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

BMC Medical Imaging

R. Cameron Craddock¹  Raphael Roger¹  John Virostko²  Daniel J. Moore³  Melissa A. Hilmes⁴  Jonathan M. Williams⁵  Alvin C. Powers⁶ 

[1] Department of Diagnostic Medicine, Dell Medical School, University of Texas at Austin, 1701 Trinity St., Stop C0200, 78712, Austin, TX, USA;Department of Diagnostic Medicine, Dell Medical School, University of Texas at Austin, 1701 Trinity St., Stop C0200, 78712, Austin, TX, USA;Livestrong Cancer Institutes, University of Texas at Austin, Austin, TX, USA;Department of Oncology, University of Texas at Austin, Austin, TX, USA;Oden Institute for Computational Engineering and Sciences, University of Texas at Austin, Austin, TX, USA;Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN, USA;Department of Pathology, Immunology, and Microbiology, Vanderbilt University, Nashville, TN, USA;Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN, USA;Department of Pediatrics, Vanderbilt University Medical Center, Nashville, TN, USA;Division of Diabetes, Endocrinology, and Metabolism, Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA;Division of Diabetes, Endocrinology, and Metabolism, Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA;Department of Molecular Physiology and Biophysics, Vanderbilt University, Nashville, TN, USA;VA Tennessee Valley Healthcare System, Nashville, TN, USA;

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

DOI  :  10.1186/s12880-021-00729-7

来源: Springer

【 摘 要 】

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.

【 授权许可】

CC BY