CT Enterography Findings Research Articles

Machine learning methods in automated detection of CT enterography findings in Crohn's disease: A feasibility study

PurposeQualitative 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 methodsSubjects 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. ResultsIn 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. ConclusionMachine learning techniques for CTE image analysis can identify the presence, location, and distribution of qualitative CD findings with similar performance to experienced radiologists.

Effectiveness and Power of Abdominal Ultrasonography in the Assessment of Crohn's Disease Activity: Comparison with Clinical, Endoscopic, and CT Enterography Findings.

Non-invasive methods play an important role in clinical assessment of Crohn's disease. Recent studies have highlighted the effectiveness and reliability of intestinal ultrasonography. We aimed to examine the relationship between intestinal ultrasonography and the clinical, endoscopic, and computed tomography enterography findings, and to assess the activity of Crohn's disease. This was a 1-year prospective study involving patients diagnosed with Crohn's Disease. Clinical and endoscopic activity indi- ces, and intestinal ultrasonography and computed tomography enterography findings were evaluated. Intestinal wall thickness, mes- enteric inflammation, lymphadenopathy, and complications were evaluated by intestinal ultrasonograpy and computed tomography enterography, while the superior mesenteric artery flow velocity, resistive index, and Limberg score were assessed by Doppler intestinal ultrasonography. Seventy-nine patients with Crohn's disease were included. A significant correlation was found between intestinal wall thick- ness, mesenteric inflammation, and complications in intestinal ultrasonography and computed tomography enterography (P = .0001). According to the receiver operating curve analysis, the intestinal wall thickness, and mesenteric inflammation were correlated with the Crohn's Disease Activity Index, Harvey-Bradshaw Index, and SES-CD scores (P < .05), and they were very effective in distinguishing active from inactive disease. According to the Crohn's Disease Activity Index and SES-CD scores, Doppler flow velocity of the superior mesenteric artery was significantly higher in the active group than in the inactive group (P < .05). The Limberg score was very consistent with the Crohn's Disease Activity Index, Harvey-Bradshaw Index , and the results of the Simple Endoscopic Score for Crohn's Disease (P < .0001). Our study showed that intestinal ultrasonography is an effective and reliable method for assessment of Crohn's disease activity compared to clinical, endoscopic, and CTE findings.

Evaluation of CT enterography findings for endoscopic complete remission after anti-TNF-α therapy in patients with Crohn's disease.

BackgroundUnnecessary prolonged treatment with biologic agents for Crohn’s disease (CD) patients with endoscopic complete remission (CR) might increase the opportunistic infections.PurposeTo evalua...

Mesenteric findings of CT enterography are well correlated with the endoscopic severity of Crohn’s disease

BackgroundMaintenance of mucosal healing is a primary goal when treating Crohn’s disease (CD). Endoscopy is the most precise method for the assessment of mucosal healing, but is considered overly invasive for patients with CD. In contrast, CT enterography (CTE) is less invasive, but little is known about the correlation between mucosal status and CTE parameters. MethodsWe recruited CD patients who underwent CTE and double balloon endoscopy (DBE) on the same day at our hospital between 2012 and 2014. CTE parameters evaluated included bowel-wall thickening, mural hyperenhancement, mural stratification (target sign), submucosal fat deposition, mesenteric hypervascularity (comb sign), increased fat density, mesenteric fibrofatty proliferation, enlarged mesenteric lymph nodes, and stenosis/sacculation. Endoscopic findings were evaluated using the Simple Endoscopic Score for Crohn’s Disease (SES-CD). CTE parameters that were predictive of higher values in the SES-CD were extracted statistically. ResultsForty-one patients were recruited, from which 191 intestinal segments were evaluated. Spearman’s rank correlation coefficients showed that the majority of CTE values exhibited mild to moderate correlations with SES-CD values. Notably, multiple ordinal logistic regression analysis demonstrated that CTE findings obtained from the mesenteric area, such as mesenteric hypervascularity (comb sign) and enlarged mesenteric lymph nodes, were more critical predictors of endoscopic mucosal ulceration than those obtained from the bowel wall. ConclusionsThis study was the first of its kind to assess correlations between CTE values and SES-CD values. Mesenteric findings of CTE, rather than mural findings, were highly correlated with the endoscopically evaluated severity of ulceration.

Obscure gastrointestinal bleeding: difficulties in comparing CT enterography and video capsule endoscopy

A paper reports the results of a retrospective study that was designed to evaluate the potential role of video capsule endoscopy (VCE) in elucidating the cause of bleeding in patients with obscure gastrointestinal bleeding (OGIB) for whom CT enterography was negative. The authors highlight the limitations of dual-phase CT enterography for the detection of flat lesions of the small bowel such as ulcers, angiodysplasias or arteriovenous malformations, and confirm the superiority of VCE for the detection of this category of lesions. This commentary discusses some of the issues raised. • Video capsule endoscopy surpasses CT enterography in detecting flat small bowel lesions. • Retrospective VCE and CT enterography findings in obscure bleeding need further evaluation. • A fair and unbiased comparison of the two investigations is still needed.

Do CT Enterography Findings Correlate with Clinical Scores of Crohnʼs Disease?

Do CT Enterography Findings Correlate with Clinical Scores of Crohnʼs Disease?

Small bowel adenocarcinoma in Crohn disease: CT-enterography features with pathological correlation

The aim of this study was to analyze the clinical, pathological, and CT-enterography findings of small bowel adenocarcinomas in Crohn disease patients. Clinical, histopathological, and imaging findings were retrospectively evaluated in seven Crohn disease patients with small bowel adenocarcinoma. CT-enterography examinations were reviewed for morphologic features and location of tumor, presence of stratification, luminal stenosis, proximal dilatation, adjacent lymph nodes, and correlated with findings at histological examination. The tumor was located in the terminal (n = 6) or distal (n = 1) ileum. On CT-enterography, the tumor was visible in five patients, whereas two patients had no visible tumor. Four different patterns were individualized including small bowel mass (n = 2), long stenosis with heterogeneous submucosal layer (n = 2), short and severe stenosis with proximal small bowel dilatation (n = 2), and sacculated small bowel loop with irregular and asymmetric circumferential thickening (n = 1). Stratification, fat stranding, and comb sign were present in two, two, and one patients, respectively. Identification of a mass being clearly visible suggests strongly the presence of small bowel adenocarcinoma in Crohn disease patients but adenocarcinoma may be completely indistinguishable from benign fibrotic or acute inflammatory stricture. Knowledge of these findings is critical to help suggest the diagnosis of this rare but severe complication of Crohn disease.

Endoscopic Score Extracted From Scope Report Correlates With Crohn's Disease Activity and CT Enterography Findings

Endoscopic Score Extracted From Scope Report Correlates With Crohn's Disease Activity and CT Enterography Findings

Crohn's disease: CT enterography manifestations before and after treatment

The purpose of this study was to determine whether CT enterography (CTE) changes of Crohn's disease (CD) after treatment correlated with clinical remission. We retrospectively studied 50 known CD patients (male: 35; female: 15) with clinical remission in a period of 3 years (2005-2008). CD was diagnosed by clinical, enteroscopic and pathologic manifestations. Clinical remission was identified by experienced gastroenterologists using the combing criteria of clinical, endoscopy and laboratory tests. First CTE and endoscopy exams were performed during their first hospitalization in our hospital meanwhile CD diagnosis was made during that time. Repeated CTE and endoscopy exams were done after treatment. CTE findings were determined by two experienced radiologists with double-blind approach. Each patient was analyzed for the CTE parameters including bowel wall attenuation, bowel wall thickening (>3mm), bowel wall thickening types (type A: multilayered mural stratification; type B: two layers with strong mucosal enhancement and prominent low-density submucosa; type C: two layers without strong mucosal enhancement; type D: homogeneous enhancement) comb sign, luminal stenosis (mild: luminal diameter 2-3 cm; moderate: luminal diameter 1-2 cm; severe: luminal diameter<1cm) and the presence of extraenteric complications (such as fistulas and abscess). All the quantitative parameters were measured three times by each review. After treatment, bowel wall thickening was attenuated in 88% of CD patients. Thickness of bowel wall was decreased from 8.8 ± 2.8mm to 6.4 ± 1.9 mm (P<0.001). CT value of bowel wall in portal stage was also declined from 90.0 ± 15.4 (HU) to 73.4 ± 14.2 (HU (P<0.001). The percentage of patients with type A or B bowel wall thickening was decreased from 78.7% to 35.4%, while those with type C or D thickening was increased from 21.2% to 64.6% (P<0.001). The percentage of patients with comb sign was decreased from 88% to 60% (P=0.001). The percentage of patients with moderate or severe luminal stenosis was reduced from 74% to 32% (P<0.001). The ROC (receiver operating characteristic) analysis showed bowel wall attenuation (A(z)=0.89) and bowel wall thickness (A(z)=0.81) were the two best parameters to predict disease activity, and combining of these two values was better than using them solely (κ=0.71, P<0.001). The bowel wall attenuation (OR=9.56, P<0.001) and bowel wall thickness (OR=3.32, P=0.001) were significantly correlated with the disease activity in the following logistic regression analysis. Therapeutic effect of CD and disease activity can be properly evaluated by CTE.

Enterografia por tomografia computadorizada: experiência inicial na avaliação das doenças do intestino delgado

OBJETIVO: O objetivo deste estudo é demonstrar a importância da enterografia por tomografia computadorizada (entero-TC) e como este exame pode contribuir na elucidação diagnóstica e avaliação clínica de pacientes com doenças do intestino delgado. MATERIAIS E MÉTODOS: Análise retrospectiva de 35 pacientes submetidos a entero-TC realizadas em aparelho multidetector de 16 canais, entre maio de 2008 e março de 2009. Utilizou-se meio de contraste iodado venoso e oral neutro (polietilenoglicol). As principais indicações foram avaliação de doença de Crohn, diarreia de origem indeterminada e suspeita de neoplasias. RESULTADOS: Houve boa correlação dos achados à entero-TC relacionados à atividade da doença em pacientes com doença de Crohn, quando comparados com dados clínicos, laboratoriais e endoscópicos. Em 15 casos identificaram-se alterações compatíveis com doença de Crohn, 9 deles sugerindo atividade. Dos pacientes com diarreia, o exame elucidou a maioria dos casos. Identificaram-se dois casos de tumor carcinoide. CONCLUSÃO: A entero-TC é método simples e eficaz para estudo das doenças inflamatórias/neoplásicas do intestino delgado, sobretudo na avaliação da doença de Crohn, indicando atividade da doença. Uma de suas principais vantagens é a possibilidade de avaliação de alterações mesentéricas e extraintestinais associadas.

PET/CT Enterography in Crohn Disease: Correlation of Disease Activity on CT Enterography with 18F-FDG Uptake

We combined (18)F-FDG PET and CT enterography in a single examination and compared the level of (18)F-FDG uptake measured by maximal standardized uptake value (SUVmax) with the CT enterography patterns of disease activity found in patients with Crohn disease (CD). Twenty-eight patients (mean age, 37.5 y; 11 male and 17 female) suspected of having active CD underwent PET/CT enterography. Abnormal bowel segments recognized on CT enterography were graded qualitatively for the presence of perienteric fat infiltration, the comb sign, and intramural attenuation and by quantitative measurements of mural enhancement (Hounsfield units) and thickness (mm). Also, for each patient, normal segments of the ileum and colon were noted, and CT enterography measurements of thickness and enhancement were obtained. For segments detected on CT enterography, a volume of interest was placed on the fused (18)F-FDG PET scan, and the SUVmax was obtained. Of the 28 patients with suspected active CD, 22 had 85 abnormal segments and 6 had no abnormal segments. SUVmax was significantly higher in the abnormal segments than in the normal segments (5.0 +/- 2.5 [95% confidence interval, 4.5-5.5] and 2.1 +/- 0.69 [95% confidence interval, 1.9-2.2], respectively; P < 0.0001). A good correlation was found between SUVmax with CT enterography measurements of mural thickness and enhancement (P < 0.00001). There was a significant difference in SUVmax between the 3 levels of disease activity found by intramural attenuation, perienteric fat infiltration, and the comb sign on CT enterography. SUVmax was significantly higher when there were intense CT enterography findings of active disease (P < 0.001). SUVmax assessment may allow an objective, reliable indication of the grade and severity of inflammation activity in abnormal segments of the bowel detected by CT enterography.

M1237 CT Enterography Findings Correlate With Components of Harvey-Bradshaw Index

(age >17) who had both upper and lower GI biopsies within a 12-month period. Patients were then divided into two groups. Group I: patients with a histologic diagnosis of a normal colon. Group II: patients with a histopathologic diagnosis of IBD in the terminal ileum and/ or colon. Group II patients were sub-classified as CD or UC, based on clinical history and consensus definitions. Cases of indeterminate colitis were excluded. The relative prevalence of a set of upper GI histopathologic conditions was evaluated. ORs for patients with a normal colon were arbitrarily set as 1. Results: In Group I (22,788 patients; 14,415 women, 63.3%) 1,227 had esophageal biopsies; 2,027 gastric biopsies; and 1,895 duodenal biopsies. In Group II 87 had esophageal biopsies; 128 gastric biopsies; and 86 duodenal biopsies. Active esophagitis was significantly more prevalent in patients with UC (27.8%) than CD (7.5%) and controls (7.7%; OR 4.58). Granulomas were only identified in the esophagus of one CD patient (2.5%). H. pylori-negative chronic active gastritis (CAG) was significantly more prevalent in CD patients (19.3%) than UC patients (9.6%) or controls (4.4%; OR 5.15). In gastric biopsies, granulomas were recognized in 2 (3.5%) CD patients, and were not identified in UC patients. Non-peptic duodenitis was only found in one CD patient (2.5%). No duodenal granulomas were detected in any patient.Conclusions: Although active esophagitis was more common in UC patients, this lesion is nonspecific and unlikely to help in the diagnosis. H. pylori-negative gastritis, also nonspecific, was more prevalent in CD patients. Granulomas were rarely noted. Duodenal biopsies did not show significant differences between any of the groups. Overall, our IBD patients had a low prevalence of upper GI pathologic findings. Whether upper GI biopsies in adults can be recommended as a useful adjunct for the specific characterization of IBD requires further investigation.

548 PET/CT Enterography in Crohn's Disease: Comparison of CT Enterography Findings With 18F-FDG Uptake

548 PET/CT Enterography in Crohn's Disease: Comparison of CT Enterography Findings With 18F-FDG Uptake

CT enterography and fistulizing Crohn’s disease: clinical benefit and radiographic findings

To estimate the clinical benefit of CT enterography (CTE) in patients with fistulizing Crohn's disease and describe the appearance of fistulas at CTE. Crohn's patients who had undergone CTE, which diagnosed an abscess or fistula, were identified. A gastroenterologist reviewed clinical notes prior to and following CTE to assess the pre-CTE clinical suspicion for fistula/abscess, and post-CTE alteration in patient management. A radiologist reassessed all fistula-positive cases, which were confirmed by a non-CT reference standard, to describe their radiologic appearance. Fifty-six patients had CT exams identifying 19 abscesses and 56 fistulas. There was no or remote suspicion of fistula or abscess at pre-imaging clinical assessment in 50% of patients. Thirty-four patients (61%) required a change in or initiation of medical therapy and another 10 (18%) underwent an interventional procedure based on CT enterography findings. Among 37 fistulas with reference standard confirmation, 30 (81%) were extraenteric tracts, and 32 (86%) were hyperenhancing compared to adjacent bowel loops. Most fistulas (68%) contained no internal air or fluid. CTE detects clinically occult fistulas and abscesses, resulting in changes in medical management and radiologic or surgical intervention. Most fistulas appear as hyperenhancing, extraenteric tracts, usually without internal air or fluid.

Using CT Enterography to Monitor Crohn's Disease Activity: A Preliminary Study

The purpose of our study was to determine whether imaging changes of Crohn's disease at sequential CT enterography examinations correlate with disease progression or regression. Forty CT enterography examinations in 20 patients (12 women, eight men; mean age, 55.5 years) with known Crohn's disease were retrospectively evaluated by a radiologist who was blinded to the clinical history. One radiologist determined whether imaging findings of Crohn's disease were present and, if so, whether the findings progressed, regressed, or remained stable between examinations. CT enterography findings were then compared with disease progression or regression based on symptoms and clinical follow-up. Direct comparison of CT enterography and endoscopy was also performed when available. Disease progression or regression by CT enterography correlated with symptoms in 16 of 20 (80%) patients. Specifically, CT enterography and symptoms agreed in 12 patients with clinical disease progression, two patients with clinical regression, and two with clinically stable disease. In four of 20 (20%) patients, symptoms progressed although CT enterography findings were negative (n = 2) or improved (n = 2). No treatment change was initiated; and at follow-up, three of four patients were improved and the remaining patient was stable symptomatically. Sixteen ileoscopies were attempted in 12 patients; however, four examinations did not reach the ileum. In the remaining examinations, endoscopy correlated with CT enterography in all cases (12/12, 100%) and with symptoms in nine of 12 (75%) cases. The weighted kappa statistic, which measures the chance-adjusted agreement between CT enterography and symptoms, was 0.57 (95% CI, 0.20-0.94). This preliminary study indicates that imaging changes between CT enterography examinations have excellent potential for reliably monitoring Crohn's disease progression or regression.

S1178 CT Enterography Findings Correlate with Tissue Inflammation But Not Fibrosis in Resected Small Bowel Crohn's Disease

S1178 CT Enterography Findings Correlate with Tissue Inflammation But Not Fibrosis in Resected Small Bowel Crohn's Disease

CT Enterography for Crohn's Disease: Accurate Preoperative Diagnostic Imaging

CT enterography (CTE) is a technique that provides detailed images of the small bowel by using a low Hounsfield unit oral contrast media. This study was designed to correlate CTE findings with operative findings in patients with Crohn's disease. We performed a retrospective study of all patients with Crohn's disease of the small bowel or colon, who had CTE and subsequent small bowel or colon surgery within three months after the CT examination. CTE findings of stricture, fistula, inflammatory mass, abscess, and combinations of these abnormalities were compared with operative findings. Specialist radiologists and fellowship-trained colorectal surgeons participated in the study. The Fisher's exact test or chi-squared tests were used with respect to categorical data, and the Wilcoxon's rank-sum test was used for quantitative data. In 36 patients, the presence or absence of stricture, fistula, abscess, or inflammatory mass was correctly determined by CTE in 100, 94, 100, and 97 percent, respectively. The accuracy for stricture or fistula number was 83 and 86 percent, respectively. There were nine patients with multiple disease phenotypes identified on CTE of which eight were confirmed at surgery. CTE overestimated or underestimated the extent of disease in 11 patients (31 percent). CTE is an accurate preoperative diagnostic imaging study for small-bowel Crohn's disease. The ability of this imaging study to detect both luminal and extraluminal pathology is a distinct advantage of CTE compared with small-bowel contrast studies.

Do Sequential CT Enterography Exams for Assessing Crohnʼs Disease Activity Correlate with Physician Global Assessment and Endoscopic Findings?

Purpose: CT enterography (CTE) is an excellent non-invasive imaging test for evaluating Crohn's disease (CD). It is not yet known if sequential CTE changes over time correlate with the physician global assessment (PGA) and/or endoscopic findings in patients with CD. Methods: A retrospective review of the imaging archive from 3/2002–3/2006 identified 23 patients (16M,7F, avg age = 51.3yr) with known or suspected CD with at least 2 CTE exams. Using electronic chart review, PGA (based on history, physical exam, and laboratory studies) at the time of each CTE&results of endoscopic exams performed within 6 months of CTE were recorded. A single radiologist blinded to patient history&endoscopic results reviewed all CTE exams&recorded the presence or absence of CD in the small bowel and/or colon (mucosal hyper-enhancement and/or wall thickening > 3 mm)&if findings worsened, improved or remained stable between exams. Imaging results were compared to PGA and endoscopic findings when available. Results: Mean time between CTE exams was 10.7 mos (1–26 mos). 14 colonoscopies with ileoscopies in 13 patients and 2 capsule studies (CE) in 2 patients were performed. 5 patients had multiple endoscopic exams. Observed agreement between imaging changes on CTE and PGA was 22/23 (96%). Estimated kappa (95% CI) was 0.92 (0.78,1.00). In 13/14 (93%) comparisons, worsening PGA correlated with disease progression by imaging findings at CTE. In 4/4 comparisons, improvement in PGA correlated with improved imaging findings at CTE. In 5/5 comparisons, PGA&CTE findings remained stable. Overall, 13/14 (93%) colonoscopy with ileoscopy results matched CTE findings. Findings which did not correlate included 1 patient with erosions in the ileum but no GI symptoms&negative CTE. Both CE studies correlated with PGA and imaging findings. In a subgroup of patients with sequential endoscopies, observed agreement between endoscopic changes&CTE was 4/5 (80%). In 1/5 patients, PGA & endoscopic findings showed disease progression while CTE findings improved. Conclusions: These results suggest that sequential CTE exams appear to be an excellent tool for assessing changes in CD activity. CTE appears to have high correlation with PGA and endoscopic findings. Large prospective studies are needed to confirm these results.