Improved detection of inflammatory bowel disease by additional automated motility analysis in magnetic resonance imaging. Invest Radiol. 2015;50:67-72. [PMID: 25260093 DOI: 10.1097/rli.0000000000000097]

AI-luminating Artificial Intelligence in Inflammatory Bowel Diseases: A Narrative Review on the Role of AI in Endoscopy, Histology, and Imaging for IBD

Endoscopy, histology, and cross-sectional imaging serve as fundamental pillars in the detection, monitoring, and prognostication of inflammatory bowel disease (IBD). However, interpretation of these studies often relies on subjective human judgment, which can lead to delays, intra- and interobserver variability, and potential diagnostic discrepancies. With the rising incidence of IBD globally coupled with the exponential digitization of these data, there is a growing demand for innovative approaches to streamline diagnosis and elevate clinical decision-making. In this context, artificial intelligence (AI) technologies emerge as a timely solution to address the evolving challenges in IBD. Early studies using deep learning and radiomics approaches for endoscopy, histology, and imaging in IBD have demonstrated promising results for using AI to detect, diagnose, characterize, phenotype, and prognosticate IBD. Nonetheless, the available literature has inherent limitations and knowledge gaps that need to be addressed before AI can transition into a mainstream clinical tool for IBD. To better understand the potential value of integrating AI in IBD, we review the available literature to summarize our current understanding and identify gaps in knowledge to inform future investigations.

Motility Mapping Quantification Using the Classical Optical Flow Algorithm for Small Bowel Crohn's Disease: Comparison with Balloon-assisted Enteroscopy Findings

PURPOSE

To quantify bowel motility shown on cine MRI using the classical optical flow algorithm and compare it with balloon-assisted enteroscopy (BAE) findings in patients with Crohn's disease (CD).

METHODS

This retrospective study included 29 consecutive patients with CD who had undergone MR enterocolonography (MREC) and BAE between March and May 2017. We developed computer software to present motion vector magnitudes between consecutive cine MR images as bowel motility maps via a classical optical flow algorithm using the Horn-Schunck method. Cine MR images were acquired with a balanced steady-state free precession sequence in the coronal direction to capture small bowel motility. The small bowels were divided into three segments. In total, 63 bowel segments were assessed via BAE and MREC. Motility scores on the maps, simplified MR index of activity (sMaRIA), and MREC score derived from a 5-point MR classification were assessed independently by two radiologists and compared with the CD endoscopic index of severity (CDEIS). Correlations were assessed using Spearman's rank coefficient. The areas under the receiver-operating characteristic curve (AUCs) of motility score for differentiating CDEIS was calculated; a P value < 0.05 was considered statistically significant.

RESULTS

Motility score was negatively correlated with CDEIS (r = -0.59 [P < 0.001] and -0.54 [P < 0.001]), and the AUCs of motility scores for detecting CDEIS ≥ 3 were 88.2% and 78.6% for observers 1 and 2, respectively. There were no significant differences in the AUC for detecting CDEIS ≥ 3 and CDEIS ≥ 12 between motility and sMaRIA or MREC score.

CONCLUSION

The motility map was feasible for locally quantifying the bowel motility. In addition, the motility score on the map reflected the endoscopic inflammatory activity of each small bowel segment in patients with CD; hence, it could be used as a tool in objectively interpreting cine MREC to predict inflammatory activity in CD.

The Role of Magnetic Resonance Enterography in Crohn’s Disease: A Review of Recent Literature

Inflammatory bowel disease (IBD) is the term used to identify a form of chronic inflammation of the gastrointestinal tract that primarily contemplates two major entities: ulcerative colitis (UC) and Crohn’s disease (CD). The classic signs are abdominal pain and diarrhoea that correlate with the localization of gastro-enteric disease, although in this pathology extraintestinal symptoms may coexist. The diagnosis of CD relies on a synergistic combination of clinical, laboratory (stool and biochemical), cross-sectional imaging evaluation, as well as endoscopic and histologic assessments. The purpose of this paper is to prove the role of imaging in the diagnosis and follow-up of patients with CD with particular focus on recent innovations of magnetic resonance enterography (MRE) as a pivotal diagnostic tool, analysing the MRE study protocol and imaging features during the various phases of disease activity and its complications.

Automatic detection of Crohn's disease using quantified motility in magnetic resonance enterography: initial experiences

AIM

To report initial experiences of automatic detection of Crohn's disease (CD) using quantified motility in magnetic resonance enterography (MRE).

MATERIALS AND METHODS

From 302 patients, three datasets with roughly equal proportions of CD and non-CD cases with various illnesses were drawn for testing and neural network training and validation. All datasets had unique MRE parameter configurations and were performed in free breathing. Nine neural networks were devised for automatic generation of three different regions of interests (ROI): small bowel, all bowel, and non-bowel. Additionally, a full-image ROI was tested. The motility in an MRE series was quantified via a registration procedure, which, accompanied with given ROIs, resulted in three motility indices (MI). A subset of the indices was used as an input for a binary logistic regression classifier, which predicted whether the MRE series represented CD.

RESULTS

The highest mean area under the curve (AUC) score, 0.78, was reached using the full-image ROI and with the dataset with the highest cine series length. The best AUC scores for the other two datasets were only 0.54 and 0.49.

CONCLUSION

The automatic system was able to detect CD in the group of MRE studies with lower temporal resolution and longer cine series showing potential in primary bowel disorder diagnostics. Larger ROI selections and utilising all available cine series for motility registration yielded slight performance improvements.

Simultaneous assessment of colon motility in children with functional constipation by cine-MRI and colonic manometry: a feasibility study

BACKGROUND

Colonic manometry is the current reference standard for assessing colonic neuromuscular function in children with intractable functional constipation (FC). Recently, cine magnetic resonance imaging (cine-MRI) has been proposed as a non-invasive alternative. We compared colonic motility patterns on cine-MRI with those obtained by manometry in children, by stimulating high-amplitude propagating contractions (HAPCs) with bisacodyl under manometric control while simultaneously acquiring cine-MRI.

METHODS

After Institutional Review Board approval, adolescents with FC scheduled to undergo colonic manometry were included. A water-perfused 8-lumen catheter was used for colonic manometry recordings. After an intraluminal bisacodyl infusion, cine-MRI sequences of the descending colon were acquired for about 30 min simultaneously with colonic manometry. Manometry recordings were analysed for HAPCs. MRI images were processed with spatiotemporal motility MRI techniques. The anonymised motility results of both techniques were visually compared for the identification of HAPCs in the descending colon.

RESULTS

Data regarding six patients (three males) were analysed (median age 14 years, range 12-17). After bisacodyl infusion, three patients showed a total of eleven HAPCs with colonic manometry. Corresponding cine-MRI recorded high colonic activity during two of these HAPCs, minimal activity during seven HAPCs, while two HAPCs were not recorded. In two of three patients with absent HAPCs on manometry, colonic activity was recorded with cine-MRI.

CONCLUSIONS

Simultaneous acquisition of colonic cine-MRI and manometry in children with FC is feasible. Their motility results did not completely overlap in the identification of HAPCs. Research is needed to unravel the role of cine-MRI in this setting.

Clinical-stage Approaches for Imaging Chronic Inflammation and Fibrosis in Crohn's Disease

The number of imaging-based indices developed for inflammatory bowel disease as research tools, objectively measuring ileocolonic and perianal activity and treatment response, has expanded in the past 2 decades. Created primarily to assess Crohn's disease (CD), there is increasing adoption of these indices into the clinical realm to guide patient care. This translation has been facilitated by validation in adult and pediatric populations, prompted by simplification of score calculations needed for practical application outside the research environment. The majority of these indices utilize magnetic resonance imaging (MRI), specifically MR enterography (MRE) and pelvic MRI, and more recently ultrasound. This review explores validated indices by modality, anatomic site and indication, including for documentation of the presence and extent of CD, disease progression, complications, and treatment response, highlighting those in clinical use or with the potential to be. As well, it details index imaging features used to quantify chronic inflammatory activity, severity, and to lesser extent fibrosis, in addition to their reference standards and any modifications. Validation in the pediatric population of indices primarily developed in adult cohorts such as the Magnetic Resonance Index of Activity (MaRIA), the Simplified Magnetic Resonance Index of Activity (MARIAs), and the MRE global score (MEGS), together with newly developed pediatric-specific indices, are discussed. Indices that may be predictive of disease course and investigational techniques with the potential to provide future imaging biomarkers, such as multiparametric MRI, are also briefly considered.

Improved Peritoneal Cavity and Abdominal Organ Imaging Using a Biphasic Contrast Agent Protocol and Spectral Photon Counting Computed Tomography K-Edge Imaging

OBJECTIVES

To validate in vitro the capability of a high-spatial-resolution prototype spectral photon-counting computed tomography (SPCCT) scanner to differentiate between 2 contrast agents and to assess in vivo the image quality and the feasibility to image the peritoneal cavity in rats using the 2 contrast agents simultaneously within the vascular and peritoneal compartments.

MATERIALS AND METHODS

The authors performed SPCCT imaging (100 mAs, 120 kVp) with energy bin thresholds set to 30, 51, 64, 72, and 85 keV in vitro on a custom-made polyoxymethylene cylindrical phantom consisting of tubes with dilutions of both contrast agents and in vivo on 2 groups of adult rats using 2 injection protocols. Approval from the institutional animal ethics committee was obtained. One group received macrocylic gadolinium chelate intraperitoneal (IP) and iodine intravenous (IV) injections (protocol A, n = 3), whereas the second group received iodine IP and gadolinium IV (protocol B, n = 3). Helical scans were performed 35 minutes after IP injection and 20 seconds after IV injection. The SPCCT and contrast material images, that is, iodine and gadolinium maps, were reconstructed with a field of view of 160 mm, an isotropic voxel size of 250 μm, and a matrix size of 640 × 640 pixels using a soft reconstruction kernel. The SPCCT images were reconstructed with 2 different spatial resolutions to compare the image quality (sharpness, diagnostic quality, and organ visualization) of SPCCT (250 μm) with single-energy computed tomography (CT) (600 μm). Two radiologists evaluated the peritoneal opacification index in 13 regions (score = 0-3 per region) on each type of image. Concentrations of contrast agents were measured in the organs of interest.

RESULTS

In vitro, the concentration measurements correlated well with the expected concentrations. The linear regressions both had R values of 0.99, slopes of 0.84 and 0.87, and offsets at -0.52 and -0.38 mg/mL for iodine and gadolinium, respectively. In vivo, the SPCCT images were of better diagnostic quality, with increased sharpness compared with the CT-like images (P < 0.0001). Intraperitoneal diffusion was excellent, with similar peritoneal opacification index on SPCCT images and overlay of contrast material maps (P = 1) without a significant difference between protocol A (37.0 ± 1.7) and protocol B (35.3 ± 1.5) (P = 0.34). Only the contrast material maps demonstrated clear visual separation of the contrast agents, allowing specific quantification of the physiological enhancement in the liver, spleen, and kidney and the urinary clearance in the renal pelvis and bladder. Renal excretion of the contrast agents injected IP was observed and was consistent with blood diffusion.

CONCLUSIONS

Spectral photon-counting CT can be used to perform a complete peritoneal dual-contrast protocol, enabling a good assessment of the peritoneal cavity and abdominal organs in rats.

Spatio-temporal motility MRI analysis of the stomach and colon

BACKGROUND

MRI is increasingly used to objectively assess gastrointestinal motility. However, motility metrics often do not offer insights into the nature of contractile action. This study introduces a systematic method of making spatio-temporal measurements of contractions, based on changes in bowel lumen diameter.

METHODS

Two heterogeneous cohorts of subjects were selected displaying gastric (n = 15) and colonic motility (n = 20) on which to test the spatio-temporal motility MRI (STMM) technique. STMM involved delineating the bowel lumen along with inner and outer bowel wall along a section of the gastrointestinal tract. A series of diameter measurements were made automatically across the central axis of the lumen. Measurements were automatically propagated through the time series using a previously validated algorithm. Contractions were quantitatively summarized with two methods measuring (a) normalized contraction plot (NCP) and (b) combined velocity distance (CVD) both of which can be visualized as spatio-temporal motility maps. Both metrics were correlated against subjective visual scoring systems.

KEY RESULTS

Good correlation was seen between reader scores and both motility metrics (NCP, R = 0.85, P < 0.001, CVD, R = 0.93, R < 0.001) in the gastric data. Good correlation was also seen between the reader scores and the two metrics in the colonic data (NCP, R = 0.82, P < 0.001, CVD, R = 0.78, R < 0.001).

CONCLUSIONS AND INFERENCES

Spatio-temporal motility MRI analysis of the stomach and colon correlates well with reader scores in a range of datasets and provides both a quantitative and qualitative means of assessing contractile activity in the gastrointestinal tract.

Detecting the effects of a standardized meal challenge on small bowel motility with MRI in prepared and unprepared bowel

OBJECTIVE

MRI is increasingly used to evaluate small bowel contractility. The objective of this study was to validate a clinically practical stimulation test (300-kcal meal) for small bowel motility.

METHODS

Thirty-one healthy subjects underwent dynamic MRI to capture global small bowel motility after ±10h fasting, of which 15 underwent bowel preparation consisting of 1 L 2.5% mannitol solution and 16 did not. Each subject underwent (1) a baseline motility scan (2) a food challenge (3) a post-challenge scan, and (4) second post-challenge scan (after ±20 minutes). This protocol was repeated within 2 weeks. Motility was quantified using a validated motility assessment technique.

KEY RESULTS

Motility in prepared subjects at baseline was significantly higher than motility in unprepared subjects (0.36 AU vs 0.18 AU, P < 0.001). In the prepared group, the food challenge produced an 8% increase in motility (P = 0.33) while in the unprepared subjects a significant increase of 30% was observed (P < 0.001). Responses to food remained insignificant (P = 0.21) and significant (P = 0.003), for the prepared and unprepared subjects, respectively, ±20 minutes post food challenge. These results were confirmed in the repeated scan session.

CONCLUSION & INFERENCES

A significant response to a 300-kcal meal was measured within 10 minutes in unprepared bowel, supporting the clinical use of this challenge to provoke and assess motility changes. A caloric challenge did not produce an observable increase in motility in mannitol prepared subjects.

Evaluation of gastrointestinal motility with MRI: Advances, challenges and opportunities

Dynamic magnetic resonance imaging (MRI) of gastrointestinal motility has developed rapidly over the past few years. The non-invasive and non-ionizing character of MRI is an important advantage together with the fact that it is fast and can visualize the entire gastrointestinal tract. Advances in imaging and quantification techniques have facilitated assessment of gastric, small intestinal, and colonic motility in a clinical setting. Automated quantitative motility assessment using dynamic MRI meets the need for non-invasive techniques. Recently, studies have begun to examine this technique in patients, including those with IBD, pseudo-obstruction and functional bowel disorders. Remaining challenges for clinical implementation are processing the large amount of data, standardization and validation of the numerous MRI metrics and subsequently assessment of the potential role of dynamic MRI. This review examines the methods, advances, and remaining challenges of evaluation of gastrointestinal motility with MRI. It accompanies an article by Khalaf et al. in this journal that describes a new protocol for assessment of pan-intestinal motility in fasted and fed state in a single MRI session.

The first joint ESGAR/ ESPR consensus statement on the technical performance of cross-sectional small bowel and colonic imaging

Objectives

To develop guidelines describing a standardised approach to patient preparation and acquisition protocols for magnetic resonance imaging (MRI), computed tomography (CT) and ultrasound (US) of the small bowel and colon, with an emphasis on imaging inflammatory bowel disease.

Methods

An expert consensus committee of 13 members from the European Society of Gastrointestinal and Abdominal Radiology (ESGAR) and European Society of Paediatric Radiology (ESPR) undertook a six-stage modified Delphi process, including a detailed literature review, to create a series of consensus statements concerning patient preparation, imaging hardware and image acquisition protocols.

Results

One hundred and fifty-seven statements were scored for agreement by the panel of which 129 statements (82 %) achieved immediate consensus with a further 19 (12 %) achieving consensus after appropriate modification. Nine (6 %) statements were rejected as consensus could not be reached.

Conclusions

These expert consensus recommendations can be used to help guide cross-sectional radiological practice for imaging the small bowel and colon.

Key points

• Cross-sectional imaging is increasingly used to evaluate the bowel

• Image quality is paramount to achieving high diagnostic accuracy

• Guidelines concerning patient preparation and image acquisition protocols are provided

Role of imaging in the evaluation of inflammatory bowel disease: How much is too much?

Inflammatory bowel disease (IBD) is a lifelong condition with waxing and waning disease course that requires reassessment of disease status as well as screening for complications throughout a patient’s lifetime. Laboratory testing, endoscopic assessment, and fecal biomarkers are often used in the initial diagnosis and ongoing monitoring of a patient with IBD. Imaging plays an integral role in the diagnosis and evaluation of IBD. Different imaging modalities can be used over the course of a patient’s lifetime, from the initial screening and diagnosis of IBD, to determining the extent of intestinal involvement, monitoring for disease activity, and evaluating for complications of uncontrolled IBD. The various imaging modalities available to the provider each have a unique set of risks and benefits when considering cost, radiation exposure, need for anesthesia, and image quality. In this article we review the imaging techniques available for the evaluation of IBD including fluoroscopic small bowel follow-through, computed tomography enterography, magnetic resonance enterography, and transabdominal ultrasound with particular focus on the judicious use of imaging and the risks and benefits of each option. We also review the risks of ionizing radiation, strategies to reduce exposure to ionizing radiation, and current imaging guidelines among pediatric and adult patient with IBD.

Non-enhanced magnetic resonance imaging of the small bowel at 7 Tesla in comparison to 1.5 Tesla: First steps towards clinical application

OBJECTIVE

To perform non-enhanced (NE) magnetic resonance imaging (MRI) of the small bowel at 7 Tesla (7T) and to compare it with 1.5 Tesla (1.5T).

MATERIAL AND METHODS

Twelve healthy subjects were prospectively examined using a 1.5T and 7T MRI system. Coronal and axial true fast imaging with steady-state precession (TrueFISP) imaging and a coronal T2-weighted (T2w) half-Fourier acquisition single-shot turbo spin-echo (HASTE) sequence were acquired. Image analysis was performed by 1) visual evaluation of tissue contrast and detail detectability, 2) measurement and calculation of contrast ratios and 3) assessment of artifacts.

RESULTS

NE MRI of the small bowel at 7T was technically feasible. In the vast majority of the cases, tissue contrast and image details were equivalent at both field strengths. At 7T, two cases revealed better detail detectability in the TrueFISP, and better contrast in the HASTE. Susceptibility artifacts and B1 inhomogeneities were significantly increased at 7T.

CONCLUSION

This study provides first insights into NE ultra-high field MRI of the small bowel and may be considered an important step towards high quality T2w abdominal imaging at 7T MRI.

Magnetic resonance imaging to evaluate gastrointestinal function

Magnetic resonance imaging of gastrointestinal (GI) function has advanced substantially in the last few years. The ability to obtain high resolution images of the undisturbed bowel with tunable tissue contrast and using no ionizing radiation are clear advantages, particularly for children and women of reproductive age. Barriers to diffusion in clinical practice so far include the need to demonstrate clinical value and the burden of data processing. Both difficulties are being addressed and the technique is providing novel insights into both upper and lower GI disorders of function at an ever increasing rate.

Magnetic resonance imaging biomarkers of gastrointestinal motor function and fluid distribution

Magnetic resonance imaging (MRI) is a well established technique that has revolutionized diagnostic radiology. Until recently, the impact that MRI has had in the assessment of gastrointestinal motor function and bowel fluid distribution in health and in disease has been more limited, despite the novel insights that MRI can provide along the entire gastrointestinal tract. MRI biomarkers include intestinal motility indices, small bowel water content and whole gut transit time. The present review discusses new developments and applications of MRI in the upper gastrointestinal tract, the small bowel and the colon reported in the literature in the last 5 years.

Quantitative assessment of small bowel motility in patients with Crohn's disease using dynamic MRI

BACKGROUND

Assessment of motility alterations by functional magnetic resonance imaging (MRI) contributes to improved evaluation of inflammatory bowel disease. The aim of the study was to quantify motility in inflammatory bowel segments and to compare motility alterations with MR-based parameters for activity of inflammation in Crohn's disease (CD).

METHODS

Thirty consecutive patients with CD underwent bowel MRI which included a dynamic sequence for automatic generation of parametric maps facilitating quantification of bowel motility. Mean motility score (MMS) of small bowel segments with signs of inflammation was measured and compared with MMS of the whole gastrointestinal tract (GI tract). MRI-based score of inflammatory activity and lesion length were correlated with the MMS ratio of inflammatory small bowel lesion and whole GI tract.

KEY RESULTS

Inflammatory bowel segments showed a mean value of MMSs of 1080, whereas the whole GI tract showed a mean value of MMSs of 2839 (p < 0.0001). Decrease in motility ranged between 20 and 87% in inflammatory bowel segments compared to the MMS of the whole GI tract. The MMS ratio of an inflammatory small bowel segment and whole GI tract showed negative correlation with MR activity score (r = -0.5921, p = 0.0003) and length of the lesion (r = -0.3495, p = 0.0462).

CONCLUSIONS & INFERENCES

Quantitative assessment of motility alterations by means of motility scoring in small bowel segments affected by CD provides additional information on inflammatory activity.