Automatic detection of Crohn's disease using quantified motility in magnetic resonance enterography: initial experiences

Arkko, Anssi-P; Kaseva, Tuomas; Salli, Eero; Mäkelä, Teemu; Savolainen, Sauli; Kangasniemi, Marko

doi:10.1016/j.crad.2021.10.006

Cited by 9 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have investigated numerous metrics to assess intestinal inflammation and stricture using MRE data [30][31][32] [36]. However, their model's performance deteriorated by about 30% in the other two datasets tested, highlighting that further investigation is needed to validate this approach.…”

Section: Machine Learning In Radiologymentioning

confidence: 99%

“…Notably, their model was trained on data that can be derived from MRE without intravenously administered contrast, increasing accessibility to this technique. Similarly, Arkko et al developed a machine learning method to detect Crohn's disease using quantified motility measurements from MRE data, which performed well in the dataset with high-pixel resolution, low temporal resolution, and high temporal length [36]. However, their model's performance deteriorated by about 30% in the other two datasets tested, highlighting that further investigation is needed to validate this approach.…”

Section: Machine Learning In Radiologymentioning

confidence: 99%

See 1 more Smart Citation

Machine and deep learning in inflammatory bowel disease

Zulqarnain¹,

Rhoads²,

Syed³

2023

Current Opinion in Gastroenterology

View full text Add to dashboard Cite

Purpose of reviewThe Management of inflammatory bowel disease (IBD) has evolved with the introduction and widespread adoption of biologic agents; however, the advent of artificial intelligence technologies like machine learning and deep learning presents another watershed moment in IBD treatment. Interest in these methods in IBD research has increased over the past 10 years, and they offer a promising path to better clinical outcomes for IBD patients.Recent findingsDeveloping new tools to evaluate IBD and inform clinical management is challenging because of the expansive volume of data and requisite manual interpretation of data. Recently, machine and deep learning models have been used to streamline diagnosis and evaluation of IBD by automating review of data from several diagnostic modalities with high accuracy. These methods decrease the amount of time that clinicians spend manually reviewing data to formulate an assessment.SummaryInterest in machine and deep learning is increasing in medicine, and these methods are poised to revolutionize the way that we treat IBD. Here, we highlight the recent advances in using these technologies to evaluate IBD and discuss the ways that they can be leveraged to improve clinical outcomes.

show abstract

Section: Machine Learning In Radiologymentioning

confidence: 99%

Section: Machine Learning In Radiologymentioning

confidence: 99%

Machine and deep learning in inflammatory bowel disease

Zulqarnain¹,

Rhoads²,

Syed³

2023

Current Opinion in Gastroenterology

View full text Add to dashboard Cite

show abstract

Section: Search Strategymentioning

confidence: 99%

“…62 Terminal ileum motility was found to be negatively associated with CD activity, which might be a candidate biomarker for monitoring disease progression and treatment efficacy. 62,63 Radiomics is a popular form of radiologic imaging analysis aiming to extract high-dimensional imaging features to reveal subtle disease characteristics. 64 Li et al 49 developed a novel CTE-based RM to assess intestinal fibrosis in CD patients, which substantially improved the quantitation of CTE in intestinal fibrosis.…”

Section: Assessment Of Intestinal Stricturesmentioning

confidence: 99%

Intestinal strictures in Crohn’s disease: a 2021 update

Lin

Wang

Liu

et al. 2022

Therap Adv Gastroenterol

View full text Add to dashboard Cite

Intestinal strictures remain one of the most intractable and common complications of Crohn’s disease (CD). Approximately 70% of CD patients will develop fibrotic strictures after 10 years of CD diagnosis. Since specific antifibrotic therapies are unavailable, endoscopic balloon dilation and surgery remain the mainstay treatments despite a high recurrence rate. Besides, there are no reliable methods for accurately evaluating intestinal fibrosis. This is largely due to the fact that the mechanisms of initiation and propagation of intestinal fibrosis are poorly understood. There is growing evidence implying that the pathogenesis of stricturing CD involves the intricate interplay of factors including aberrant immune and nonimmune responses, host-microbiome dysbiosis, and genetic susceptibility. Currently, the progress on intestinal strictures has been fueled by the advent of novel techniques, such as single-cell sequencing, multi-omics, and artificial intelligence. Here, we perform a timely and comprehensive review of the substantial advances in intestinal strictures in 2021, aiming to provide prompt information regarding fibrosis and set the stage for the improvement of diagnosis, treatment, and prognosis of intestinal strictures.

show abstract

“…CNNs, a type of deep learning (Figure 1), excel in pattern recognition and are affecting the way in which medical images can be analyzed 12,13 . This technology offers an innovative approach to diagnosing and monitoring CD activity [14][15][16][17] .…”

Section: Introductionmentioning

confidence: 99%

Deep Learning in Magnetic Resonance Enterography for Crohn’s Disease Assessment: A Systematic Review

Brem,

Elisha,

Konen

et al. 2023

Preprint

View full text Add to dashboard Cite

Crohn’s disease (CD) poses significant morbidity, underscoring the need for effective, non-invasive inflammatory assessment using magnetic resonance enterography (MRE).This literature review evaluates recent publications on deep learning’s role in enhancing MRE segmentation, image quality, and visualization of inflammatory activity related to CD.We searched MEDLINE/PUBMED for studies that reported the use of deep learning algorithms for assessment of CD activity. The study was conducted according to the PRISMA guidelines. The risk of bias was evaluated using the QUADAS_J2 tool.Five eligible studies, encompassing 468 subjects, were identified.Our study suggests that diverse deep learning applications, including image quality enhancement, bowel segmentation, and motility measurement are useful and promising for CD assessment. However, most of the studies are preliminary, retrospective studies, and have a high risk of bias in at least one category.Future research is needed to assess how automated deep learning can impact patient care, especially when considering the increasing integration of these models into hospital systems.

show abstract

Automatic detection of Crohn's disease using quantified motility in magnetic resonance enterography: initial experiences

Cited by 9 publications

References 26 publications

Machine and deep learning in inflammatory bowel disease

Machine and deep learning in inflammatory bowel disease

Intestinal strictures in Crohn’s disease: a 2021 update

Deep Learning in Magnetic Resonance Enterography for Crohn’s Disease Assessment: A Systematic Review

Contact Info

Product

Resources

About