Artificial intelligence for discrimination of Crohn's disease and gastrointestinal tuberculosis: A systematic review

BACKGROUND AND AIM

Discrimination of gastrointestinal tuberculosis (GITB) and Crohn's disease (CD) is difficult. Use of artificial intelligence (AI)-based technologies may help in discriminating these two entities.

METHODS

We conducted a systematic review on the use of AI for discrimination of GITB and CD. Electronic databases (PubMed and Embase) were searched on June 6, 2022, to identify relevant studies. We included any study reporting the use of clinical, endoscopic, and radiological information (textual or images) to discriminate GITB and CD using any AI technique. Quality of studies was assessed with MI-CLAIM checklist.

RESULTS

Out of 27 identified results, a total of 9 studies were included. All studies used retrospective databases. There were five studies of only endoscopy-based AI, one of radiology-based AI, and three of multiparameter-based AI. The AI models performed fairly well with high accuracy ranging from 69.6-100%. Text-based convolutional neural network was used in three studies and Classification and regression tree analysis used in two studies. Interestingly, irrespective of the AI method used, the performance of discriminating GITB and CD did not match in discriminating from other diseases (in studies where a third disease was also considered).

CONCLUSION

The use of AI in differentiating GITB and CD seem to have acceptable accuracy but there were no direct comparisons with traditional multiparameter models. The use of multiple parameter-based AI models have the potential for further exploration in search of an ideal tool and improve on the accuracy of traditional models.

Magnifying Endoscopy With Narrow Band Imaging for Graft Failure and Disease Recurrence in Patients With Crohn Disease After Intestinal Transplantation: 2 Case Reports

Crohn disease (CD) is one of the most common causes of short bowel syndrome and intestinal failure. Intestinal transplantation (IT) is sometimes needed for patients with CD who develop intestinal failure after multiple intestinal resections resulting from CD-related complications, such as uncontrollable bleeding and penetrating diseases. However, there have been few case reports concerning the endoscopic surveillance of patients with CD after IT. In this article, we present 2 patients with CD who underwent IT because of short bowel syndrome with intestinal failure. We administered posttransplantation immunosuppressants and conducted regular follow-up magnifying endoscopy with narrow-band imaging (ME-NBI). Both cases demonstrated favorable outcomes after surveillance with ME-NBI. In this report, we outline our post-IT follow-up strategies applying the VENCH scoring system, which is based on endoscopic features using ME-NBI to predict graft rejection. Our approach could effectively distinguish between acute cellular rejection and non-rejection, particularly disease recurrence of underlying CD. This study was approved by the institutional review board of Far Eastern Memorial Hospital (FEMH-105023-F). The patients provided written informed consent for publication.

Value of the virtual monoenergetic image from dual-layer dual-energy computed tomography enterography in the preoperative assessment of the internal penetrating complication of Crohn's disease

BACKGROUND

To determine the utility of virtual-monoenergetic imaging (VMI) at low energy levels from contrast-enhanced dual-layer dual-energy (DLDE) computed tomography enterography (CTE) in the preoperative assessment of internal penetrating lesions of Crohn's disease (CD).

MATERIALS AND METHODS

Thirty-eight patients with penetrating lesions of CD by surgery undergoing contrast-enhanced DLDE CTE were retrospectively included. Polyenergetic imaging (PEI) and VMIs at low energy levels [40-70 kiloelectron volts (keV)] with 10 keV intervals were reconstructed. The objective parameters of image quality [noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR)] and the subjective parameter of image quality [diagnostic performance of lesions (DPL), overall image quality(OIQ)] of PEI and all VMIs at the low energy level were compared to determine the VMI on the optimal energy level. The lesion detection capability between PEI and the optimal VMI was compared.

RESULTS

VMI40 was determined to be the optimal VMI among all VMIs at the low energy level for owning the best image quality. No significant difference was found in the detecting capability in penetrating lesions between VMI40 and PEI (p = 1.0), whereas a significant difference was found in the detecting capability in the bowel origin of the penetrating lesions (p = 0.004), the involved organ or structure by the fistula (p = 0.016) and the orifice of the fistula connected to the involved organ or structure ( p = 0.031) between them.

CONCLUSIONS

Compared to conventional PEI, VMI40 improves the detection capability in anatomical details of penetrating lesions of CD, helping colorectal surgeons rationalizing preoperative plans of internal penetrating lesions of CD.

Multiparametric MRI for Staging of Bowel Inflammatory Activity in Crohn's Disease with MUSE-IVIM and DCE-MRI: A Preliminary Study

RATIONALE AND OBJECTIVES

To investigate if the combination of multishot diffusion imaging-based multiplexed sensitivity encoding intravoxel incoherent motion (MUSE-IVIM) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is feasible for staging Crohn's disease (CD) activity.

MATERIALS AND METHODS

A total of 65 CD patients were enrolled and analyzed in this retrospective study. The simplified endoscopic score for Crohn's disease (SES-CD) and magnetic resonance index of activity (MaRIA) were used as the reference. The MUSE-IVIM and DCE-MRI data were acquired at 3.0-T MRI scanner and processed by two radiologists. Three MUSE-IVIM parameters: fast apparent diffusion coefficient (ADCfast), slow apparent diffusion coefficient (ADCslow), and the fractional perfusion (Fraction of ADCfast), as well as four DCE-MRI parameters: volume transfer constant (Ktrans), rate constant (Kep), extravascular extracellular volume fraction (Ve), and plasma volume fraction (Vp) were generated. Intraclass correlation coefficient (ICC), non-parametric test (Kruskal-Wallis H and Mann-Whitney U), logistic regression, receiver operating characteristic analysis, Delong test, and Spearman's correlation test were performed.

RESULTS

According to SES-CD, 116 ileocolonic segments with CD lesions were identified as: inactive, mild, and moderate to severe. With multivariable logistic regression analysis, ADCfast (p < 0.001), Fraction of ADCfast (p = 0.005), Ktrans (p < 0.001) and Kep (p = 0.003) were identified as significant factors for differentiating among the three groups. Binary logistic analyses identified ADCfast (p = 0.001), Ktrans (p = 0.014), and Kep (p = 0.029) as independent predictors for the active status. The combination of ADCfast, Ktrans, and Kep performed better than MaRIA score (p = 0.028), for differentiating inactive and active status. MaRIA score was positively correlated with ADCfast (p < 0.001), Ktrans (p < 0.001), Kep (p < 0.001), and Ve (p = 0.001), however, negatively correlated with Fraction of ADCfast (p < 0.001).

CONCLUSION

The combination of MUSE-IVIM and DCE-MRI has been demonstrated to accurately stage inflammatory activity in CD.

Reading of small bowel capsule endoscopy after frame reduction using an artificial intelligence algorithm

OBJECTIVES

Poorly visualized images that appear during small bowel capsule endoscopy (SBCE) can confuse the interpretation of small bowel lesions and increase the physician's workload. Using a validated artificial intelligence (AI) algorithm that can evaluate the mucosal visualization, we aimed to assess whether SBCE reading after the removal of poorly visualized images could affect the diagnosis of SBCE.

METHODS

A study was conducted to analyze 90 SBCE cases in which a small bowel examination was completed. Two experienced endoscopists alternately performed two types of readings. They used the AI algorithm to remove poorly visualized images for the frame reduction reading (AI user group) and conducted whole frame reading without AI (AI non-user group) for the same patient. A poorly visualized image was defined as an image with < 50% mucosal visualization. The study outcomes were diagnostic concordance and reading time between the two groups. The SBCE diagnosis was classified as Crohn's disease, bleeding, polyp, angiodysplasia, and nonspecific finding.

RESULTS

The final SBCE diagnoses between the two groups showed statistically significant diagnostic concordance (k = 0.954, p < 0.001). The mean number of lesion images was 3008.5 ± 9964.9 in the AI non-user group and 1401.7 ± 4811.3 in the AI user group. There were no cases in which lesions were completely removed. Compared with the AI non-user group (120.9 min), the reading time was reduced by 35.6% in the AI user group (77.9 min).

CONCLUSIONS

SBCE reading after reducing poorly visualized frames using the AI algorithm did not have a negative effect on the final diagnosis. SBCE reading method integrated with frame reduction and mucosal visualization evaluation will help improve AI-assisted SBCE interpretation.

Use of shear wave imaging with intestinal ultrasonography in patients with chronic diarrhea

OBJECTIVE

A retrospective study was designed to determine the role of shear wave elastography (SWE) and intestinal ultrasonography to differentiate between inflammatory and fibrotic bowel strictures by determining Young's modulus (E) and shear wave dispersion (SWD) and to compare its role with contrast-enhanced computed tomography (CECT) in patients with chronic diarrhea and pain abdomen.

METHODS

Seventy-six patients who had increased small bowel thickness (SBWT) >3 mm, and large bowel wall thickness (LBWT) >4 mm on intestinal ultrasonography (IUS) were evaluated in a two-step manner. The first step involved classifying patients with increased SBWT >3 mm and LBWT >4 mm by use of SWE and dispersion into three groups that is group I (fibrotic), group II (inflammatory) thickening, and group III (mixed-fibrosis and inflammatory) wall thickening. In the second step, etiological classification was done using six gray scale features of IUS that is length and degree of bowel thickening, presence of bowel stratification, Limberg grade of vascularity, status of mesenteric fat, juxta bowel status-nodes, fluid, and fistula formation to reach to a definitive diagnosis. These findings were compared with findings on CECT. Twenty-three patients had diagnosis confirmed by biopsy while 18 underwent surgery with histologic confirmation of operative findings. The sensitivity, specificity and AUROC for both modalities were compared.

RESULTS

Group I that is fibrotic group had 33 patients with fibrotic strictures of which fibrotic Crohn's disease (CD)and tuberculosis of the bowel were the dominant types followed by neoplastic and infective causes. In Group II that is inflammatory there were 32 patients with predominantly infective ileo-colitis, and ulcerative colitis patients while 11 patients were present in group III that is (mixed fibrotic and inflammatory) type of bowel wall thickening and were patients of inflammatory CD, infective ileo-colitis. The presence of length of bowel involvement, Limberg grade, mesenteric fat proliferation, and SBWT>9 mm were the statistically significant parameters on IUS which helped to reach to final diagnosis. The sensitivity and specificity of combined SWE with SWD and IUS were 100% and 99% while that of CECT was 78% and 96% respectively with AUROC of 100% and 64%.

CONCLUSION

SWI combined with IUS in a two-step manner is an accurate way to evaluate patients with chronic diarrhea who have increased SBWT and is not only able to differentiate inflammatory from fibrotic bowel wall thickening but also helps to form an etiological diagnosis.

CT enterography-based radiomics combined with body composition to predict infliximab treatment failure in Crohn's disease

PURPOSE

Accurately predicting the treatment response in patients with Crohn's disease (CD) receiving infliximab therapy is crucial for clinical decision-making. We aimed to construct a prediction model incorporating radiomics and body composition features derived from computed tomography (CT) enterography for identifying individuals at high risk for infliximab treatment failure.

METHODS

This retrospective study included 137 patients with CD between 2015 and 2021, who were divided into a training cohort and a validation cohort with a ratio of 7:3. Patients underwent CT enterography examinations within 1 month before infliximab initiation. Radiomic features of the intestinal segments involved were extracted, and body composition features were measured at the level of the L3 lumbar vertebra. A model that combined radiomics with body composition was constructed. The primary outcome was the occurrence of infliximab treatment failure within 1 year. The model performance was evaluated using discrimination, calibration, and decision curves.

RESULTS

Fifty-two patients (38.0%) showed infliximab treatment failure. Eight significant radiomic features were used to develop the radiomics model. The model incorporating radiomics model score, skeletal muscle index (SMI), and creeping fat showed good discrimination for predicting infliximab treatment failure, with an area under the curve (AUC) of 0.88 (95% CI 0.81, 0.95) in the training cohort and 0.83 (95% CI 0.66, 1.00) in the validation cohort. The favorable clinical application was observed using decision curve analysis.

CONCLUSIONS

We constructed a comprehensive model incorporating radiomics and muscle volume, which could potentially be used to facilitate the individualized prediction of infliximab treatment response in patients with CD.

Utilization of point-of-care ultrasound to evaluate for enterovesical fistula

Enterovesical fistula formation is a relatively rare disease process although a common complication for patients with inflammatory bowel disease (IBD), notably Crohn's disease. Enterovesical fistulas most commonly arise from diverticulitis (65-80%), cancer (10-20%), or Crohn's disease (5-7%). An increasing amount of evidence supports the use of ultrasonography as the primary imaging method for the monitoring of complications in individuals with a documented history of IBD. Our case report presents a 30-year-old female with a history of Crohn's disease who presented to the Emergency Department with concern for possible enterovesical fistula formation. Using bedside gray-scale ultrasonography, a fistulous tract clearly visualizing air bubbles and fecal matter actively moving from bowel to the bladder through the fistula was visualized confirming the diagnosis of an enterovesical fistula. While CT imaging is instrumental in identifying mural and extramural complications of IBD, performing ultrasonography in patients with IBD serves as an efficient, inexpensive, and noninvasive diagnostic aid for the diagnosis of enterovesical fistula.

Residual abnormalities on CTE predict adverse outcomes in Crohn's disease with endoscopic healing

BACKGROUND

Residual abnormalities on computed tomography enterography (CTE) in Crohn's disease (CD) with endoscopic healing (EH) may have prognostic implications and affect therapeutic strategy.

METHODS

CD patients with EH who underwent CTE between March 2015 and June 2022 were enrolled. CTE findings of the terminal ileum and the most severe segment of colon at the time of EH were assessed respectively for each patient. Cox regression analysis and Kaplan-Meier curves were used to evaluate the association between residual abnormalities and adverse outcomes.

RESULTS

A total of 140 patients (217 digestive segments) were included. Mesenteric edema (hazard ratio [HR] = 3.61, 95% CI = 1.81-7.20, P<0.001), fibrofatty proliferation (HR = 3.40, 95% CI = 1.97-5.85, P<0.001) and active small bowel inflammation (HR = 2.74, 95% CI = 1.59-4.71, P<0.001) were risk factors for clinical relapse. Furthermore, we built a scoring system using the three parameters. Radiologic score ≥ 1 was the best threshold to predict clinical relapse (HR = 4.56, 95% CI = 2.54-8.19, P<0.001) and it was validated in different outcomes.

CONCLUSION

The scoring system based on three residual abnormalities on CTE can predict adverse outcomes in CD patients with EH.

Proposal of an Abbreviated Noncontrast MR Enterography Protocol for Patients With Crohn Disease

MR enterography (MRE) protocols used in patients with Crohn disease are burdened by long acquisition time, high cost, and suboptimal patient experience. For several indications, highly diagnostic MRE can be performed in five or fewer sequences, without IV contrast material or antiperistaltic medication and with an examination room time of less than 12 minutes. As such, MRE could be more patient friendly, more frequently performed, and require fewer health care resources.

Defining Magnetic Resonance Imaging Treatment Response and Remission in Crohn's Disease: A Systematic Review

BACKGROUND

Magnetic resonance imaging is increasingly used to assess treatment response in Crohn's disease clinical trials. We aimed to describe the definition of MRI response and remission as assessed by magnetic resonance enterography [MRE] to evaluate treatment efficacy in these patients.

METHODS

Electronic databases were searched up to May 1, 2023. All published studies enrolling patients with inflammatory bowel disease and assessment of treatment efficacy with MRE were eligible for inclusion.

RESULTS

Eighteen studies were included. All studies were performed in patients with Crohn's disease. The study period ranged from 2008 to 2023. The majority of studies used endoscopy as the reference standard [61.1%]. MRE response was defined in 11 studies [61.1%]. Five scores and nine different definitions were proposed for MRE response. MRE remission was defined in 12 studies [66.7%]. Three scores and nine different definitions for MRE remission were described. The MaRIA score was the most frequent index used to evaluate MRE response [63.6%] and remission [41.7%]. MRE response was defined as MaRIA score <11 in 63.6% of studies using this index. In 60% of studies using the MaRIA score, MRE remission was defined as MaRIA score <7. In addition, 11 different time points of assessment were reported, ranging from 6 weeks to years.

CONCLUSION

In this systematic review, significant heterogeneity in the definition of MRE response and remission evaluated in patients with Crohn's disease was observed. Harmonization of eligibility and outcome criteria for MRE in Crohn's Disease clinical trials is needed.

Artificial Intelligence-assisted Analysis of Pan-enteric Capsule Endoscopy in Patients with Suspected Crohn's Disease: A Study on Diagnostic Performance

BACKGROUND AND AIM

Pan-enteric capsule endoscopy [PCE] is a highly sensitive but time-consuming tool for detecting pathology. Artificial intelligence [AI] algorithms might offer a possibility to assist in the review and reduce the analysis time of PCE. This study examines the agreement between PCE assessments aided by AI technology and standard evaluations, in patients suspected of Crohn's disease [CD].

METHOD

PCEs from a prospective, blinded, multicentre study, including patients suspected of CD, were processed by the deep learning solution AXARO® [Augmented Endoscopy, Paris, France]. Based on the image output, two observers classified the patient's PCE as normal or suggestive of CD, ulcerative colitis, or cancer. The primary outcome was per-patient sensitivities and specificities for detecting CD and inflammatory bowel disease [IBD]. Complete reading of PCE served as the reference standard.

RESULTS

A total of 131 patients' PCEs were analysed, with a median recording time of 303 min. The AXARO® framework reduced output to a median of 470 images [2.1%] per patient, and the pooled median review time was 3.2 min per patient. For detecting CD, the observers had a sensitivity of 96% and 92% and a specificity of 93% and 90%, respectively. For the detection of IBD, both observers had a sensitivity of 97% and had a specificity of 91% and 90%, respectively. The negative predictive value was 95% for CD and 97% for IBD.

CONCLUSIONS

Using the AXARO® framework reduced the initial review time substantially while maintaining high diagnostic accuracy-suggesting its use as a rapid tool to rule out IBD in PCEs of patients suspected of Crohn's disease.

Role of visceral fat on postoperative complications and relapse in patients with Crohn's disease after ileocecal resection: Is it overrated?

INTRODUCTION

The role of visceral fat in disease development, particularly in Crohn´s disease (CD), is significant. However, its preoperative prognostic value for postoperative complications and CD relapse after ileocecal resection (ICR) remains unknown. This study aims to assess the predictive potential of preoperatively measured visceral and subcutaneous fat in postoperative complications and CD recurrence using magnetic resonance imaging (MRI). The primary endpoint was postoperative anastomotic leakage of the ileocolonic anastomosis, with secondary endpoints evaluating postoperative complications according to the Clavien Dindo classification and CD recurrence at the anastomosis.

METHODS

We conducted a retrospective analysis of 347 CD patients who underwent ICR at our tertiary referral center between 2010 and 2020. We included 223 patients with high-quality preoperative MRI scans, recording demographics, postoperative outcomes, and CD recurrence rates at the anastomosis. To assess adipose tissue distribution, we measured total fat area (TFA), visceral fat area (VFA), subcutaneous fat area (SFA), and abdominal circumference (AC) at the lumbar 3 (L3) level using MRI cross-sectional images. Ratios of these values were calculated.

RESULTS

None of the radiological variables showed an association with anastomotic leakage (TFA p = 0.932, VFA p = 0.982, SFA p = 0.951, SFA/TFA p = 0.422, VFA/TFA p = 0.422), postoperative complications, or CD recurrence (TFA p = 0.264, VFA p = 0.916, SFA p = 0.103, SFA/TFA p = 0.059, VFA/TFA p = 0.059).

CONCLUSIONS

Radiological visceral obesity variables were associated with postoperative outcomes or clinical recurrence in CD patients undergoing ICR. Preoperative measurement of visceral fat measurement is not specific for predicting postoperative complications or CD relapse.

Visceral adipose tissue volume effect in Crohn's disease using reduced exposure CT enterography

PURPOSE

The purpose of this investigation was to assess the effect of visceral adipose tissue volume (VA) on reader efficacy in diagnosing and characterizing small bowel Crohn's disease using lower exposure CT enterography (CTE). Secondarily, we investigated the effect of lower exposure and VA on reader diagnostic confidence.

METHODS

Prospective paired investigation of 256 CTE, 129 with Crohn's disease, were reconstructed at 100% and simulated 50% and 30% exposure. The senior author provided the disease classification for the 129 patients with Crohn's disease. Patient VA was measured, and exams were evaluated by six readers for presence or absence of Crohn's disease and phenotype using a 0-10-point scale. Logistic regression models assessed the effect of VA on sensitivity and specificity.

RESULTS

The effect of VA on sensitivity was significantly reduced at 30% exposure (odds radio [OR]: 1.00) compared to 100% exposure (OR: 1.12) (p = 0.048). There was no statistically significant difference among the exposures with respect to the effect of visceral fat on specificity (p = 0.159). The study readers' probability of agreement with the senior author on disease classification was 60%, 56%, and 53% at 100%, 50%, and 30% exposure, respectively (p = 0.004). When detecting low severity Crohn's disease, readers' mean sensitivity was 83%, 75%, and 74% at 100%, 50%, and 30% exposure, respectively (p = 0.002). In low severity disease, sensitivity also tended to increase as visceral fat increased (ORs per 1000 cm3 increase in visceral fat: 1.32, 1.31, and 1.18, p = 0.010, 0.016, and 0.100, at 100%, 50%, and 30% exposure).

CONCLUSIONS

While the interaction is complex, VA plays a role in detecting and characterizing small bowel Crohn's disease when exposure is altered, particularly in low severity disease.

Crohn's disease inflammation severity assessment with iodine density from photon counting CT enterography: comparison with endoscopic histopathology

PURPOSE

To determine optimal iodine density thresholds for active inflammation in CD patients with PCCT enterography and determine if iodine density can be used to stratify CD activity severity.

METHODS

A retrospective PACS search identified patients with CD imaged with PCCT enterography from 4/11/2022 to 10/30/2022 and with clinical notes, endoscopic/surgical pathology and available source PCCT data for iodine density analysis. Two abdominal radiologists with expertise in CD each drew two region of interest measurements within the visibly most affected region of terminal or neoterminal ileum wall on commercially available system (SyngoVia). Radiologists were blinded to clinical information and pathologic findings. Disease activity and severity were recorded from the pathology report. Harvey-Bradshaw Index, medications, and laboratory values were recorded. Receiver operating characteristic (ROC) curves were utilized to determine the optimum iodine density threshold for active inflammation and mild versus moderate-to-severe inflammation. Intra- and inter-reader agreement was assessed by intra-class correlation coefficient (ICC).

RESULTS

23 CD patients (15 females; mean [SD] age: 52 [17] years) imaged with PCCT enterography were included. 15/23 had active inflammation: 9/15 mild, 4/15 moderate, and 2/15 severe active inflammation. The optimal iodine density threshold for active inflammation was 2.7 mg/mL, with 97% sensitivity, 100% specificity, and 98% accuracy (AUC = 1.00). The optimal iodine density threshold for distinguishing mild from moderate-to-severe inflammation was 3.4 mg/mL, with 83% sensitivity, 89% specificity, and 87% accuracy (AUC = 0.85). Intra-reader reliability (R1/R2) ICC was 0.81/0.86. Inter-reader reliability ICC was 0.94.

CONCLUSION

Iodine density from PCCT enterography can distinguish mild from moderate-to-severe active inflammation.

Intestinal ultrasound score predicts therapeutic outcomes of infliximab in pediatric patients with Crohn's disease

BACKGROUND AND AIMS

Objective evaluation of treatment response is critical in the management of Crohn's disease (CD). Compared with endoscopy, intestinal ultrasound (IUS) is non-invasive and well-tolerated. This study is aimed to assess the predictive value of IUS score for treatment response in pediatric CD patients.

METHODS

We conducted a retrospective study in pediatric CD patients who underwent endoscopy and IUS at start of infliximab treatment [T0] and after 22-38 weeks [T1] between February 2021 and January 2023. Pediatric Crohn's Disease Activity Index (PCDAI), biochemical parameters, the Simple Endoscopic Score for Crohn's disease (SES-CD) and IUS parameters were collected at two timepoints. IUS scores were assessed by International Bowel Ultrasound Segment Activity Score (IBUS-SAS).

RESULTS

Thirty patients were included, with 53.3% reaching endoscopic response and 43.3% endoscopic remission. After infliximab treatment, IBUS-SAS (58.5 ± 24.2 vs 34.4 ± 21.6, p = .0001) was significantly decreased. At T1, change in IBUS-SAS (-38.2 ± 22.0 vs -7.9 ± 24.1, p = .0015) were pronounced in patients with endoscopic response compared with endoscopic non-response. Significant correlation were observed between IBUS-SAS and SES-CD, PCDAI, C-reaction protein, erythrocyte sedimentation rate, hemoglobin, albumin. The most accurate cutoff values for predicting endoscopic response were 57.4% decrease of IBUS-SAS (AUROC: 0.862, p < .001). The optimal cut-off of IBUS-SAS to correlate endoscopic remission was 26.0 (AUROC: 0.686, p = .017).

CONCLUSIONS

The validated ultrasound-base score, IBUS-SAS is an effective index for monitoring endoscopic response to infliximab therapy in CD. IUS evaluation could guide treatment decision for pediatric CD.

MICDnet: Multimodal information processing networks for Crohn's disease diagnosis

Crohn's disease (CD) is a chronic inflammatory disease with increasing incidence worldwide and unclear etiology. Its clinical manifestations vary depending on location, extent, and severity of the lesions. In order to diagnose Crohn's disease, medical professionals need to comprehensively analyze patients' multimodal examination data, which includes medical imaging such as colonoscopy, pathological, and text information from clinical records. The processes of multimodal data analysis require collaboration among medical professionals from different departments, which wastes a lot of time and human resources. Therefore, a multimodal medical assisted diagnosis system for Crohn's disease is particularly significant. Existing network frameworks find it hard to effectively capture multimodal patient data for diagnosis, and multimodal data for Crohn's disease is currently lacking. In addition,a combination of data from patients with similar symptoms could serve as an effective reference for disease diagnosis. Thus, we propose a multimodal information diagnosis network (MICDnet) to learn CD feature representations by integrating colonoscopy, pathology images and clinical texts. Specifically, MICDnet first preprocesses each modality data, then uses encoders to extract image and text features separately. After that, multimodal feature fusion is performed. Finally, CD classification and diagnosis are conducted based on the fused features. Under the authorization, we build a dataset of 136 hospitalized inspectors, with colonoscopy images of seven areas, pathology images, and clinical record text for each individual. Training MICDnet on this dataset shows that multimodal diagnosis can improve the diagnostic accuracy of CD, and the diagnostic performance of MICDnet is superior to other models.

Wall Thickness Ratio-A New Magnetic Resonance Parameter-Is Associated With the Outcome of Biological Therapy in Patients With Ileal and Ileocolonic Crohn's Disease

GOALS

The present study was aimed at identifying a new magnetic resonance enterography (MRE) parameter assessing the clinical outcome of biological therapy in patients with active ileal/ileocolonic Crohn's disease (CD).

BACKGROUND

Transmural healing (TH) has been associated with improved outcomes in CD. However, some patients with clinical remission and inactive disease at endoscopy do not achieve TH.

MATERIALS AND METHODS

Ileal/ileocolonic CD patients scheduled for biological therapy were prospectively evaluated, at baseline (T0) and after 1 year of treatment (T1), with Harvey Bradshaw Index score, blood tests, ileocolonscopy, and MRE. Clinical activity was assessed after 2 years of treatment (T2). Wall thickness ratio (WTR) was calculated in the same affected ileal segment, as the ratio between the ileum wall thickness value at T1 and the ileum wall thickness value at T0.

RESULTS

A total of 103 patients were included. Mean WTR at T1 in nonresponders was significantly higher than in responders. At receiver operating characteristic analysis, WTR values were significantly associated to biological therapy responsiveness. A WTR cutoff value of 0.77 mm was identified to discriminate responders from nonresponders (sensitivity: 79%; specificity: 67%). In responders, the proportion of patients with a WTR<0.77 was significantly higher than the proportion of patients achieving TH at T1. Among patients achieving endoscopic remission, 11/29 (37.9%) presented TH, while 20/29 (68.9%) presented WTR<0.77 ( P : 0.035). At multivariate logistic regression analysis, WTR<0.77 was significantly associated to biological therapy response.

CONCLUSION

WTR index represents an easy-to-calculate MRE parameter and seems to be a promising tool for monitoring therapeutic response in CD patients during biological therapy.

MR Enterography in Ulcerative Colitis: Beyond Endoscopy

Ulcerative colitis (UC) is a chronic idiopathic inflammatory bowel disease (IBD) that progressively affects mucosa and submuccosa of the colon and rectum in a continual pattern. In comparison, Crohn disease (CD), the other type of IBD, is a chronic transmural inflammatory disorder that can involve any part of the gastrointestinal tract. MR enterography (MRE) has emerged as an important imaging modality for the diagnosis and detection of disease activity and complications in CD, with comparable results to those of endoscopy. But MRE has been underused for assessment of UC in recent years, and clinicians heavily rely on endoscopic findings for management of UC. Despite UC being considered an endoscopically assessable disease, MRE can provide useful information beyond that obtained with endoscopy about mural or extramural abnormalities, inaccessible parts of the colonic lumen, associated extraintestinal diseases, and superimposed pathologic conditions. Moreover, endoscopy might be contraindicated in some clinical settings due to the risk of colonic perforation. In addition to depicting the features of UC activity in different phases, MRE demonstrates findings of disease chronicity that cannot be achieved with endoscopy, particularly in a patient with colitis of unknown cause. The valuable diagnostic role of MRE to exclude undiagnosed CD in patients with UC who have refractory disease or those with postproctocolectomy complications is also emphasized. Radiologists can play a crucial role in the management of UC with MRE by addressing what is beyond endoscopy. ©RSNA, 2023 Test Your Knowledge questions are available in the supplemental material.

Automatized Detection of Crohn's Disease in Intestinal Ultrasound Using Convolutional Neural Network

INTRODUCTION

The use of intestinal ultrasound (IUS) for the diagnosis and follow-up of inflammatory bowel disease is steadily growing. Although access to educational platforms of IUS is feasible, novice ultrasound operators lack experience in performing and interpreting IUS. An artificial intelligence (AI)-based operator supporting system that automatically detects bowel wall inflammation may simplify the use of IUS by less experienced operators. Our aim was to develop and validate an artificial intelligence module that can distinguish bowel wall thickening (a surrogate of bowel inflammation) from normal bowel images of IUS.

METHODS

We used a self-collected image data set to develop and validate a convolutional neural network module that can distinguish bowel wall thickening >3 mm (a surrogate of bowel inflammation) from normal bowel images of IUS.

RESULTS

The data set consisted of 1008 images, distributed uniformly (50% normal images, 50% abnormal images). Execution of the training phase and the classification phase was performed using 805 and 203 images, respectively. The overall accuracy, sensitivity, and specificity for detection of bowel wall thickening were 90.1%, 86.4%, and 94%, respectively. The network exhibited an average area under the ROC curve of 0.9777 for this task.

CONCLUSIONS

We developed a machine-learning module based on a pretrained convolutional neural network that is highly accurate in the recognition of bowel wall thickening on intestinal ultrasound images in Crohn's disease. Incorporation of convolutional neural network to IUS may facilitate the use of IUS by inexperienced operators and allow automatized detection of bowel inflammation and standardization of IUS imaging interpretation.

Imaging Agents for PET of Inflammatory Bowel Disease: A Review

Inflammatory bowel disease (IBD), which encompasses ulcerative colitis and Crohn disease, is a chronic inflammatory disorder resulting from an aberrant immune response, though its exact cause is unknown. The current mainstay standard of care for the diagnosis and surveillance of IBD is endoscopy. However, this methodology is invasive and images only superficial tissue structures, revealing very little about the molecular drivers of inflammation. Accordingly, there is an unmet need for noninvasive imaging tools that provide reliable and quantitative visualization of intestinal inflammation with high spatial and molecular specificity. In recent years, several PET agents for imaging IBD have been reported. Such agents allow noninvasive visualization and quantification of dynamic molecular inflammatory processes in vivo. This review focuses on recent advancements in the development of PET tracers for imaging biomarkers of interest in IBD pathogenesis, such as cell-surface molecules that are overexpressed on immune cells and cytokines that perpetuate inflammatory signaling.

Focal loss of mural stratification as a radiological predictor for small bowel adenocarcinoma in Crohn's disease

AIM

Patients with Crohn's disease (CD) are at higher risk of small bowel adenocarcinoma (SBA). We aimed to identify radiological predictors of SBA in CD.

METHODS

We conducted a retrospective case-control study at two tertiary inflammatory bowel disease centers and identified CD patients diagnosed with SBA between 2003 and 2019. Patients were matched with up to four controls. Pre-operative imaging (magnetic resonance imaging (MRI) or computed tomography (CT)) were reviewed by three gastrointestinal radiologists.

RESULTS

Nineteen patients with CD-associated SBA with a mean age of 54.9 and 32 matched controls were included. Mean length of small bowel involvement was 216 (± 188) mm in the SBA group versus 156 (± 167) mm in the control group (p = 0.76). Only 11.8 % of cases had a diagnosis of SBA made preoperatively. In univariate analysis, focal loss of mural stratification (odds ratio [OR], 11; 95%CI, 2.43-49.5, p = 0.002), and wall thickening (OR, 1.32; 95%CI, 1.05-1.66, p = 0.02) were significantly associated with SBA. After adjustment, focal loss of mural stratification was the only independent risk factor (OR, 11; 95 % CI, 2.43-49.5, p = 0.002).

CONCLUSIONS

Focal loss of mural stratification was identified as a predictor of CD-associated SBA, which should be described in imaging reports and further validated.

Duodenal stenosis surgical treatment in Crohn's disease

We present the case of a 34-year-old man with daily vomiting and 20% weight loss in a year. A gastroduodenoscopy was performed, noticing 2nd and 3rd duodenal portion dilatation and inflammatory involvement of the 3rd and 4th portion, causing luminal stenosis. These findings are the same than in the magnetic resonance . The biopsy proves the histological diagnosis of Crohn's disease. At the beginning the patient was treated with Prednisone, Adalimumab and Ustekinumab. After 9 months, surgery was decided because the disease was refractory to treatment and there was corticosteroid dependence. A partial resection of 3rd and 4th portion of the duodenum and the first loop of jejunum was performed, with duodenojejunal anastomosis. The patient presents good postoperative evolution and after 1 year he remained asymptomatic under treatment with Ustekinumab.

Assessing Active Bowel Inflammation in Crohn's Disease Using Intestinal Ultrasound: Correlation With Fecal Calprotectin

AIM

To analyze the correlation between intestinal ultrasound (IUS) and serum and fecal biomarkers, and the characteristics of small bowel disease, for the assessment of active bowel inflammation.

METHODS

Patients with Crohn's disease (CD) who underwent an initial IUS examination between July 2018 and November 2022 at our institution were included retrospectively. We divided small and large bowels into seven segments, and recorded the presence of active inflammation according to following criteria: bowel wall thickness ≥ mm with ≥1 of feature of active disease on IUS. The correlations between IUS-assessed activity and serum C-reactive protein (CRP, mg/dL) and fecal calprotectin (FC, μg/g) levels were analyzed.

RESULTS

A total of 127 patients were included (mean age: 32.42 ± 12.07, M:F = 90:37, median disease duration 6 years [0-35]). Of them, 78 showed active bowel inflammation (61.4%), with inflammation distal to the terminal ileum being the most common disease location (n = 61, 78.2%). FC and serum CRP levels were significantly correlated with the number of segments with active inflammation (rho = 0.58, 0.48), number of segments with complications (r = 0.35, 0.31), and US activity score (r = 0.62, 0.54). With FC cutoff values of 100 and 150 μg/g, the concordance rates for patients with active small bowel disease were 78.7% (26/33) and 72.7% (24/33), respectively, which were better than those for other disease locations.

CONCLUSIONS

Disease activity determined by IUS was significantly correlated with the biomarkers, with a better concordance rate in patients with active small bowel disease than in those with other disease locations with FC cut-off values of 100 and 150 μg/g.