterol Res 2011; 4: 216–222.
PubMed Google Scholar
4Gao W, Yang HX, Ma CE. The value of BISAP score for predicting mortality and severity in acute pancreatitis: A systematic review and meta-analysis. PLoS One 2015; 10:e0130412.
10.1371/journal.pone.0142025
PubMed Web of Science® Google Scholar
5Quintens H, Chevallier D, Padovani B, et al. Cancer of the prostate. Computed tomography and magnetic resonance imaging in the assessment of extracapsular extension. J Urol 1990; 96: 207–209.
CAS Google Scholar
6Tang W, Zhang XM, Xiao B, et al. Magnetic resonance imaging versus Acute Physiology and Chronic Healthy Evaluation II score in predicting the severity of acute pancreatitis. Eur J Radiol 2011; 80: 637–642.
10.1016/j.ejrad.2010.08.020
PubMed Web of Science® Google Scholar
7Lambin P, Riosvelazquez E, Leijenaar R, et al. Radiomics: Extracting more information from medical images using advanced feature analysis. Eur J Cancer 2012; 48: 441–446.
10.1016/j.ejca.2011.11.036
PubMed Web of Science® Google Scholar
8Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: The bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 2017; 14: 749–762.
10.1038/nrclinonc.2017.141
PubMed Web of Science® Google Scholar
9Gillies RJ, Kinahan PE, Hricak H. Radiomics: Images are more than pictures, they are data. Radiology 2016; 278: 563–577.
10.1148/radiol.2015151169
PubMed Web of Science® Google Scholar
10Chen Y, Chen TW, Wu CQ, et al. Radiomics model of contrast-enhanced computed tomography for predicting the recurrence of acute pancreatitis. Eur Radiol 2018 [Epub ahead of print].
10.1007/s00330-018-5824-1
Web of Science® Google Scholar
11Shinagare AB, Ip IK, Raja AS, et al. Use of CT and MRI in emergency department patients with acute pancreatitis. Abdom Imaging 2015; 40: 272–277.
10.1007/s00261-014-0210-1
PubMed Web of Science® Google Scholar
12Spanier BWM, Nio Y, van der Hulst RWM, et al. Practice and yield of early CT scan in acute pancreatitis: A Dutch observational multicenter study. Pancreatology 2010; 10: 222–228.
10.1159/000243731
CAS PubMed Web of Science® Google Scholar
13Banks PA, Bollen TL, Dervenis C, et al. Classification of acute pancreatitis-2012: Revision of the Atlanta classification and definitions by international consensus. Gut 2013; 62: 102–111.
10.1136/gutjnl-2012-302779
PubMed Web of Science® Google Scholar
14Zhang L, Fried DV, Fave XJ, et al. IBEX: An open infrastructure software platform to facilitate collaborative work in radiomics. Med Phys 2015; 42: 1341–1353.
10.1118/1.4908210
PubMed Google Scholar
15Shafiq-Ul-Hassan M, Zhang GG, Latifi K, et al. Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels. Med Phys 2017; 44: 1050–1062.
10.1002/mp.12123
CAS PubMed Web of Science® Google Scholar
16Kursa M, Rudnicki W. Feature selection with the Boruta package. J Stat Softw 2010; 36: 1–13.
10.18637/jss.v036.i11
Web of Science® Google Scholar
17Kursa MB. Robustness of random forest-based gene selection methods. BMC Bioinform 2014; 15: 8.
10.1186/1471-2105-15-8
PubMed Web of Science® Google Scholar
18DeLong ER, DeLong DM, Clarke-Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics 1988; 44: 837–845
10.2307/2531595
CAS PubMed Web of Science® Google Scholar
19Yadav D, Lowenfels AB. The epidemiology of pancreatitis and pancreatic cancer. Gastroenterology 2013; 144: 1252–1261.
10.1053/j.gastro.2013.01.068
PubMed Web of Science® Google Scholar
20Li XY, Wang XB, Liu XF, et al. Prevalence and risk factors of organ failure in patients with severe acute pancreatitis. World J Emerg Med 2010; 1: 201–204.
PubMed Google Scholar
21Tsuji Y, Takahashi N, Isoda H. Early diagnosis of pancreatic necrosis based on perfusion CT to predict the severity of acute pancreatitis. J Gastroenterol 2017; 52: 1130–1139.
10.1007/s00535-017-1330-5
PubMed Web of Science® Google Scholar
22Larvin M. Assessment of severity and prognosis in acute pancreatitis. Eur J Gastroenterol Hepatol 1997; 9: 122–130.
10.1097/00042737-199702000-00004
CAS PubMed Web of Science® Google Scholar
23Bollen TL, Singh VK, Maurer R, et al. A comparative evaluation of radiologic and clinical scoring systems in the early prediction of severity in acute pancreatitis. Am J Gastroenterol 2012; 107: 612–619.
10.1038/ajg.2011.438
PubMed Web of Science® Google Scholar
24Arvanitakis M, Koustiani G, Gantzarou A, et al. Staging of severity and prognosis of acute pancreatitis by computed tomography and magnetic resonance imaging—A comparative study. Dig Liver Dis 2007; 39: 473–482.
10.1016/j.dld.2007.01.015
CAS PubMed Web of Science® Google Scholar
25Cho JH, Kim TN, Chung HH, Kim KH. Comparison of scoring systems in predicting the severity of acute pancreatitis. World J Gastroenterol 2015; 21: 2387–2394.
10.3748/wjg.v21.i8.2387
PubMed Web of Science® Google Scholar
26Papachristou GI, Muddana V, Yadav D, et al. Comparison of BISAP, Ranson's, APACHE-II, and CTSI scores in predicting organ failure, complications, and mortality in acute pancreatitis. Am J Gastroenterol 2010; 107: 435–441.
10.1038/ajg.2009.622
Web of Science® Google Scholar
27Larue RTHM, van Timmeren JE, de Jong EEC, et al. Influence of gray level discretization on radiomic feature stability for different CT scanners, tube currents and slice thicknesses: A comprehensive phantom study. Acta Oncol 2017; 56: 1544–1553.
10.1080/0284186X.2017.1351624
PubMed Web of Science® Google Scholar
28Liu Q, Gu Q, Wu Z. Feature selection method based on support vector machine and shape analysis for high-throughput medical data. Comput Biol Med 2017; 91: 103–111.
10.1016/j.compbiomed.2017.10.008
PubMed Web of Science® Google Scholar
29Knoefel WT, Kollias N, Warshaw AL, et al. Pancreatic microcirculatory changes in experimental pancreatitis of graded severity in the rat. Surgery 1994; 116: 904–913.
CAS PubMed Web of Science® Google Scholar
30Grossmann P, Stringfield O, El-Hachem N, et al. Defining the biological basis of radiomic phenotypes in lung cancer. Elife 2017; 6:e23421.
10.7554/eLife.23421
PubMed Web of Science® Google Scholar
31Zhou M, Leung A, Echegaray S, et al. Non-small cell lung cancer radiogenomics map identifies relationships between molecular and imaging phenotypes with prognostic implications. Radiology 2018; 286: 307–315.
10.1148/radiol.2017161845
PubMed Web of Science® Google Scholar

Citing Literature

Volume51, Issue2

February 2020

Pages 397-406

Radiomics model of contrast-enhanced MRI for early prediction of acute pancreatitis severity

Abstract

Background

Purpose

Study Type

Subjects

Field Strength/Sequence

Assessment

Statistical Tests

Results

Data Conclusion

Supporting Information

References

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Radiomics model of contrast-enhanced MRI for early prediction of acute pancreatitis severity

Abstract

Background

Purpose

Study Type

Subjects

Field Strength/Sequence

Assessment

Statistical Tests

Results

Data Conclusion

Supporting Information

References

Citing Literature

References

Related

Information