The value of magnetic resonance enterography in diagnostic difficulties associated with Crohn’s disease

Abstract

IntroductionThe diagnosis of Crohn’s disease (CD), one of the inflammatory bowel diseases (IBD), along with ulcera­tive colitis (UC), is often challenging due to the limitations of small intestine visualisation. Magnetic resonance enterography (MRE) enables imaging of intraluminal and extraintestinal complications without ionizing radiation. The objective of this study is to select CD-related MRE features and determine the feasibility of this technique to indicate a group of patients that should be subjected to more invasive diagnostic procedures.Material and methodsA total of 131 patients (mean age 25) underwent MRE, 60 of whom had been previously diagnosed with CD and 17 with UC. Additionally, 26 patients with suspected IBD and 28 with other or unknown patholo­gies were included in the study. Radiological reports of MRE examinations, effectuated using a 1.5-T field strength, were retrospectively analysed regarding radiological features of IBD, such as the following: bowel wall thickening, enhancement, comb sign, stricture, enlarged mesenteric nodes, inflammatory infiltration, and abnormal diffusion restriction in diffusion-weighted imaging. The statistical model was based on machine learning of the Kohonen map, together with univariate and multivariate analysis.ResultsThe selected neuron (Neuron 3) incorporated 23 cases of CD, 9 of suspected IBD, 2 patients with UC, and 4 with other pathologies. The statistical analysis identified bowel wall thickening, intestinal stricture, and lymphadenopathy as the 3 MRE findings most associated with Neuron 3 (AUC = 0.919, p = 0.031).ConclusionsBowel wall thickening, stricture, and enlarged mesenteric lymph nodes in MRE are independent predictive factors for CD diagnosis; thus, patients presenting these features should undergo further examinations. MRE constitutes a powerful imaging modality in cases of suspected IBD.

A Systematic Review of Artificial Intelligence and Machine Learning Applications to Inflammatory Bowel Disease, with Practical Guidelines for Interpretation

“…Many articles trialed different ML methods before selecting the optimal one, and some researchers implemented ML for multiple IBD applications. Three main clinical application areas were identified: diagnosis (23%), 15 , 20–36 disease course (28%), 15 , 30 , 37–56 and disease severity (21%). 19 , 57–71 Diagnosis classification tasks involved differentiating IBD patients (or one subtype) from controls.…”

“… 23 , 29 , 45 , 59 , 61 , 66 , 73 Crohn’s disease data (only) was used in 27 studies, 12 , 17 , 19 , 26–29 , 32 , 37–39 , 41 , 44 , 47–50 , 58 , 60 , 63 , 65 , 74–79 and UC data (only) was used in 15 studies, 25 , 40 , 42 , 46 , 52 , 55 , 59 , 61 , 62 , 64 , 68–70 , 80 , 81 with the remainder ( n = 36) using a mix of CD and UC data, or IBD data as one class. 11 , 13–16 , 18 , 20–24 , 30 , 31 , 33–36 , 43 , 45 , 51 , 53 , 54 , 56 , 57 , 66 , 67 , 71–73 , 82–88 Half of the research using UC-only data focused on predicting disease activity with endoscopy data, whereas the aims of ML classifications on CD data were varied. A breakdown of the method and classification task can be found in Figure 3 , which can be customized here (isstafford.github.io/review_ml_ibd_2021/).…”

Advances in Imaging of Inflammation, Fibrosis, and Cancer in the Gastrointestinal Tract

“…In addition to endoscopy, CT enterography (CTE) is often used as a means of imaging IBD to identify increased thickening of the intestinal wall [11,41]. Similar parameters can also be measured using intestinal ultrasonography [76] and magnetic resonance enterography [77]. A recent development in the use of the latter involves utilization of very small superparamagnetic iron oxide nanoparticles (VSOPs) as a contrast agent to detect intestinal inflammation and extracellular matrix composition changes.…”