RESUMEN

Background Clinical decision making and drug development for fibrostenosing Crohn disease is constrained by a lack of imaging definitions, scoring conventions, and validated end points. Purpose To assess the reliability of MR enterography features to describe Crohn disease strictures and determine correlation with stricture severity. Materials and Methods A retrospective study of patients with symptomatic terminal ileal Crohn disease strictures who underwent MR enterography at tertiary care centers (Cleveland Clinic: September 2013 to November 2020; Mayo Clinic: February 2008 to March 2019) was conducted by using convenience sampling. In the development phase, blinded and trained radiologists independently evaluated 26 MR enterography features from baseline and follow-up examinations performed more than 6 months apart, with no bowel resection performed between examinations. Follow-up examinations closest to 12 months after baseline were selected. Reliability was assessed using the intraclass correlation coefficient (ICC). In the validation phase, after five features were redefined, reliability was re-estimated in an independent convenience sample using baseline examinations. Multivariable linear regression analysis identified features with at least moderate interrater reliability (ICC ≥0.41) that were independently associated with stricture severity. Results Ninety-nine (mean age, 40 years ± 14 [SD]; 50 male) patients were included in the development group and 51 (mean age, 45 years ± 16 [SD]; 35 female) patients were included in the validation group. In the development group, nine features had at least moderate interrater reliability. One additional feature demonstrated moderate reliability in the validation group. Stricture length (ICC = 0.85 [95% CI: 0.75, 0.91] and 0.91 [95% CI: 0.75, 0.96] in development and validation phase, respectively) and maximal associated small bowel dilation (ICC = 0.74 [95% CI: 0.63, 0.80] and 0.73 [95% CI: 0.58, 0.87] in development and validation group, respectively) had the highest interrater reliability. Stricture length, maximal stricture wall thickness, and maximal associated small bowel dilation were independently (regression coefficients, 0.09-3.97; P < .001) associated with stricture severity. Conclusion MR enterography definitions and scoring conventions for reliably assessing features of Crohn disease strictures were developed and validated, and feature correlation with stricture severity was determined. © RSNA, 2024 Supplemental material is available for this article. See also the article by Rieder and Ma et al in this issue. See also the editorial by Galgano and Summerlin in this issue.

Asunto(s)

RESUMEN

Background Standardized methods to measure and describe Crohn disease strictures at CT enterography are needed to guide clinical decision making and for use in therapeutic studies. Purpose To assess the reliability of CT enterography features to describe Crohn disease strictures and their correlation with stricture severity. Materials and Methods A retrospective study was conducted in 43 adult patients with symptomatic terminal ileal Crohn disease strictures who underwent standard-of-care CT enterography at a tertiary care center at the Cleveland Clinic between January 2008 and August 2016. After training on standardized definitions, four abdominal radiologists blinded to all patient information assessed imaging features (seven continuous measurements and nine observations) of the most distal ileal stricture in two separate sessions (separated by ≥2 weeks) in random order. Features with an interrater intraclass correlation coefficient (ICC) of 0.41 or greater (ie, moderate reliability or better) were considered reliable. Univariable and multivariable linear regression analysis identified reliable features associated with a visual analog scale of overall stricture severity. Significant reliable features were assessed as components of a CT enterography-based model to quantitate stricture severity. Results Examinations in 43 patients (mean age, 52 years ± 16 [SD]; 23 female) were evaluated. Five continuous measurements and six observations demonstrated at least moderate interrater reliability (interrater ICC range, 0.42 [95% CI: 0.25, 0.57] to 0.80 [95% CI: 0.67, 0.88]). Of these, 10 were univariably associated with stricture severity, and three continuous measurements-stricture length (interrater ICC, 0.64 [95% CI: 0.42, 0.81]), maximal associated small bowel dilation (interrater ICC, 0.80 [95% CI: 0.67, 0.88]), and maximal stricture wall thickness (interrater ICC, 0.50 [95% CI: 0.34, 0.62])-were independently associated (P value range, <.001 to .003) with stricture severity in a multivariable model. These three measurements were used to derive a well-calibrated (optimism-adjusted calibration slope = 1.00) quantitative model of stricture severity. Conclusion Standardized CT enterography measurements and observations can reliably describe terminal ileal Crohn disease strictures. Stricture length, maximal associated small bowel dilation, and maximal stricture wall thickness are correlated with stricture severity. © RSNA, 2024 Supplemental material is available for this article. See also the article by Rieder et al in this issue. See also the editorial by Galgano and Summerlin in this issue.

Asunto(s)

RESUMEN

BACKGROUND/AIMS:  The purpose of this study was to investigate whether computed tomography enterography can be used to predict the presence of perianal fistula in Crohn's disease patients. MATERIALS AND METHODS:  According to the presentation of perianal fistula or not, this study divided retrospectively included Crohn's disease patients into 2 groups. The disease duration, incidence of involved intestinal segments, and scoring of the activity of the lesions in all patients were statistically analyzed to explore significant factors between the 2 groups. The statistically significant findings identified in the univariate analysis were incorporated into the multivariate analysis. Logistic regression models were subsequently constructed to assess the predictive factors associated with the occurrence of perianal fistula in individuals with Crohn's disease.The contribution of each factor to the outcome variable was confirmed by the nomogram. The clinical utility of the nomogram was confirmed by calibration and decision curves. RESULTS:  There were 40 cases with perianal Crohn's disease and 58 without perianal Crohn's disease. After univariate and multivariate analysis, disease duration (early stage of Crohn's disease), ascending colon, and rectum were identified as the independent predictive factors for perianal fistula in Crohn's disease patients. The clinical utility of the nomogram was effective, which implied potential benefits for Crohn's disease patients. CONCLUSION:  Computed tomography enterography can be used to predict the presence of perianal fistula in Crohn's disease patients by analyzing the location and the stage of the disease.

Asunto(s)

RESUMEN

BACKGROUND: Crohn's disease (CD) is a chronic inflammatory disease of the digestive tract with unknown etiology. It follows a relapse-remission pattern, making disease activity assessment crucial for treatment. Our study aims to evaluate the diagnostic accuracy of various imaging modalities and to validate and compare the International Bowel Ultrasound Segmental Activity Score (IBUS-SAS), the multidetector computed tomography enterography score (MDCTEs), and the simplified endoscopic activity score for Crohn's disease (SES-CD). METHODS: We assessed diagnostic performance using the CD Activity Index (CDAI). We first categorized patients into remission and active groups. For those in the active stage, we further categorized them into mild/moderate and severe activity groups. We used Spearman rank correlation to evaluate the relationships among IBUS-SAS, bowel wall thickness (BWT), Color Doppler imaging signal (CDS), inflammatory fat (i-fat), bowel wall stratification (BWS), and clinical inflammatory indicators. RESULTS: A total of 103 CD patients were evaluated. The IBUS-SAS cut-off for remission and activity was 23.8, with an AUC of 0.923, sensitivity of 91.4%, and specificity of 84.8%. The SES-CD had an AUC of 0.801, sensitivity of 62.9%, and specificity of 84.4% at a cut-off of 4.5. The MDCTEs showed an AUC of 0.855, sensitivity of 77.1%, and specificity of 75.8% for a cut-off of 6.5. The Delong test revealed significant differences in diagnostic efficacy when comparing IBUS-SAS to SES-CD and IBUS-SAS to MDCTEs. In the group of mild or moderate-to-severe active, the IBUS-SAS had an AUC of 0.925, sensitivity of 83.7%, and specificity of 88.9% at a cut-off of 40. The SES-CD exhibited an AUC of 0.850, sensitivity of 90.7%, and specificity of 70.4% at a cut-off of 8.5. MDCTEs showed an AUC of 0.909, sensitivity of 83.7%, and specificity of 85.2% at a cut-off of 8.5. During Delong test, the IBUS-SAS, MDCTEs, and SES-CD showed no significant differences in assessing moderate-to-severe activity. Both IBUS-SAS and ultrasound parameters correlated with certain serum indicators (p < 0.05), although only weakly to moderately (all r < 0.5). CONCLUSION: The IBUS-SAS, MDCTEs and SES-CD can evaluate disease remission/active and mild/moderate-to-severe active in CD, and IBUS-SAS offers the potential to precisely define CD activity.

Asunto(s)

Asunto(s)

RESUMEN

BACKGROUND: Point-of-care ultrasound (POCUS) has transformed inflammatory bowel disease (IBD) management, but the cost to purchase high-end equipment can be prohibitive. AIM: To assess prospectively the feasibility of POCUS using pre-existing mid-end ultrasound equipment without incurring additional cost. METHODS: Consecutive IBD patients underwent POCUS with or without faecal calprotectin (FCP) using a mid-end ultrasound machine. If POCUS with or without FCP could not guide management, we performed additional ileocolonoscopy or cross-sectional imaging. We evaluated the impact of POCUS on IBD management and its correlation with ileocolonoscopy or cross-sectional imaging. We analysed pregnant, paediatric and post-operative patients separately. RESULTS: Among 508 patients with IBD, we analysed 419 (60.4% Crohn's disease [CD]; 61.3% male, age [years]: 36 [18-78]) undergoing 556 POCUS sessions. POCUS with or without FCP independently influenced clinical management in 42.8% of patients with CD and 49.7% with ulcerative colitis (UC). POCUS helped avoid colonoscopy in 51.4% of patients with CD and 51.8% with UC, and cross-sectional imaging in 38.1% of suspected active small bowel CD. In patients with additional diagnostics, POCUS-based decisions remained unchanged in 81.2% with CD and 85% with UC. Sensitivity and specificity of POCUS compared to ileocolonoscopy were 80% and 94.4% for CD and 80.8% and 92.8% for UC, respectively. Sensitivity and specificity compared to cross-sectional imaging were 87.2% and 87.5%, respectively. CONCLUSION: POCUS using existing mid-end ultrasound equipment in low-resource settings influenced IBD clinical decision-making with excellent accuracy, often avoiding colonoscopy and cross-sectional imaging.

Asunto(s)

RESUMEN

PURPOSE: Qualitative findings in Crohn's disease (CD) can be challenging to reliably report and quantify. We evaluated machine learning methodologies to both standardize the detection of common qualitative findings of ileal CD and determine finding spatial localization on CT enterography (CTE). MATERIALS AND METHODS: Subjects with ileal CD and a CTE from a single center retrospective study between 2016 and 2021 were included. 165 CTEs were reviewed by two fellowship-trained abdominal radiologists for the presence and spatial distribution of five qualitative CD findings: mural enhancement, mural stratification, stenosis, wall thickening, and mesenteric fat stranding. A Random Forest (RF) ensemble model using automatically extracted specialist-directed bowel features and an unbiased convolutional neural network (CNN) were developed to predict the presence of qualitative findings. Model performance was assessed using area under the curve (AUC), sensitivity, specificity, accuracy, and kappa agreement statistics. RESULTS: In 165 subjects with 29,895 individual qualitative finding assessments, agreement between radiologists for localization was good to very good (κ = 0.66 to 0.73), except for mesenteric fat stranding (κ = 0.47). RF prediction models had excellent performance, with an overall AUC, sensitivity, specificity of 0.91, 0.81 and 0.85, respectively. RF model and radiologist agreement for localization of CD findings approximated agreement between radiologists (κ = 0.67 to 0.76). Unbiased CNN models without benefit of disease knowledge had very similar performance to RF models which used specialist-defined imaging features. CONCLUSION: Machine learning techniques for CTE image analysis can identify the presence, location, and distribution of qualitative CD findings with similar performance to experienced radiologists.

Asunto(s)

RESUMEN

INTRODUCTION: Stricture is a common complication in Crohn's disease (CD). Accurate identification of strictures that poorly respond to biologic therapy is essential for making optimal therapeutic decisions. The aim of this study was to determine the association between ultrasound characteristics of strictures and their therapeutic outcomes. METHODS: Consecutive CD patients with symptomatic strictures scheduled for biologic therapy were retrospectively recruited at a tertiary hospital. Baseline intestinal ultrasound was conducted to assess stricture characteristics, including bowel wall thickness, length, stratification, vascularity, and creeping fat wrapping angle. Patients were followed up for a minimum of 1 year, during which long-term outcomes including surgery, steroid-free clinical remission, and mucosal healing were recorded. Statistical analyses were performed. RESULTS: A total of 43 patients were enrolled. Strictures were located in the ileocecal region (39.5%), colon (37.2%), anastomosis (20.9%), and small intestine (2.3%). The median follow-up time was 17 months (interquartile range 7-25), with 27 patients (62.8%) undergoing surgery. On multivariant analysis, creeping fat wrapping angle > 180° (odds ratio: 6.2, 95% confidence interval [CI]: 1.1-41.1) and a high Limberg score (odds ratio: 2.3, 95% CI: 1.4-6.0) were independent predictors of surgery, with an area under the curve of 0.771 (95% CI: 0.602-0.940), accuracy of 83.7%, sensitivity of 96.3%, and specificity of 62.5%. On Cox survival analysis, creeping fat >180° was significantly associated with surgery (hazard ratio, 5.2; 95% CI: 1.2-21.8; P = 0.03). In addition, creeping fat was significantly associated with steroid-free clinical remission ( P = 0.015) and mucosal healing ( P = 0.06). DISCUSSION: Intestinal ultrasound characteristics can predict outcomes in patients with stricturing CD who undertook biologic therapy.

Asunto(s)

RESUMEN

OBJECTIVE: To demonstrate the value of using 50 keV virtual monochromatic images with deep learning image reconstruction (DLIR) in low-dose dual-energy CT enterography (CTE). METHODS: In this prospective study, 114 participants (62 % M; 41.9 ± 16 years) underwent dual-energy CTE. The early-enteric phase was performed using standard-dose (noise index (NI): 8) and images were reconstructed at 70 keV and 50 keV with 40 % strength ASIR-V (ASIR-V40%). The late-enteric phase used low-dose (NI: 12) and images were reconstructed at 50 keV with ASIR-V40%, and DLIR at medium (DLIR-M) and high strength (DLIR-H). Image standard deviation (SD), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), edge-rise-slope (ERS) were computed. The quantitative comb sign score was calculated for the 27 patients with Crohn's disease. The subjective noise, image contrast, display of rectus artery were scored using a 5-point scale by two radiologists blindly. RESULTS: Effective dose was reduced by 50 % (P < 0.001) in the late-enteric phase to 3.26 mSv. The lower-dose 50 keV-DLIR-H images (SD:17.7 ± 0.5HU) had similar image noise (P = 0.97) as the standard-dose 70 keV-ASIR-V40% images (SD:17.7 ± 0.73HU), but with higher (P < 0.001) SNR, CNR, ERS and quantitative comb sign score (5.7 ± 0.17, 1.8 ± 0.12, 156.04 ± 5.21 and 5.05 ± 0.73, respectively). Furthermore, the lower-dose 50 keV-DLIR-H images obtained the highest score in the rectus artery visibility (4.27 ± 0.6). CONCLUSIONS: The 50 keV images in dual-energy CTE with DLIR provides high-quality images, with a 50 % reduction in radiation dose. Images with high contrast and density resolutions significantly enhance the diagnostic confidence of Crohn's disease and are essential for the clinical development of individualized treatment plans.

Asunto(s)

RESUMEN

BACKGROUND: Due to similar clinical manifestations and imaging signs, differential diagnosis of primary intestinal lymphoma (PIL) and Crohn's disease (CD) is a challenge in clinical practice. AIM: To investigate the ability of radiomics combined with machine learning methods to differentiate PIL from CD. METHODS: We collected contrast-enhanced computed tomography (CECT) and clinical data from 120 patients form center 1. A total of 944 features were extracted single-phase images of CECT scans. Using the last absolute shrinkage and selection operator model, the best predictive radiographic features and clinical indications were screened. Data from 54 patients were collected at center 2 as an external validation set to verify the robustness of the model. The area under the receiver operating characteristic curve, accuracy, sensitivity and specificity were used for evaluation. RESULTS: A total of five machine learning models were built to distinguish PIL from CD. Based on the results from the test group, most models performed well with a large area under the curve (AUC) (> 0.850) and high accuracy (> 0.900). The combined clinical and radiomics model (AUC = 1.000, accuracy = 1.000) was the best model among all models. CONCLUSION: Based on machine learning, a model combining clinical data with radiologic features was constructed that can effectively differentiate PIL from CD.

Asunto(s)

Asunto(s)

RESUMEN

BACKGROUND: Magnetic resonance enteroclysis (MRE) has been widely applied to diagnose Crohn's disease (CD). Magnetic resonance (MR) at 3.0 T improves signal-to-noise ratio (SNR), shortens image acquisition time, and shows more advantages. OBJECTIVE: This study aimed to retrospectively analyze the diagnostic value of 3.0 T MR imaging for active CD. METHODS: 48 CD patients hospitalized in our hospital from January 2021 to December 2022 were selected as the study subjects. These 48 CD patients underwent both double-balloon enteroscopy and 3.0 T MRE. All patients' arterial phase signal, venous phase signal, bowel wall, and bowel lumen of MRE were observed to identify whether they suffered from active CD. Based on the results of enteroscopy, the number of true positives, true negatives, false negatives, and false positives diagnosed by MRE were screened; next, the diagnostic accuracy, sensitivity, and specificity of MRE in assessing active CD were calculated. RESULTS: Of the 48 patients, 39 were diagnosed with small bowel CD by MRE, which was not significantly different from the results of enteroscopy (P>0.05). According to MRE diagnostic results, the arterial phase predominantly presented high signal intensity, and the venous phase mainly presented low signal intensity or isointensity. Small bowel CD lesions were primarily characterized by bowel wall thickening, rare pneumatosis enhancement of the bowel wall, bowel lumen pneumatosis or dilatation, and rare strictures. Besides, MRE presented an accuracy of 93.75%, sensitivity of 97.37%, and specificity of 80.00% in diagnosing CD. CONCLUSION: 3.0 T MR imaging has diagnostic value for active CD and shows certain clinical application value.

Asunto(s)

RESUMEN

PURPOSE: Crohn's disease (CD) is a progressive disorder leading to cumulative bowel damage. The Lémann index is a validated tool that can help in monitoring the progression of the disease and evaluating the effectiveness of different therapies. Our aim was to describe the main radiological findings in incidentally diagnosed CD and to evaluate bowel damage in this subgroup compared to patients diagnosed at later stages. METHODS: Patients with an incidental diagnosis of CD during the colorectal cancer screening program were compared to controls with a CD cohort diagnosed after symptomatic onset and matched 1:1 by disease extent. All cross-sectional examinations were centrally read, performing a descriptive analysis of the main findings and calculation of Lémann index. RESULTS: Thirty-eight patients were included: 19 with preclinical CD (median age 55 years (IQR, 54-62), 53% male, 74% non-smokers; 74% B1 and 26% B2) and 19 matched-controls with symptomatic CD. In those with preclinical CD, the most frequent transmural findings on MRE were contrast enhancement (79%), wall thickening (79%), followed by lymphadenopathy (68%), edema (42%), and increased vascularity (42%). Among those with strictures, controls showed a higher rate of preestenotic dilation (100% vs. 0%, p = 0.01). Bowel damage assessment revealed no statistically significant differences in the Lémann index between preclinical CD and controls (p = 0.95). A statistically significant higher score in the colonic/rectum score was observed (p = 0.014). CONCLUSION: Patients with preclinical CD demonstrate similar radiological findings and degree of bowel damage as new-onset symptomatic CD.

Asunto(s)

RESUMEN

INTRODUCTION: Anti-interleukin 12/23 agents have shown greater durability in response compared with anti-tumor necrosis factor α agents. Data on the association between body composition (BC) or body mass index (BMI) and ustekinumab's therapeutic response is limited. We aimed to evaluate the impact of BC on time to failing standard doses of ustekinumab in patients with Crohn's disease (CD). METHOD: Patients with CD aged 16 years and older from 2 tertiary centers were studied retrospectively. Included patients had abdominal imaging within 6 months of ustekinumab induction and were followed until April 30, 2022. An experienced abdominal radiologist blinded to the clinical information measured the area of visceral fat area and skeletal muscle area at the mid L3 vertebral level, with values corrected for height 2 to derive respective indices (visceral fat index [VFI], skeletal muscle index [SMI]) and the VFI:SMI ratio. RESULTS: Ninety-nine patients met inclusion criteria. The mean age at ustekinumab induction was 46.6 (±1.6) years. The median BMI (interquartile range) was 26.5 (22.6-30.8). Twenty-four patients (24.2%) did not respond or lost response to standard doses of ustekinumab over the follow-up duration. A younger age (hazard ratio 0.96, 95% confidence interval 0.94-0.99, P = 0.01) and a VFI:SMI ratio >1.6 (hazard ratio 4.65, 95% confidence interval 1.73-12.45, P = 0.002) were both associated with a shorter time to failing ustekinumab at standard doses on multivariate analysis. BMI, notably, had no association with the primary outcome. DISCUSSION: A high VFI:SMI ratio is associated with an increased risk of failing standard doses of ustekinumab. BC measurements derived from cross-sectional imaging at the start of ustekinumab therapy is a useful indicator for therapeutic durability.

Asunto(s)

RESUMEN

BACKGROUND: To compare the value of adipose tissues in abdomen and lumbar vertebra for predicting Crohn's disease (CD) activity based on chemical shift encoded magnetic resonance imaging (CSE-MRI). METHODS: 84 CD patients were divided into remission, mild, and moderate-severely groups based on CD activity index (CDAI). Differences in different adipose parameters [subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), mesenteric fat index (MFI), and bone marrow fat fraction (BMFF)] and blood inflammatory indicators among three groups, as well as the correlation of above parameters and CDAI were analyzed. The areas under the receiver-operating characteristic curves (AUCs) for the parameters selected by multivariate logistic regression analysis for predicting active CD were calculated. RESULTS: There were no significant differences in VAT and MFI among three groups (both P > 0.05). The cross-sectional areas of SAT in moderate-severe group were significantly lower than those in remission group (P = 0.014). BMFF values of remission group were significantly higher than those in the mild and moderate-severe groups (both P < 0.001). BMFF was negatively correlated with CDAI (r = -0.595, P < 0.001). SAT exhibited no significant correlation with CDAI. Erythrocyte sedimentation rate (ESR) and BMFF were the independent predictors of CDAI. Both combined had a higher diagnostic efficacy for active CD with an AUC of 0.895. CONCLUSIONS: BMFF is the best marker for predicting CD activity in fat parameters of abdomen and lumbar vertebra based on CSE-MRI. The model based on BMFF and ESR has a high efficiency in predicting active CD. TRIAL REGISTRATION: No. 22 K164 (Registered 18-07-2022).

Asunto(s)

RESUMEN

INTRODUCTION: Endoscopy is still the gold, standard for assessing disease activity in Crohn's disease (CD). Its invasiveness, poor acceptability, and cost limit its use in the era of tight control and treat-to-target management. Fecal calprotectin (FC) and intestinal ultrasound (IUS) are non-invasive alternatives to colonoscopy to assess disease activity. We aimed to evaluate the performance of IUS and FC to assess mucosal healing in CD. METHODS: All consecutive CD patients who underwent colonoscopy for mucosal healing assessment and IUS and/or FC within four weeks between September 2019 and April 2022 were included in a prospective cohort. The bowel-wall thickness (BWT) and color Doppler signal (CDS) were assessed for each segment. Endoscopic remission was defined by a CDEIS score < 3. RESULTS: In total, 153 patients were included, of whom 122 showed endoscopic mucosal healing. Eighty-two (53.6 %) were female, the median was age 36 years (IQR, 28-46), and the median disease duration was 10 years (IQR, 4-19). The sensitivity (Se), specificity (Sp), positive predictive value (PPV), and negative predictive value (NPV) of a BWT < 3 mm to predict endoscopic mucosal healing were 56 %, 88 %, 95 %, and 36 %, respectively (patients misclassified as mucosal healing, 2.5 %). The best FC threshold (< 92.9 µg/g) provided similar results: 77 %, 89 %, 96 %, and 67 %, respectively (patients misclassified, 2.2 %). The association of an FC < 250 µg/g with a BWT < 3 mm and the absence of CDS increased the Sp and PPV: Se 58 %, Sp 95 %, PPV 97 %, VPN 43 %; patients misclassified, 1.3 %. CONCLUSION: Noninvasive evaluation of mucosal healing by IUS or calprotectin efficiently identifies patients with CD who have achieved endoscopic mucosal healing.

Asunto(s)

RESUMEN

Crohn's disease (CD) poses significant morbidity, underscoring the need for effective, non-invasive inflammatory assessment using magnetic resonance enterography (MRE). This literature review evaluates recent publications on the role of deep learning in improving MRE for CD assessment. We searched MEDLINE/PUBMED for studies that reported the use of deep learning algorithms for assessment of CD activity. The study was conducted according to the PRISMA guidelines. The risk of bias was evaluated using the QUADAS-2 tool. Five eligible studies, encompassing 468 subjects, were identified. Our study suggests that diverse deep learning applications, including image quality enhancement, bowel segmentation for disease burden quantification, and 3D reconstruction for surgical planning are useful and promising for CD assessment. However, most of the studies are preliminary, retrospective studies, and have a high risk of bias in at least one category. Future research is needed to assess how deep learning can impact CD patient diagnostics, particularly when considering the increasing integration of such models into hospital systems.

Asunto(s)

RESUMEN

BACKGROUND: MRI diffusion-weighted imaging (DWI) is commonly used in MR enterography protocols for assessment of intestinal inflammation in patients with Crohn's disease. The intravoxel incoherent motion (IVIM) approach to DWI has been proposed as a more objective approach, providing quantitative parameters that reflect water diffusivity (D), blood flow (D*), and perfusion fraction (f). PURPOSE: We aimed to determine if DWI-IVIM metrics from the terminal ileum in patients with newly diagnosed Crohn's disease differ from healthy participants and change in response to biologic medical therapy. METHODS: In this prospective case-control study, 20 consecutive pediatric patients (mean age = 14 years ± 2 [SD]; eight females) with newly diagnosed ileal Crohn's disease and 15 pediatric healthy participants (mean age = 18 years ± 4 [SD]; eight females) underwent research MRI examinations of the small bowel between 12/2018 and 10/2021. Participants with Crohn's disease underwent MR studies at baseline, 6 weeks, and 6 months following initiation of anti-TNF-alpha therapy, whereas control participants underwent one research MRI examination. The MRI protocol included a DWI-IVIM sequence with nine b-values and the IVIM parameters (D, D*, and f) were extracted. Unpaired t-tests and mixed-effects models were used for analyses. RESULTS: Mean IVIM D (P < 0.001), D* (P = 0.004), and f (P = 0.001) metrics were lower for Crohn's patients at the time of diagnosis compared to healthy participants. Mean IVIM f value increased over time in response to medical therapy (mean f at baseline, 22% ± 6%; 6 weeks, 25% ± 7%; 6 months, 29% ± 10%; P = 0.016). Mean IVIM D* value increased over time in response to treatment (mean D* at baseline, 10.9 ± 3.0 × 10-3 mm2/s; 6 weeks, 11.8 ± 2.8 × 10-3 mm2/s; 6 months, 13.3 ± 3.3 × 10-3 mm2/s; P = 0.047), while there was no significant change in mean IVIM D value (P = 0.10). CONCLUSION: MRI DWI-IVIM metrics in patients with ileal Crohn's disease change over time in response to biological therapy and help discriminate these patients from healthy participants.

Asunto(s)

RESUMEN

OBJECTIVES: Differentiating intestinal tuberculosis (ITB) from Crohn's disease (CD) remains a diagnostic dilemma. Misdiagnosis carries potential grave implications. We aim to establish a multidisciplinary-based model using machine learning approach for distinguishing ITB from CD. METHODS: Eighty-two patients including 25 patients with ITB and 57 patients with CD were retrospectively recruited (54 in training cohort and 28 in testing cohort). The region of interest (ROI) for the lesion was delineated on magnetic resonance enterography (MRE) and colonoscopy images. Radiomic features were extracted by least absolute shrinkage and selection operator regression. Pathological feature was extracted automatically by deep-learning method. Clinical features were filtered by logistic regression analysis. Diagnostic performance was evaluated by receiver operating characteristic (ROC) curve and decision curve analysis (DCA). Delong's test was applied to compare the efficiency between the multidisciplinary-based model and the other four single-disciplinary-based models. RESULTS: The radiomics model based on MRE features yielded an AUC of 0.87 (95% confidence interval [CI] 0.68-0.96) on the test data set, which was similar to the clinical model (AUC, 0.90 [95% CI 0.71-0.98]) and higher than the colonoscopy radiomics model (AUC, 0.68 [95% CI 0.48-0.84]) and pathology deep-learning model (AUC, 0.70 [95% CI 0.49-0.85]). Multidisciplinary model, integrating 3 clinical, 21 MRE radiomic, 5 colonoscopy radiomic, and 4 pathology deep-learning features, could significantly improve the diagnostic performance (AUC of 0.94, 95% CI 0.78-1.00) on the bases of single-disciplinary-based models. DCA confirmed the clinical utility. CONCLUSIONS: Multidisciplinary-based model integrating clinical, MRE, colonoscopy, and pathology features was useful in distinguishing ITB from CD.

Asunto(s)

Asunto(s)