A scalable approach to T2-MRI colon segmentation

End to End Colonic Content Assessment: ColonMetry Application

The analysis of colonic contents is a valuable tool for the gastroenterologist and has multiple applications in clinical routine. When considering magnetic resonance imaging (MRI) modalities, T2 weighted images are capable of segmenting the colonic lumen, whereas fecal and gas contents can only be distinguished in T1 weighted images. In this paper, we present an end-to-end quasi-automatic framework that comprises all the steps needed to accurately segment the colon in T2 and T1 images and to extract colonic content and morphology data to provide the quantification of colonic content and morphology data. As a consequence, physicians have gained new insights into the effects of diets and the mechanisms of abdominal distension.

Colonic Volume Changes in Paediatric Constipation Compared to Normal Values Measured Using MRI

BACKGROUND

Functional constipation in children is common. Management of this condition can be challenging and is often based on symptom reports. Increased, objective knowledge of colonic volume changes in constipation compared to health could provide additional information. However, very little data on paediatric colonic volume is available except from methods that are invasive or require unphysiological colonic preparations.

OBJECTIVES

(1) To measure volumes of the undisturbed colon in children with functional constipation (FC) using magnetic resonance imaging (MRI) and provide initial normal range values for healthy controls, and (2) to investigate possible correlation of colonic volume with whole gut transit time (WGTT).

METHODS

Total and regional (ascending, transverse, descending, sigmoid, and rectum) colon volumes were measured from MRI images of 35 participants aged 7-18 years (16 with FC and 19 healthy controls), and corrected for body surface area. Linear regression was used to explore the relationship between total colon volume and WGTT.

RESULTS

Total colonic volume was significantly higher, with a median (interquartile range) of 309 mL (243-384 mL) for the FC group than for the healthy controls of 227 mL (180-263 mL). The largest increase between patients and controls was in the sigmoid colon-rectum region. In a linear regression model, there was a positive significant correlation between total colonic volume and WGTT (R = 0.56, p = 0.0005).

CONCLUSIONS

This initial study shows increased volumes of the colon in children with FC, in a physiological state, without use of any bowel preparation. Increased knowledge of colonic morphology may improve understanding of FC in this age group and help to direct treatment.

Gastrointestinal Contributions to the Postprandial Experience

Food ingestion induces homeostatic sensations (satiety, fullness) with a hedonic dimension (satisfaction, changes in mood) that characterize the postprandial experience. Both types of sensation are secondary to intraluminal stimuli produced by the food itself, as well as to the activity of the digestive tract. Postprandial sensations also depend on the nutrient composition of the meal and on colonic fermentation of non-absorbed residues. Gastrointestinal function and the sensitivity of the digestive tract, i.e., perception of gut stimuli, are determined by inherent individual factors, e.g., sex, and can be modulated by different conditioning mechanisms. This narrative review examines the factors that determine perception of digestive stimuli and the postprandial experience.

A Fully Automatic Procedure for Brain Tumor Segmentation from Multi-Spectral MRI Records Using Ensemble Learning and Atlas-Based Data Enhancement

The accurate and reliable segmentation of gliomas from magnetic resonance image (MRI) data has an important role in diagnosis, intervention planning, and monitoring the tumor’s evolution during and after therapy. Segmentation has serious anatomical obstacles like the great variety of the tumor’s location, size, shape, and appearance and the modified position of normal tissues. Other phenomena like intensity inhomogeneity and the lack of standard intensity scale in MRI data represent further difficulties. This paper proposes a fully automatic brain tumor segmentation procedure that attempts to handle all the above problems. Having its foundations on the MRI data provided by the MICCAI Brain Tumor Segmentation (BraTS) Challenges, the procedure consists of three main phases. The first pre-processing phase prepares the MRI data to be suitable for supervised classification, by attempting to fix missing data, suppressing the intensity inhomogeneity, normalizing the histogram of observed data channels, generating additional morphological, gradient-based, and Gabor-wavelet features, and optionally applying atlas-based data enhancement. The second phase accomplishes the main classification process using ensembles of binary decision trees and provides an initial, intermediary labeling for each pixel of test records. The last phase reevaluates these intermediary labels using a random forest classifier, then deploys a spatial region growing-based structural validation of suspected tumors, thus achieving a high-quality final segmentation result. The accuracy of the procedure is evaluated using the multi-spectral MRI records of the BraTS 2015 and BraTS 2019 training data sets. The procedure achieves high-quality segmentation results, characterized by average Dice similarity scores of up to 86%.