Dual-energy CT enterography in evaluation of Crohn's disease: the role of virtual monochromatic images

Establishing a machine learning model based on dual-energy CT enterography to evaluate Crohn's disease activity

OBJECTIVES

The simplified endoscopic score of Crohn's disease (SES-CD) is the gold standard for quantitatively evaluating Crohn's disease (CD) activity but is invasive. This study aimed to develop and validate a machine learning (ML) model based on dual-energy CT enterography (DECTE) to noninvasively evaluate CD activity.

METHODS

We evaluated the activity in 202 bowel segments of 46 CD patients according to the SES-CD score and divided the segments randomly into training set and testing set at a ratio of 7:3. Least absolute shrinkage and selection operator (LASSO) was used for feature selection, and three models based on significant parameters were established based on logistic regression. Model performance was evaluated using receiver operating characteristic (ROC), calibration, and clinical decision curves.

RESULTS

There were 110 active and 92 inactive bowel segments. In univariate analysis, the slope of spectral curve in the venous phases (λHU-V) has the best diagnostic performance, with an area under the ROC curve (AUC) of 0.81 and an optimal threshold of 1.975. In the testing set, the AUC of the three models established by the 7 variables to differentiate CD activity was 0.81-0.87 (DeLong test p value was 0.071-0.766, p > 0.05), and the combined model had the highest AUC of 0.87 (95% confidence interval (CI): 0.779-0.959).

CONCLUSIONS

The ML model based the DECTE can feasibly evaluate CD activity, and DECTE parameters provide a quantitative analysis basis for evaluating specific bowel activities in CD patients.

CRITICAL RELEVANCE STATEMENT

The machine learning model based on dual-energy computed tomography enterography can be used for evaluating Crohn's disease activity noninvasively and quantitatively.

KEY POINTS

Dual-energy CT parameters are related to Crohn's disease activity. Three machine learning models effectively evaluated Crohn's disease activity. Combined models based on conventional and dual-energy CT have the best performance.

Mucosal healing assessment in Crohn's disease with normalized iodine concentration from dual-energy CT enterography: comparison with endoscopy

OBJECTIVES

Mucosal healing (MH) is an important goal in the treatment of patients with Crohn's disease (CD). Noninvasive assessment of MH with normalized iodine concentration (NIC) is unknown.

METHODS

In this retrospective study, 94 patients with diagnosed CD underwent endoscopy and dual-energy CT enterography (DECTE) at the post-infliximab treatment review. Two radiologists reviewed DECTE images by consensus for assessing diseased bowel segments of the colon or terminal ileum, and the NIC was measured. Patients were divided into transmural healing (TH), MH and non-MH groups. The diagnostic performance of the MH and non-MH groups with clinical factors and NIC was assessed utilizing receiver operating characteristic (ROC) curve analysis.

RESULTS

Of the 94 patients included in our study, 8 patients achieved TH, 34 patients achieved MH, and 52 patients did not achieve MH at the post-IFX treatment review. The area under the ROC curve (AUC), sensitivity, specificity, and accuracy values were 0.929 (95% confidence interval [CI] 0.883-0.967), 0.853, 0.827, and 0.837, respectively, for differentiating MHs from non-MHs, and the optimal NIC threshold was 0.448. The AUC of the combined model for distinguishing MHs from non-MHs in CD patients, which was based on the NIC and calprotectin, was 0.964 (95% CI 0.935-0.987).

CONCLUSIONS

The normalized iodine concentration measurement in DECTE has good performance in assessment MH in patients with CD. Iodine concentration from DECTE can be used as a radiologic marker for MH.

Dual energy computed tomography in Crohn's disease: a targeted review

INTRODUCTION

Crohn's disease (CD) is a common chronic inflammatory bowel disease characterized by transmural inflammation and extra-intestinal complications. The diagnosis of CD is made using a combination of clinical, biochemical, endoscopic, imaging and histological features. Among imaging methods, computed tomography enterography (CTE) is the most commonly used. Dual-energy CTE allows objective evaluation of patients with CD. Along with the findings seen in conventional CTE, dual-energy CTE can generate iodine density maps and quantify the iodine content in the involved segments of the bowel, thus providing a measure of the perfusion of the affected bowel. In addition, the virtual monochromatic images generated from dual-energy CTE allow better qualitative evaluation of the mural and extramural findings.

AREAS COVERED

We performed a targeted systemic review of all the studies in the literature to understand the role of dual-energy CT in the diagnosis and assessment of the severity of CD.

EXPERT OPINION

Dual-energy CTE is superior to conventional CTE in the evaluation of CD. Besides quantifying iodine in the pathological segments, other quantitative parameters like the mural thickness of affected bowel segments, the number of segments involved, ulcerations, comb sign, lymphadenopathy, and the mural heterogeneity can also be assessed in dual-energy CTE.

Role of Dual Energy Computed Tomography in Inflammatory Bowel Disease

Dual-energy computed tomography (DECT), which allows material-based differential X-ray absorption behavior from near simultaneously acquired low- and high-kilovolt datasets is finding increasing applications in the evaluation of bowel diseases. In patients with inflammatory bowel disease, DECT techniques permit both qualitative and quantitative assessment. Particularly in patients with Crohn's disease, monoenergetic and iodine specific images have been explored. This article focuses on the principles and applications of DECT in inflammatory bowel disease along with review of its limitations and challenges.

Virtual Non-contrast Imaging in The Abdomen and The Pelvis: An Overview

Virtual non-contrast (VNC) imaging is a post-processing technique generated from contrast-enhanced scans using dual-energy computed tomography (DECT). It is generated by removing iodine from imaging acquired at multiple energies. Myriad clinical studies have shown its ability to diagnose the various abdominal and pelvic pathologies discussed in the article. VNC is also a problem-solving tool for characterizing incidentally detected lesions ("incidentalomas"), often decreasing the need for additional follow-up imaging. It also obviates the multiphase image acquisitions to evaluate hematuria, hepatic steatosis, aortic endoleaks, and gastrointestinal bleeding by generating image datasets from different tissue attenuation values. The scope of this article is to provide an overview of various applications of VNC imaging obtained by DECT in the abdomen and pelvis.

Crohn Disease Active Inflammation Assessment with Iodine Density from Dual-Energy CT Enterography: Comparison with Histopathologic Analysis

Background Dual-energy CT enterography (DECTE) has been shown to be useful in characterizing Crohn disease activity compared with clinical markers of inflammation but, to the knowledge of the authors, comparison has not been made with histopathologic specimens. Purpose To compare mucosal iodine density obtained at DECTE from Crohn disease-affected bowel with histopathologic specimens from surgically resected ileocolectomy bowel segments or terminal ileum colonoscopic biopsies in the same patients. Materials and Methods This was a retrospective study. Bowel segments in adults with Crohn disease who underwent DECTE from January 2017 to April 2019 within 90 days of ileocolectomy or colonoscopy were retrospectively evaluated with prototype software allowing the semiautomatic determination of inner hyperdense bowel wall (mucosal) mean iodine density, normalized to the aorta. Mean normalized iodine density and clinical activity indexes (Crohn Disease Activity Index [CDAI] and Harvey-Bradshaw Index [HBI]) were compared with histologic active inflammation grades by using two-tailed t tests. Receiver operating characteristic curves were generated for mean normalized iodine density, CDAI, and HBI to determine sensitivity, specificity, and accuracy. A P value less than .05 was considered to indicate statistical significance. Results The following 16 patients were evaluated (mean age, 41 years ± 14 [standard deviation]): 10 patients (five men, five women; mean age, 41 years ± 15) with 19 surgical resection specimens and six patients with terminal ileum colonoscopic mucosal biopsies (four men, two women; mean age, 43 years ± 14). Mean normalized iodine density was 16.5% ± 5.7 for bowel segments with no active inflammation (n = 8) and 34.7% ± 9.7 for segments with any active inflammation (n = 17; P < .001). A 20% mean normalized iodine density threshold had sensitivity, specificity, and accuracy of 17 of 17 (100%; 95% CI: 80.5, 100), six of eight (75%; 95% CI: 35, 97), and 23 of 25 (92%; 95% CI: 74, 99), respectively, for active inflammation. Clinical indexes were similar for patients with and without active inflammation at histopathologic analysis (CDAI score, 261 vs 251, respectively [P = .77]; HBI score, 7.8 vs 6.4, respectively [P = .36]). Conclusion Iodine density from dual-energy CT enterography may be used as a radiologic marker of Crohn disease activity as correlated with histopathologic analysis. © RSNA, 2021 See also the editorial by Ohliger in this issue.

The Role of Dual-Energy Computed Tomography in Locating Gastrointestinal Tract Perforations

Objective With each passing day, dual-energy computed tomography (DECT) is being used more frequently in the evaluation of abdominal pathologies. In this article, we aimed to assess the role of dual-energy CT in locating gastrointestinal perforations, which are among the causes of acute abdomen. Materials and methods All patients who underwent DECT due to acute abdomen in a COVID-19 designated hospital between June 1st, 2020 and December 31st, 2020, who were found to have gastrointestinal tract (GIT) perforation and underwent surgery were included in the study. DECT results and intraoperative findings of the patients were compared. Results Thirteen patients (nine males and four females) who underwent DECT for acute abdomen and were diagnosed with perforation in the gastrointestinal system were included in the study. The mean age of the patients was 57.6 years (range: 11-85 years). Two patients had gastric perforation, three had duodenal perforations, and one patient had a perforation in the gallbladder wall. Two patients were diagnosed with jejunal perforations, one patient with Meckel's diverticulum, and three patients with colorectal perforation. Although free air was detected in the abdomen of one patient, perforation could not be located. In patients with GIT perforation who were operated on following DECT imaging, the perforation location shown on DECT correlated 100% with the perforation locations detected during surgery. Conclusion DECT is significantly effective in planning surgical treatment and determining the foci of perforation in GIT perforations.

Inflammatory Bowel Diseases and Coexisting Spondyloarthritis: A Neglected and too Often Under-Reported Association by Radiologists. A Multicenter Study by Italian Research Group of Imaging in Rheumatology

Purpose: The purpose of this study was to evaluate the prevalence and the underreporting rate of sacroiliitis (SI) in a large cohort of patients with biopsy-proved Crohn’s disease (CD) who underwent magnetic resonance enterography (MRE) or computed tomography enterography (CTE). Materials and Methods: Patients with CD were recruited from eight Italian health centers in the period from January 2013 to December 2017. Disease activity was recorded according to the CD activity index (CDAI). The scans were read by two blinded readers who defined the presence of SI according to Assessment of SpondyloArthritis International Society (ASAS) classifications and European League Against Rheumatism (EULAR) recommendations. Moreover, SI was scored using a simplified Spondyloarthritis Research Consortium of Canada (SPARCC) scoring system. Results: Interobserver agreement in diagnosing SI on imaging was good (K = 0.72–0.83). SI was diagnosed in 129 (14.4%, 54 men, 75 women) out of 894 patients; however, sacroiliac joint (SIJ) abnormalities were not mentioned in the radiological reports of 112 patients (86%). Fifty (38.7%) out of 129 patients also underwent a subsequent SIJ evaluation through a dedicated MRI protocol to confirm SI. SI was found in a higher percentage of patients with “active” than “inactive” CD (18% vs. 4%). Conclusion: This study confirms the feasibility of CTE and MRE for the screening of SI in CD patients; however, it also underlines the remarkable problem concerning the underreporting of this entity in radiological practice.