Skip to main content

Advertisement

SpringerLink
Log in

Automatic quantitative evaluation of normal pancreas based on deep learning in a Chinese adult population

  • Pancreas
  • Published:
Abdominal Radiology Aims and scope Submit manuscript

Abstract

Objective

To develop a 3D U-Net-based model for the automatic segmentation of the pancreas using the diameters, volume, and density of normal pancreases among Chinese adults.

Methods

A total of 2778 pancreas images (dataset 1) were retrospectively collected and randomly divided into training (n = 2252), validation (n = 245), and test (n = 281) datasets. The segmentation model for the pancreas was constructed through cascaded application of two 3D U-Net networks. The segmentation efficiency for the pancreas was evaluated by the Dice similarity coefficient (DSC). Another dataset of 3189 normal pancreas CT images (dataset 2) was obtained for external validation, including 1063 non-contrast images, 1063 arterial phase images, and 1063 portal venous phase images. The pancreas segmentation in dataset 2 was assessed objectively and manually revised by two radiologists. Then, the pancreatic volume, diameters, and average CT value for each phase of pancreas images in dataset 2 were calculated. The relationships between pancreas volume and age, sex, height, and weight were analyzed.

Results

In dataset 1, a mean DSC of 0.94 for the test dataset was achieved. In dataset 2, the objective assessment yielded a 90% satisfaction rate for the automatic segmentation of the pancreas as external validation. The diameters of the pancreas were 43.71–44.28 mm, 67.40–68.15 mm, and 114.53–117.06 mm, respectively. The average pancreatic volume was 63,969.06–65,247.75 mm3, which was greatest at the age of 18–38 and then decreased to a minimum at the age of 69–85. The CT value of the pancreas also decreased with age, from a maximum value of 38.87 ± 9.70 HU to a minimum of 27.72 ± 10.85 HU.

Conclusion

The pancreas segmentation tool based on deep learning can segment the pancreas on CT images and measure its normal diameter, volume, and CT value accurately and effectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Sakata N, Egawa S, Rikiyama T, et al. Computed Tomography Reflected Endocrine Function of the Pancreas[J]. Gastrointest Surg, 2011, 15(3):525-532. https://doi.org/10.1007/s11605-010-1406-5.

    Article  Google Scholar 

  2. Age-related volumetric changes in pancreas: a stereological study on computed tomography. Surg Radiol Anat[J], 2012(34):935–941. https://doi.org/10.1007/s00276-012-0988-x.

  3. Saisho Y, Butler AE, Meier JJ, et al. Pancreas volumes in humans from birth to age one hundred taking into account sex, obesity, and presence of type-2 diabetes [J]. Clin Anat. 2007,20(8): 933-942. https://doi.org/10.1002/ca.20543.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. A. Djuric-Stefanovic, D. Masulovic, J.Kostic et al. CT volumetry of normal pancreas: correlation with the pancreatic diameters measurable by the cross-sectional imaging, and relationship with the gender, age, and body constitution[J]. Surg Radiol Anat. 2012,34(9):811-817. https://doi.org/10.1007/s00276-0962-7.

    Article  CAS  PubMed  Google Scholar 

  5. J-M Lohr, N Panic, M Vujasinovic, et al. The aging pancreas: a systematic review of the evidence and analysis of the consequences[J]. J Intern Med. 2018,283(5):446-460. https://doi.org/10.1111/joim.12745.

    Article  PubMed  Google Scholar 

  6. Steve V DeSouza, Ruma G Singh, Harry D Yoon, et al. Pancreas volume in health and disease: a system review and meta-analysis[J]. Expert Rev Gastroenterol Hepatol. 2018,12(8):757–766. https://doi.org/10.1080/17474124.2018.1496015.

  7. Figen Tunali Turkdogan, Ersen Ertekin, Ozum Tuncyurek, et al. A new method: measurement of pancreas volume in computerized tomography as a diagnostic guide for acute pancreatitis[J]. J Pak Med Assoc. 2020,70(8):1408–1412.https://doi.org/10.5455/JPMA.5850.

  8. Zhiyong Lin, Yingpu Cui, Jia Liu, et al. Automated segmentation of kidney and renal mass and automated detection of renal mass in CT urography using 3D U-Net-based deep convolutional neural network[J]. European Radiology.2020. https://doi.org/10.1007/s00330-020-07608-9.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Peter M Graffy, Veit Sandfort, Ronald M Summers, et al. Automated Liver Fat Quantification at Nonenhanced Abdominal CT for Population-based Steatosis Assessment[J]. Radiology. 2019,293(2):334–342. https://doi.org/10.1148/radiol.2019190512.

  10. Fan Fu, Jiang Wei, Miao Zhang et al. Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network. 2020,11:4829. https://doi.org/10.1038/s/41467-020-18606-2.

  11. Philippe MF, Benabadji S, Trystram LB et al. Pancreatic Volume and Endocrine and Exocrine Functions in Patients with Diabetes[J]. Pancreas, 2011,40(3): 359-363. https://doi.org/10.1097/mpa.0b013e3182072032.

    Article  CAS  PubMed  Google Scholar 

  12. Roth Holger R, Lu Le, Lay Nathan, et al. Spatial aggregation of holistically-nested convolutional neural network for automated pancreas localization and augmentation[J]. Medical Image Analysis. 2018,45:94–107.https://doi.org/10.1016/j.media.01.006.

  13. Weisheng Li, Sheng Qin, Feiyan Li, et al. MAD-UNET: A deep U-shaped network combined with an attention mechanism for pancreas segmentation in CT images[J]. Medical Physics. 2021,1(48):329-341. https://doi.org/10.1002/mp.14617.

    Article  Google Scholar 

  14. Koç U, Taydaş O. Evaluation of pancreatic steatosis prevalence and anthropometric measurements using non-contrast computed tomography. Turk J Gastroenterol. 2020 Sep;31(9):640-648. https://doi.org/10.5152/tjg.2020.19434.

  15. Henning Schrader, Bjoren A. Menge, Simone Schneider, et al. Reduced Pancreatic Volume and B-Cell Area in Patients with Chronic Pancreatitis[J]. Gastroenterology. 2009,136(2):513-522. https://doi.org/10.1053/j.gastro.2008.10.083.

    Article  PubMed  Google Scholar 

  16. Roh YH, Kang BK, Song SY, et al. Preoperative CT anthropometric measurements and pancreatic pathology increase risk for postoperative pancreatic fistula in patients following pancreaticoduodenectomy[J]. PLoS One. 2020,15(12):e0243515. https://doi.org/10.1371/journal.pone.0243515.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Shimonov M, Abtomonova Z, Groutz A, et al. Associations between body composition and prognosis of patients admitted because of acute pancreatitis: a retrospective study[J]. Eur J Clin Nutr. 2020. https://doi.org/10.1038/s41430-020-00789-y. Epub ahead of print. PMID: 33116236.

  18. Klupp F, Klauss M, Rahbari NN, et al. Volume changes of the pancreatic head remnant after distal pancreatectomy[J]. Surgery.2020,167(2):455-467. https://doi.org/10.1016/j.surg.2019.09.008.

    Article  PubMed  Google Scholar 

  19. Lim S, Bae JH, Chun EJ, et al. Difference in Pancreatic volume, fat content, and fat density measured by multidetector-row computed tomography according to the duration of diabetes[J].Acta Diabetol.2014,51(5):739–748. https://doi.org/10.1007/s00592-014-0581-3.

  20. Sun Zhaonan, Cui Yingpu, Liu Xiang et al. Quantitative evaluation of chronically obstructed kidneys from noncontrast computed tomography based on deep learning[J]. European Journal of Radiology. 2021. https://doi.org/10.1016/j.ejrad.2021.109535.

    Article  Google Scholar 

  21. Nalin Nanda, Prerna Kakkar, Sushama Nagpal. Computer-Aided Segmentation of Liver Lesions in CT Scans Using Cascaded Convolutional Neural Networks and Genetically Optimised Classifier[J]. Arabian Journal for Science and Engineering.2019,44:4049-4062. https://doi.org/10.1007/s13369-019-03735-8.

    Article  Google Scholar 

Download references

Acknowledgements

Thanks for the programming support from Weipeng Liu and Xiangpeng Wang and data processing support from Huang Jiahao of Beijing Smart Tree Medical Technology Co. Ltd.

Funding

The authors state that this work has not received any funding.

Author information

Authors and Affiliations

  1. Department of Radiology, Peking University First Hospital, No.8, Xishiku Street, Xicheng District, Beijing, 100034, China

    Jinxiu Cai, Xiaochao Guo, Ke Wang, Xiaodong Zhang & Xiaoying Wang

  2. Beijing Smart Tree Medical Technology Co.Ltd, Beijing, China

    Yaofeng Zhang & Dadou Zhang

Authors
  1. Jinxiu Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaochao Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ke Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yaofeng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Dadou Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xiaodong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Xiaoying Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaoying Wang.

Ethics declarations

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Ethical approval

Institutional Review Board approval was obtained [IRB number 2019 (160)].

Informed Consent

Written informed consent was waived by the Institutional Review Board.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 12 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Cai, J., Guo, X., Wang, K. et al. Automatic quantitative evaluation of normal pancreas based on deep learning in a Chinese adult population. Abdom Radiol 47, 1082–1090 (2022). https://doi.org/10.1007/s00261-021-03327-x

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00261-021-03327-x

Keywords

Search

Navigation