Dataset Information

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

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.

SUBMITTER: Roger R

PROVIDER: S-EPMC8734282 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Roger Raphael R Hilmes Melissa A MA Williams Jonathan M JM Moore Daniel J DJ Powers Alvin C AC Craddock R Cameron RC Virostko John J

BMC medical imaging 20220105 1

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 convolut ...[more]

PMID: 34986790

Similar Datasets

Project description:ObjectiveAlthough impairment in pancreatic insulin secretion is known to precede the clinical diagnosis of type 2 diabetes by up to a decade, fasting blood glucose concentration only rises abnormally once the impairment reaches a critical threshold. Despite its centrality to the pathogenesis of type 2 diabetes, the pancreas is the least studied organ due to its inaccessible anatomical position. Previous ultrasound and CT studies have suggested a possible decrease in pancreatic volume in type 2 diabetes. However, ultrasound techniques are relatively insensitive while CT uses ionizing radiation, making these modalities unsuitable for precise, longitudinal studies designed to explore the underlying mechanisms of type 2 diabetes. Hence there is a need to develop a non-invasive, safe and precise method to quantitate pancreas volume.MethodsWe developed and applied magnetic resonance imaging at 3.0T to obtain balanced turbo field echo (BTFE) structural images of the pancreas, together with 3-point Dixon images to quantify pancreatic triglyceride content. Pancreas volume, morphology and triglyceride content was quantified in a group of 41 subjects with well-controlled type 2 diabetes (HbA1c ≤ 7.6%) taking only metformin (duration of T2DM 5.7 ± 0.7 years), and a control group of 14 normal glucose tolerance subjects matched for age, weight and sex.ResultsThe mean pancreatic volume was found to be 33% less in type 2 diabetes than in normal glucose tolerant subjects (55.5 ± 2.8 vs. 82.6 ± 4.8 cm3; p < 0.0001). Pancreas volume was positively correlated with HOMA-β in the type 2 diabetes subjects (r = 0.31; p = 0.03) and controls (r = 0.46; p = 0.05) considered separately; and in the whole population studied (r = 0.37; p = 0.003). In type 2 diabetes, the pancreas was typically involuted with a serrated border. Pancreatic triglyceride content was 23% greater (5.4 ± 0.3 vs. 4.4 ± 0.4%; p = 0.02) in the type 2 diabetes group.ConclusionThis study describes for the first time gross abnormalities of the pancreas in early type 2 diabetes and quantifies the decrease in pancreas size, the irregular morphology and increase in fat content.

Project description:BackgroundMany scholars have proven cervical vertebral maturation (CVM) method can predict the growth and development and assist in choosing the best time for treatment. However, assessing CVM is a complex process. The experience and seniority of the clinicians have an enormous impact on judgment. This study aims to establish a fully automated, high-accuracy CVM assessment system called the psc-CVM assessment system, based on deep learning, to provide valuable reference information for the growth period determination.MethodsThis study used 10,200 lateral cephalograms as the data set (7111 in train set, 1544 in validation set and 1545 in test set) to train the system. The psc-CVM assessment system is designed as three parts with different roles, each operating in a specific order. 1) Position Network for locating the position of cervical vertebrae; 2) Shape Recognition Network for recognizing and extracting the shapes of cervical vertebrae; and 3) CVM Assessment Network for assessing CVM according to the shapes of cervical vertebrae. Statistical analysis was conducted to detect the performance of the system and the agreement of CVM assessment between the system and the expert panel. Heat maps were analyzed to understand better what the system had learned. The area of the third (C3), fourth (C4) cervical vertebrae and the lower edge of second (C2) cervical vertebrae were activated when the system was assessing the images.ResultsThe system has achieved good performance for CVM assessment with an average AUC (the area under the curve) of 0.94 and total accuracy of 70.42%, as evaluated on the test set. The Cohen's Kappa between the system and the expert panel is 0.645. The weighted Kappa between the system and the expert panel is 0.844. The overall ICC between the psc-CVM assessment system and the expert panel was 0.946. The F1 score rank for the psc-CVM assessment system was: CVS (cervical vertebral maturation stage) 6 > CVS1 > CVS4 > CVS5 > CVS3 > CVS2.ConclusionsThe results showed that the psc-CVM assessment system achieved high accuracy in CVM assessment. The system in this study was significantly consistent with expert panels in CVM assessment, indicating that the system can be used as an efficient, accurate, and stable diagnostic aid to provide a clinical aid for determining growth and developmental stages by CVM.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets