Novel Dual-Energy Computed Tomography Enterography Iodine Density Maps Provide Unique Depiction of Crohn Disease Activity

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.

Accuracy of iodine quantification in dual energy CT: A phantom study across 3 different CT systems

INTRODUCTION

No study has rigorously compared the performances of iodine quantification on recent CT systems employing different emission-based technologies, depending on the manufacturers and models.

METHODS

A specific bespoke phantom was used for this study, with 12 known concentrations of iodinated contrast agent: 0.4, 0.5, 1.0, 2.0, 3.0, 4.0, 5.0, 10.0, 15.0, 20.0, 30.0 and 50.0 mg/mL. Three different dual-energy scanners were tested: one system using dual-source acquisition (CT#1) and two systems using Fast kilovolt-peak switching technology ± artificial intelligence (AI) reconstruction methods (CT#2 and #3) from two different manufacturers. For each system, helical scans were performed following recommended clinical protocols. Four acquisitions were performed per iodine concentration (mg/mL), and measurements were made on iodine-maps using ROIs. Mean measured values were compared to the known concentrations, and the absolute quantification error (AQE) and the relative percentage error (RPE) were used to compare the performances of each CT.

RESULTS

The accuracy of the obtained measurements varied depending on the studied model but not on the acquisition mode (dual-source vs kVp switch ± AI). The quantification was more precise at high concentrations. RPE values were below 10 % with CT#2 (kVp switch) and below 25 % with CT#1 (dual-source), but were significantly higher with CT#3 (kVp switch + AI), exceeding 50 % at low concentrations (<3 mg/mL).

CONCLUSIONS

With the help of a phantom, we identified variability in the results accuracy depending on the CT model, with sometimes significant deviation. Considering the performances of the different DECT technologies in iodine mapping, dual-source (CT#1) and kVp switch (CT#2) technologies appear more accurate than kVp switch technology combined with deep-learning-based reconstruction (CT#3) especially at low concentrations (<3 mg/mL).

IMPLICATIONS FOR PRACTICE

As the primary and daily user of medical imaging devices, the radiographer role is to be attentive to the performance of imaging systems, particularly when performing quantitative acquisitions like iodine-quantification. In CT quantitative imaging (iodine map), it's essential for radiographers to consider their CT systems as measuring tools, and to be aware of their accuracies and limits.

Application of multi-spectral CT imaging in Crohn's disease: a systematic review

BACKGROUND

No quantitative computed tomography (CT) biomarker is actually sufficiently accurate to assess Crohn's disease (CD) lesion activity, with adequate precision to guide clinical decisions.

PURPOSE

To assess the available literature on the use of iodine concentration (IC), from multi-spectral CT acquisition, as a quantitative parameter able to distinguish healthy from affected bowel and assess CD bowel activity and heterogeneity of activity along the involved segments.

MATERIAL AND METHODS

A literature search was conducted to identify original research studies published up to February 2022. The inclusion criteria were original research papers (>10 human participants), English language publications, focus on dual-energy CT (DECT) of CD with iodine quantification (IQ) as an outcome measure. The exclusion criteria were animal-only studies, languages other than English, review articles, case reports, correspondence, and study populations <10 patients.

RESULTS

Nine studies were included in this review; all of which showed a strong correlation between IC measurements and CD activity markers, such as CD activity index (CDAI), endoscopy findings and simple endoscopic score for Crohn's disease (SES-CD), and routine CT enterography (CTE) signs and histopathologic score. Statistically significant differences in IC were reported between affected bowel segments and healthy ones (higher P value was P < 0.001), normal segments and those with active inflammation (P < 0.0001) as well as between patients with active disease and those in remission (P < 0.001).

CONCLUSION

The mean normalized IC at DECTE could be a reliable tool in assisting radiologists in the diagnosis, classification and grading of CD activity.

Crohn's disease active inflammation assessment with iodine density from dual-energy CT enterography: comparison with endoscopy and conventional interpretation

PURPOSE

To compare terminal ileum (TI) mucosal iodine density obtained at dual-energy CT enterography (DECTE) with conventional CT interpretation and endoscopy in patients with Crohn's disease (CD).

MATERIALS AND METHODS

Twenty-three CD patients (14 men; mean[SD] age:48.1[16.7] years) with endoscopy within 30 days of DECTE were retrospectively identified. An inflammatory bowel disease gastroenterologist reviewed endoscopic images. Two radiologists qualitatively assessed the presence of active TI inflammation. Mean iodine density normalized to the aorta (I%), mean absolute iodine density (I), and iodine density standard deviation (I_SD) from the distal 2 cm ileum (TI) mucosa obtained using semiautomatic prototype software were compared with endoscopic assessment using Mann Whitney tests. The optimal threshold I% and I were determined from receiver operating curves (ROC). Sensitivity and specificity of conventional interpretation and determined iodine thresholds were compared using McNemar's test. Inter-reader agreement was assessed using kappa. A p < 0.05 indicated statistical significance.

RESULTS

Twelve (52.1%) patients had endoscopic active inflammation. I% was 37.9[13.3]% for patients with and 21.7[7.5]% for patients without endoscopic active inflammation (p = 0.001). The optimal ROC threshold 24.6% had 100% sensitivity and 81.8% specificity (AUC = 0.909, 95% CI 0.777-1). I was 2.44[0.73]mg/mL for patients with and 1.77[1.00]mg/mL for patients without active endoscopic inflammation (p = 0.0455). The optimal ROC threshold 1.78 mg/mL I had 91.7% sensitivity and 63.6% specificity (AUC = 0.75, 95% CI 0.532-0.968). I_SD was similar for patients with and without endoscopic active inflammation (0.82[0.33]mg/mL and 0.77[0.28]mg/mL, respectively, p = 0.37). Conventional interpretation sensitivity and specificity (R1/R2) were 83.3%/91.7% and 72.7%/54.5%, respectively (all p > 0.05) with moderate inter-reader agreement (Κ = 0.542[95% CI 0.0202-0.088]).

CONCLUSION

Mean normalized iodine density is highly sensitive and specific for endoscopic active inflammation. DECTE could be considered as a surrogate to endoscopy in CD patients. Despite trends towards improved sensitivity and specificity compared with conventional interpretation, future larger studies are needed.

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.

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.