Development and Validation of a Novel Computed-Tomography Enterography Radiomic Approach for Characterization of Intestinal Fibrosis in Crohn’s Disease

Li, Xuehua; Dong, Liang; Meng, Jixin; Zhou, Jie; Zhao, Chen; Huang, Shu‐Chun; Lu, Baolan; Qiu, Yun; Baker, Mark E.; Ye, Ziyin; Cao, Qinghua; Wang, Mingyu; Yuan, Chenglang; Chen, Zhihui; Feng, Shengyu; Zhang, Yuxuan; Iacucci, Marietta; Ghosh, Subrata; Rieder, Florian; Sun, Canhui; Chen, Minhu; Li, Ziping; Mao, Ren; Huang, Bingsheng; Feng, Shi Ting

doi:10.1053/j.gastro.2021.02.027

Cited by 68 publications

(62 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Contrast agent (320 mgI/mL) was injected at 1.5 mL/kg bodyweight via peripheral veins at 3.0 mL/s. Similar to other small intestinal radiomics studies, 19 We used venous phase CTE images after a delay of 70 seconds to delineate lesions and extract image features.…”

Section: Methodsmentioning

confidence: 99%

“… 13 Radiomics has been applied widely in colorectal cancer, 14–17 but it is also being applied gradually to inflammatory bowel disease. For example, radiomics has been used to predict the loss of the secondary response to infliximab in CD, 18 to measure intestinal fibrosis in CD, 19 and to distinguish CD from ulcerative colitis, 20 all of which had good diagnostic efficacy. However, use of radiomics to distinguish CD from ITB has not been undertaken.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Clinical Radiomics Nomogram to Identify Crohn’s Disease from Intestinal Tuberculosis

Zhu

Wang

et al. 2021

JIR

View full text Add to dashboard Cite

Purpose To establish a clinical radiomics nomogram to differentiate Crohn’s disease (CD) from intestinal tuberculosis (ITB). Patients and Methods Ninety-three patients with CD and 67 patients with ITB were recruited (111 in training cohort and 49 in test cohort). The region of interest (ROI) for the lesions in the ileocecal region was delineated on computed tomography enterography and radiomics features extracted. Radiomics features were filtered by the gradient boosting decision tree (GBDT), and a radiomics score was calculated by using the radiomics signature-based formula. We constructed a clinical radiomics model and nomogram combining clinical factors and radiomics score through multivariate logistic regression analysis, and the internal validation was undertaken by ten-fold cross validation. Analyses of receiver operating characteristic (ROC) curves and decision curve analysis (DCA) were used to evaluate the prediction performance. DeLong test was applied to evaluate the performance of the clinical, radiomics and combined model. Results The clinical radiomics nomogram, which was based on the 9 radiomics signature and two clinical factors, indicated that the clinical radiomics model had an area under the ROC curve (AUC) value of 0.96 (95% confidence interval [CI]: 0.93–0.99) in the training cohort and 0.93 (95% CI: 0.86–1.00) in validation cohort. The clinical radiomics model was superior to the clinical model and radiomics model, and the difference was significant ( P = 0.006, 0.004) in the training cohort. DCA confirmed the clinical utility of clinical radiomics nomogram. Conclusion CTE-based radiomics model has a good performance in distinguishing CD from ITB. A nomogram constructed by combining radiomics and clinical factors can help clinicians accurately diagnose and select appropriate treatment strategies between CD and ITB.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Clinical Radiomics Nomogram to Identify Crohn’s Disease from Intestinal Tuberculosis

Zhu

Wang

et al. 2021

JIR

View full text Add to dashboard Cite

show abstract

“…Stidham et al reported that structural bowel damage measurements of CT enterography data in CD by semiautomated approaches are comparable to those of experienced radiologists 18. Furthermore, radiomics models can predict moderate to severe histological intestinal fibrosis more accurately than skilled radiologists 19…”

Section: Ai In Ibd Diagnosismentioning

confidence: 99%

Artificial intelligence and inflammatory bowel disease: practicalities and future prospects

Brooks-Warburton

Ashton

Dhar

et al. 2021

Frontline Gastroenterol

View full text Add to dashboard Cite

Artificial intelligence (AI) is an emerging technology predicted to have significant applications in healthcare. This review highlights AI applications that impact the patient journey in inflammatory bowel disease (IBD), from genomics to endoscopic applications in disease classification, stratification and self-monitoring to risk stratification for personalised management. We discuss the practical AI applications currently in use while giving a balanced view of concerns and pitfalls and look to the future with the potential of where AI can provide significant value to the care of the patient with IBD.

show abstract

“…This retrospective analysis of 138 exams showed very good maximum bowel wall thickness correlation between the semi-automated method and the mean measurement performed by two radiologists (r=0.702). Another retrospective, multicentre, CT enterography study on 167 patients aimed to classify bowel fibrosis by developing a radiomics model based on machine learning 40. In the test cohort, the radiomics model had good performance across the three centres, with area under the curve (AUC) between 0.724 and 0.816.…”

Section: Automation and Aimentioning

confidence: 99%

Imaging in inflammatory bowel disease: current and future perspectives

Shaban

Hoad

Naim

et al. 2022

Frontline Gastroenterol

View full text Add to dashboard Cite

The use of cross-sectional imaging and ultrasonography has long complemented endoscopic assessment of inflammatory bowel disease (IBD). Clinical symptoms alone are often not enough to assess disease activity, so a reliance on non-invasive techniques is essential. In this paper, we aim to examine the current use of radiological modalities in aiding the management of patients with IBD. We focus on the various sections of the gastrointestinal tract and how different modalities can aid in assessing current disease state and response to treatments. We also have a look at how newer sequences in cross-sectional imaging and ultrasonography can allow for better differentiation of disease activity (ie, fibrotic vs inflammatory) as well improve evaluation of small bowel, colonic and perianal disease. Furthermore, we examine how advanced image processing has the potential to allow radiology to be a surrogate for biomarkers. An example of this is explored when reviewing the ability of MR sequences to quantify visceral fat, which potentially plays a role in determining disease activity in Crohn’s disease. Lastly, we look into the expected role for artificial intelligence to be used as an adjunct to radiology to better improve IBD evaluation.

show abstract

Development and Validation of a Novel Computed-Tomography Enterography Radiomic Approach for Characterization of Intestinal Fibrosis in Crohn’s Disease

Cited by 68 publications

References 48 publications

A Novel Clinical Radiomics Nomogram to Identify Crohn’s Disease from Intestinal Tuberculosis

A Novel Clinical Radiomics Nomogram to Identify Crohn’s Disease from Intestinal Tuberculosis

Artificial intelligence and inflammatory bowel disease: practicalities and future prospects

Imaging in inflammatory bowel disease: current and future perspectives

Contact Info

Product

Resources

About