Intestinal fibrosis classification in patients with Crohn’s disease using CT enterography–based deep learning: comparisons with radiomics and radiologists

Meng, Jixin; Luo, Zixin; Chen, Zhihui; Zhou, Jie; Zhao, Chen; Lu, Baolan; Zhang, Mengchen; Wang, Yangdi; Yuan, Chenglang; Shen, Xiao-di; Huang, Qinqin; Zhang, Zhuya; Ye, Ziyin; Cao, Qinghua; Zhou, Zhiyang; Xu, Yikai; Mao, Ren; Chen, Minhu; Sun, Canhui; Li, Ziping; Feng, Shi‐Ting; Meng, Xiaochun; Huang, Bingsheng; Li, Xuehua

doi:10.1007/s00330-022-08842-z

Cited by 42 publications

(23 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A later study suggested that deep learning models (i.e. multi‐layer neural networks) may be more efficient than radiomics while maintaining similar performance characteristics, and still outperforming radiologist assessments 52 . Although an expert IBD pathologist scored the histopathological samples in both studies, neither employed a validated scoring system, nor comprehensively evaluated all histomorphological components of a stricture.…”

Section: Characterization Of CD Strictures On Routine Cross‐sectional...mentioning

confidence: 99%

Crohn's disease related strictures in cross‐sectional imaging: More than meets the eye?

et al. 2022

View full text Add to dashboard Cite

Strictures in Crohn's disease (CD) are a hallmark of long‐standing intestinal damage, brought about by inflammatory and non‐inflammatory pathways. Understanding the complex pathophysiology related to inflammatory infiltrates, extracellular matrix deposition, as well as muscular hyperplasia is crucial to produce high‐quality scoring indices for assessing CD strictures. In addition, cross‐sectional imaging modalities are the primary tool for diagnosis and follow‐up of strictures, especially with the initiation of anti‐fibrotic therapy clinical trials. This in turn requires such modalities to both diagnose strictures with high accuracy, as well as be able to delineate the impact of each histomorphologic component on the individual stricture. We discuss the current knowledge on cross‐sectional imaging modalities used for stricturing CD, with an emphasis on histomorphologic correlates, novel imaging parameters which may improve segregation between inflammatory, muscular, and fibrotic stricture components, as well as a future outlook on the role of artificial intelligence in this field of gastroenterology.

show abstract

Section: Characterization Of CD Strictures On Routine Cross‐sectional...mentioning

confidence: 99%

Crohn's disease related strictures in cross‐sectional imaging: More than meets the eye?

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Conventional CTE bowel features cannot satisfactorily characterize bowel fibrosis unless novel image analysis methods are employed, such as radiomics or deep learning. 13,26 Contrarily, our study attached great importance to abnormalities of the mesentery. We analysed not only many conventional mesenteric findings, such as the comb sign and mesenteric oedema, but also the degree of CF wrapping around the inflamed gut (i.e.…”

Section: Discussionmentioning

confidence: 92%

Mesenteric abnormalities play an important role in grading intestinal fibrosis in patients with Crohn’s disease: a computed tomography and clinical marker-based nomogram

Meng

Mao

Zhou

et al. 2022

Therap Adv Gastroenterol

Self Cite

View full text Add to dashboard Cite

Background: While the grading of intestinal fibrosis is closely related to the therapeutic strategy of patients with Crohn’s disease (CD), it has not yet been well resolved. Mesenteric abnormalities are inextricably linked to intestinal fibrosis. Objectives: We aimed to establish an optimal model for assessing intestinal fibrosis using computed tomography enterography (CTE) and clinical markers. Design: A total of 174 patients with CD between January 2014 and June 2020 were included in this retrospective multicentre study. Methods: All patients underwent CTE within 3 months prior to surgery. Intestinal fibrosis was pathologically scored as non-mild or moderate-to-severe. Selected imaging of the intestinal walls and mesentery and/or clinical factors were used to develop the diagnostic models. The area under the receiver operating characteristic curve (AUC) analysis was used to evaluate the discrimination performance of the models. A decision curve analysis was performed to evaluate the clinical usefulness of the models. Results: One-, two-, and three-variable models were identified as possible diagnostic models. Model 1 [mesenteric creeping fat index (MCFI)], Model 2 (mesenteric oedema and MCFI), and Model 3 (mesenteric oedema, MCFI, and disease duration) were established. The AUCs of Model 1 in training and test cohorts 1 and 2 were 0.799, 0.859, and 0.693, respectively; Model 2 was 0.851, 0.833, and 0.757, respectively; and Model 3 was 0.832, 0.821, and 0.850, respectively. We did not observe any significant difference in diagnostic performance between the training and total test cohorts in any model (all p > 0.05). The decision curves showed that Model 3 had the highest net clinical benefit in test cohort 2. The nomogram of this optimal model was constructed by considering the favourable and robust performance of Model 3. Conclusion: A nomogram integrating mesenteric abnormalities on CTE with a clinical marker was optimal for differentiating between non-mild and moderate-to-severe fibrosis in patients with CD.

show abstract

“…The advent of artificial intelligence (AI), particularly machine learning, has opened an avenue for the efficient integration and interpretation The diagnostic performance of the deep learning model was not inferior to that of the prior radiomic model, but it was more timesaving than the radiomic model (48.4 vs. 599.8 s). 54 Notably, both radiomic and deep learning models significantly outperformed the radiologist's interpretation of fibrosis grading. 53 Hence, the application of AI has the potential to help radiologists diagnose fibrosis more accurately and quickly.…”

Section: Ai In Stricturementioning

confidence: 99%

Inflammatory bowel disease cross‐sectional imaging: What's new?

et al. 2022

Self Cite

View full text Add to dashboard Cite

Cross‐sectional imaging—ultrasonography, computed tomography enterography, and magnetic resonance enterography—is a routine and indispensable tool for patients with Crohn's disease (CD) that helps to detect or monitor disease characteristics before, during, and after CD treatment. New emerging radiological technologies may have further clinical applications in the management of CD. In this review article, we focus on the latest developments in cross‐sectional imaging in CD research, including its role in intra‐ and extra‐luminal lesion detection, intestinal inflammation and fibrosis grading, therapeutic response assessment and outcome prediction, postoperative recurrence detection and prediction, and the gut‐brain axis.

show abstract

Intestinal fibrosis classification in patients with Crohn’s disease using CT enterography–based deep learning: comparisons with radiomics and radiologists

Cited by 42 publications

References 37 publications

Crohn's disease related strictures in cross‐sectional imaging: More than meets the eye?

Crohn's disease related strictures in cross‐sectional imaging: More than meets the eye?

Mesenteric abnormalities play an important role in grading intestinal fibrosis in patients with Crohn’s disease: a computed tomography and clinical marker-based nomogram

Inflammatory bowel disease cross‐sectional imaging: What's new?

Contact Info

Product

Resources

About