Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Jan 5;22(1):5.
doi: 10.1186/s12880-021-00729-7.

Deep learning-based pancreas volume assessment in individuals with type 1 diabetes

Raphael Roger  1 , Melissa A Hilmes  2   3 , Jonathan M Williams  4 , Daniel J Moore  3   5 , Alvin C Powers  4   6   7 , R Cameron Craddock  1 , John Virostko  8   9   10   11
Affiliations

Deep learning-based pancreas volume assessment in individuals with type 1 diabetes

Raphael Roger et al. BMC Med Imaging. .

Abstract

Pancreas volume is reduced in individuals with diabetes and in autoantibody positive individuals at high risk for developing type 1 diabetes (T1D). Studies investigating pancreas volume are underway to assess pancreas volume in large clinical databases and studies, but manual pancreas annotation is time-consuming and subjective, preventing extension to large studies and databases. This study develops deep learning for automated pancreas volume measurement in individuals with diabetes. A convolutional neural network was trained using manual pancreas annotation on 160 abdominal magnetic resonance imaging (MRI) scans from individuals with T1D, controls, or a combination thereof. Models trained using each cohort were then tested on scans of 25 individuals with T1D. Deep learning and manual segmentations of the pancreas displayed high overlap (Dice coefficient = 0.81) and excellent correlation of pancreas volume measurements (R2 = 0.94). Correlation was highest when training data included individuals both with and without T1D. The pancreas of individuals with T1D can be automatically segmented to measure pancreas volume. This algorithm can be applied to large imaging datasets to quantify the spectrum of human pancreas volume.

Keywords: Artificial intelligence; Auto-segmentation; Automatic segmentation; MRI; Machine learning; Neural network; Semantic; Size; T1D.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Fig. 1
Fig. 1
Representative manual and deep learning-based pancreas segmentations from an individual (A) with T1D or (B) with no pancreas pathology. The representative individual with T1D was a 13-year-old male with 2-month diabetes duration (Dice coefficient = 0.82) while the representative control individual was a 15-year-old male with no known pancreas pathology (Dice coefficient = 0.84). Three dimensional overlays of manual (red) and deep learning-based (green) segmentations are shown for both representative individuals with the pancreas tail oriented to the reader’s left for best visualization. Note the smaller and thinner pancreas size in the individual with T1D
Fig. 2
Fig. 2
Manual and deep learning-based pancreas volume measurements display correlation across a cohort including individuals with and without T1D (R2 = 0.94) and in subsets of individuals with T1D (red; R2 = 0.91) or controls (blue; R2 = 0.93)
Fig. 3
Fig. 3
Bland-Altman plot of the agreement between deep learning-based and manual pancreas volume measurements. The 95% limits of agreement are displayed with dotted lines. Deep learning-based measurement of pancreas volume tends to underestimate pancreas size compared with manual measurements (bias = 2.7 ml), particularly at larger pancreas sizes
See this image and copyright information in PMC

References

    1. Garcia TS, Rech TH, Leitao CB. Pancreatic size and fat content in diabetes: a systematic review and meta-analysis of imaging studies. PLoS One. 2017;12(7):e0180911. doi: 10.1371/journal.pone.0180911. - DOI - PMC - PubMed
    1. Campbell-Thompson ML, Filipp SL, Grajo JR, Nambam B, Beegle R, Middlebrooks EH, Gurka MJ, Atkinson MA, Schatz DA, Haller MJ. Relative pancreas volume is reduced in first-degree relatives of patients with type 1 diabetes. Diabetes Care. 2019;42(2):281–287. doi: 10.2337/dc18-1512. - DOI - PMC - PubMed
    1. Virostko J, Williams J, Hilmes M, Bowman C, Wright JJ, Du L, Kang H, Russell WE, Powers AC, Moore DJ. Pancreas volume declines during the first year after diagnosis of type 1 diabetes and exhibits altered diffusion at disease onset. Diabetes Care. 2019;42(2):248–257. doi: 10.2337/dc18-1507. - DOI - PMC - PubMed
    1. Al-Mrabeh A, Hollingsworth KG, Shaw JAM, McConnachie A, Sattar N, Lean MEJ, Taylor R. 2-year remission of type 2 diabetes and pancreas morphology: a post-hoc analysis of the DiRECT open-label, cluster-randomised trial. Lancet Diabetes Endocrinol. 2020;8(12):939–948. doi: 10.1016/S2213-8587(20)30303-X. - DOI - PubMed
    1. Anwar SM, Majid M, Qayyum A, Awais M, Alnowami M, Khan MK. Medical image analysis using convolutional neural networks: a review. J Med Syst. 2018;42(11):1–13. doi: 10.1007/s10916-018-1088-1. - DOI - PubMed

Publication types