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

Computed tomography enterography radiomics and machine learning for identification of Crohn's disease

BACKGROUND

Crohn's disease is a severe chronic and relapsing inflammatory bowel disease. Although contrast-enhanced computed tomography enterography is commonly used to evaluate crohn's disease, its imaging findings are often nonspecific and can overlap with other bowel diseases. Recent studies have explored the application of radiomics-based machine learning algorithms to aid in the diagnosis of medical images. This study aims to develop a non-invasive method for detecting bowel lesions associated with Crohn's disease using CT enterography radiomics and machine learning algorithms.

METHODS

A total of 139 patients with pathologically confirmed Crohn's disease were retrospectively enrolled in this study. Radiomics features were extracted from both arterial- and venous-phase CT enterography images, representing both bowel lesions with Crohn's disease and segments of normal bowel. A machine learning classification system was constructed by combining six selected radiomics features with eight classification algorithms. The models were trained using leave-one-out cross-validation and evaluated for accuracy.

RESULTS

The classification model demonstrated robust performance and high accuracy, with an area under the curve of 0.938 and 0.961 for the arterial- and venous-phase images, respectively. The model achieved an accuracy of 0.938 for arterial-phase images and 0.961 for venous-phase images.

CONCLUSIONS

This study successfully identified a radiomics machine learning method that effectively differentiates Crohn's disease bowel lesions from normal bowel segments. Further studies with larger sample sizes and external cohorts are needed to validate these findings.

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.

Clinical implication of radiologic complete remission on Crohn's Disease: Compared with endoscopic remission

OBJECTIVES

To determine the clinical implications of radiologic complete remission (CR) in Crohn's disease (CD) evaluated by computed tomography (CT) or magnetic resonance enterography (MRE) in comparison with endoscopic CR.

METHODS

Twenty-five CD patients who achieved endoscopic CR after medical treatment were retrospectively enrolled in this study. All patients underwent ileocolonoscopy, CT, or MRE at baseline, at the time of endoscopic CR, and during follow-up. Two radiologists assessed the mural and perienteric abnormalities on pre- and post-treatment CT or MRE in consensus. Patients were divided into radiologic CR and non-CR groups at the time of endoscopic CR. CD recurrence during subsequent follow-up periods was evaluated using clinical, laboratory, and CT/MRI findings. Statistical analysis was performed to assess whether there were significant differences in patient outcomes between the groups.

RESULTS

At the time of endoscopic CR, nine patients (mean age, 36.6 years) showed normalization of all radiologic features and were designated as the radiologic CR group. However, 16 patients (mean age: 32.9 years) showed residual CT/MRE abnormalities, suggesting persistent active inflammation, and were designated as the radiologic non-CR group. During follow-up, there was a significant difference between the groups regarding clinical outcomes (deep CR, 8/9 vs 5/16, P = 0.011; CD recurrence, 1/9 vs 14/16, P < 0.001). The mean fecal calprotectin level was significantly lower in the radiologic CR group (287.5 ug/g) than in the non-CR group (652.4 ug/g) (P = 0.023).

CONCLUSIONS

Radiologic CR can represent a better therapeutic endpoint in CD, showing superiority over endoscopic CR in predicting both clinical and biochemical outcomes.