Validation of threshold values for pancreas thickness and T1-weighted signal intensity ratio in the pediatric pancreas

Current and emerging artificial intelligence applications for pediatric abdominal imaging

Artificial intelligence (AI) uses computers to mimic cognitive functions of the human brain, allowing inferences to be made from generally large datasets. Traditional machine learning (e.g., decision tree analysis, support vector machines) and deep learning (e.g., convolutional neural networks) are two commonly employed AI approaches both outside and within the field of medicine. Such techniques can be used to evaluate medical images for the purposes of automated detection and segmentation, classification tasks (including diagnosis, lesion or tissue characterization, and prediction), and image reconstruction. In this review article we highlight recent literature describing current and emerging AI methods applied to abdominal imaging (e.g., CT, MRI and US) and suggest potential future applications of AI in the pediatric population.

Magnetic resonance imaging glossary of findings of pediatric pancreatitis and the revised Atlanta classification

While still uncommon, the incidence of acute pancreatitis in children has been increasing over the last two decades. The Atlanta classification for acute pancreatitis, developed for adults, stratifies cases of acute pancreatitis based on imaging and clinical criteria. This classification scheme allows for standardized use of terminology to facilitate treatment and prognostication. Although US and CT should be used in critical or unstable patients, MRI is an ideal imaging modality in pediatric patients with acute pancreatitis because of its ability to characterize tissue without ionizing radiation. We review MRI examples specific to Atlanta classification terminology in pediatric patients. Chronic pancreatitis has also been increasingly diagnosed in children, and imaging plays a key role in the diagnosis and management of this insidious disease. MRI with magnetic resonance cholangiopancreatography is the optimal modality for assessing the pancreas in a child with known or suspected chronic pancreatitis because it provides tissue characterization and high-contrast imaging of the pancreatic duct without the use of invasive instrumentation or ionizing radiation. We also review and demonstrate accepted MRI findings of chronic pancreatitis.

Normal pancreatic thickness values in healthy children: an MRI study

INTRODUCTION

Normal pancreatic thickness values on ultrasound (US) have been defined in literature. However, there is insufficient information about normal pancreatic measurements acquired from computed tomography (CT) or magnetic resonance imaging (MRI). To define normal pancreatic thickness measurements acquired from different localizations in order to provide reference values for more objectively identified parenchymal thickness changes.

MATERIALS AND METHODS

A retrospective evaluation was made of the abdominal MRI examinations of 162 pediatric patients. Patients with any pancreatic disease, or chronic gastrointestinal inflammatory disease were excluded from the study. Measurements were taken from T2-weighted images.

RESULTS

Evaluation was made of 162 children, comprising 82 (50.6%) males and 80 (49.3%) females with a mean age of 9.8 ± 2.4 years. Mean pancreatic thickness was 18.3 ± 3.1 mm, 10.2 ± 2.9 mm, 14.9 ± 3 mm, 14.9 ± 3.3 mm in head, neck, body and tail localizations, accordingly. A positive correlation was determined between age, height, weight, body mass index (BMI) and pancreatic thickness in all the anatomic localizations (r > 0.55, p < 0.05). No significant difference was determined with gender. Interobserver agreement between two researchers was moderate and strong according to the different anatomic localizations.

CONCLUSIONS

The defined normal ranges are mostly consistent with previously published US and CT based values. Pancreatic thickness values were positively correlated with age, height, weight and BMI for all four anatomical regions of the pancreas. Knowledge of normal pancreatic thickness values will increase the diagnostic accuracy of radiologists in the assessment of pancreatic diseases and may aid in interpreting atrophy in the setting of chronic pancreatitis.

Current State of Imaging of Pediatric Pancreatitis: AJR Expert Panel Narrative Review

Pancreatitis is as common in children as it is in adults, though causes and accepted imaging strategies differ in children. In this narrative review we discuss the epidemiology of childhood pancreatitis and key imaging features for pediatric acute, acute recurrent, and chronic pancreatitis. We rely heavily on our collective experience in discussing advantages and disadvantages of different imaging modalities; practical tips for optimization of ultrasound, CT, and MRI with MRCP in children; and image interpretation pearls. Challenges and considerations unique to imaging pediatric pancreatitis are discussed, including timing of imaging, role of secretin-enhanced MRCP, utility of urgent MRI, severity prediction, autoimmune pancreatitis, and best methods for serial imaging. We suggest a methodical approach to pancreatic MRI interpretation in children and have included a sample structured report, and we provide consensus statements according to our experience imaging children with pancreatitis.