Novel Imaging Approaches in Inflammatory Bowel Diseases

DeepAIP: Deep learning for anti-inflammatory peptide prediction using pre-trained protein language model features based on contextual self-attention network

Non-steroidal anti-inflammatory drugs (NSAIDs), glucocorticoids, and other immunosuppressants are commonly used medications for treating inflammation. However, these drugs often come with numerous side effects. Therefore, finding more effective methods for inflammation treatment has become more necessary. The study of anti-inflammatory peptides can effectively address these issues. In this work, we propose a contextual self-attention deep learning model, coupled with features extracted from a pre-trained protein language model, to predict Anti-inflammatory Peptides (AIP). The contextual self-attention module can effectively enhance and learn the features extracted from the pre-trained protein language model, resulting in high accuracy to predict AIP. Additionally, we compared the performance of features extracted from popular pre-trained protein language models available in the market. Finally, Prot-T5 features demonstrated the best comprehensive performance as the input for our deep learning model named DeepAIP. Compared with existing methods on benchmark test dataset, DeepAIP gets higher Matthews Correlation Coefficient and Accuracy score than the second-best method by 16.35 % and 6.91 %, respectively. Performance comparison analysis was conducted using a dataset of 17 novel anti-inflammatory peptide sequences. DeepAIP demonstrates outstanding accuracy, correctly identifying all 17 peptide types as AIP and predicting values closer to the true ones. Data and code are available at https://github.com/YangQingGuoCCZU/DeepAIP.

Magnetic Resonance Enterography and Intestinal Ultrasound for the Assessment and Monitoring of Crohn's Disease

Magnetic resonance enterography [MRE] and intestinal ultrasound [IUS] have developed rapidly in the past few decades, emerging as the primary non-invasive options for both diagnosing and monitoring Crohn's disease [CD]. In this review, we evaluate the pertinent data relating to the use of MRE and IUS in CD. We summarise the key imaging features of CD activity, highlight their increasing role in both the clinical and the research settings, and discuss how these modalities fit within the diagnostic pathway. We discuss how they can be used to assess disease activity and treatment responsiveness, including the emergence of activity scores for standardised reporting. Additionally, we address areas of controversy such as the use of contrast agents, the role of diffusion-weighted imaging, and point-of-care ultrasound. We also highlight exciting new developments, including the applications of artificial intelligence. Finally, we provide suggestions for future research priorities.

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.

IF-AIP: A machine learning method for the identification of anti-inflammatory peptides using multi-feature fusion strategy

BACKGROUND

The most commonly used therapy currently for inflammatory and autoimmune diseases is nonspecific anti-inflammatory drugs, which have various hazardous side effects. Recently, some anti-inflammatory peptides (AIPs) have been found to be a substitute therapy for inflammatory diseases like rheumatoid arthritis and Alzheimer's. Therefore, the identification of these AIPs is an emerging topic that is equally important.

METHODS

In this work, we have proposed an identification model for AIPs using a voting classifier. We used eight different feature descriptors and five conventional machine-learning classifiers. The eight feature encodings were concatenated to get a hybrid feature set. The five baseline models trained on the hybrid feature set were integrated via a voting classifier. Finally, a feature selection algorithm was used to select the optimal feature set for the construction of our final model, named IF-AIP.

RESULTS

We tested the proposed model on two independent datasets. On independent data 1, the IF-AIP model shows an improvement of 3%-5.6% in terms of accuracies and 6.7%-10.8% in terms of MCC compared to the existing methods. On the independent dataset 2, our model IF-AIP shows an overall improvement of 2.9%-5.7% in terms of accuracy and 8.3%-8.6% in terms of MCC score compared to the existing methods. A comparative performance analysis was conducted between the proposed model and existing methods using a set of 24 novel peptide sequences. Notably, the IF-AIP method exhibited exceptional accuracy, correctly identifying all 24 peptides as AIPs. The source code, pre-trained models, and all datasets are made available at https://github.com/Mir-Saima/IF-AIP.

Current status of image-enhanced endoscopy in inflammatory bowel disease

In inflammatory bowel disease (IBD), chronic inflammation leads to unfavorable clinical outcomes and increases the risk of developing colorectal neoplasm (CRN); thereby highlighting the importance of endoscopically evaluating disease activity as well as detecting and characterizing CRN in patients with IBD. With recent advances in image-enhanced endoscopic (IEE) technologies, especially virtual chromoendoscopy (VCE) platforms, this review discusses state-of-the-art IEE techniques and their applicability in assessing disease activity and surveillance colonoscopy in patients with IBD. Among various IEE, VCE demonstrated the capacity to identify quiescent disease activity. And endoscopic remission defined by the new scoring system using VCE platform better predicted clinical outcomes, which may benefit the tailoring of therapeutic strategies in patients with IBD. High-definition dye-chromoendoscopy (HD-DCE) is numerically superior to high-definition white light endoscopy (HD-WLE) in detecting CRN in IBD; however, discrepancy is observed in the statistical significance. VCE showed comparable performance in detecting dysplasia to HD-WLE or DCE and potential for optical diagnosis to differentiate neoplastic from nonneoplastic lesions during surveillance colonoscopy. Applying these novel advanced IEE technologies would provide opportunities for personalized medicine in IBD and optimal treatment of CRN in patients with IBD.

Study of tumor necrosis factor receptor in the inflammatory bowel disease

Ulcerative colitis (UC) and Crohn’s disease (CD) are part of Inflammatory Bowel Diseases (IBD) and have pathophysiological processes such as bowel necrosis and enteric neurons and enteric glial cells. In addition, the main inflammatory mediator is related to the tumor necrosis factor-alpha (TNF-α). TNF-α is a me-diator of the intestinal inflammatory processes, thus being one of the main cytokines involved in the pathogenesis of IBD, however, its levels, when measured, are present in the serum of patients with IBD. In addition, TNF-α plays an important role in promoting inflammation, such as the production of interleukins (IL), for instance IL-1β and IL-6. There are two receptors for TNF as following: The tumor necrosis factor 1 receptor (TNFR1); and the tumor necrosis factor 2 receptor (TNFR2). They are involved in the pathogenesis of IBD and their receptors have been detected in IBD and their expression is correlated with disease activity. The soluble TNF form binds to the TNFR1 receptor with, and its activation results in a signaling cascade effects such as apoptosis, cell proliferation and cytokine secretion. In contrast, the transmembrane TNF form can bind both to TNFR1 and TNFR2. Recent studies have suggested that TNF-α is one of the main pro-inflammatory cytokines involved in the pathogenesis of IBD, since TNF levels are present in the serum of both patients with UC and CD. Intravenous and subcutaneous biologics targeting TNF-α have revolutionized the treatment of IBD, thus becoming the best available agents to induce and maintain IBD remission. The application of antibodies aimed at neutralizing TNF-α in patients with IBD that induce a satisfactory clinical response in up to 60% of patients, and also induced long-term maintenance of disease remission in most patients. It has been suggested that anti-TNF-α agents inactivate the pro-inflammatory cytokine TNF-α by direct neutralization, i.e., resulting in suppression of inflammation. However, anti-TNF-α antibodies perform more complex functions than a simple blockade.

Impaired Intestinal Permeability Assessed by Confocal Laser Endomicroscopy-A New Potential Therapeutic Target in Inflammatory Bowel Disease

Inflammatory bowel diseases (IBD) represent a global phenomenon, with a continuously rising prevalence. The strategies concerning IBD management are progressing from clinical monitorization to a targeted approach, and current therapies strive to reduce microscopic mucosal inflammation and stimulate repair of the epithelial barrier function. Intestinal permeability has recently been receiving increased attention, as evidence suggests that it could be related to disease activity in IBD. However, most investigations do not successfully provide adequate information regarding the morphological integrity of the intestinal barrier. In this review, we discuss the advantages of confocal laser endomicroscopy (CLE), which allows in vivo visualization of histological abnormalities and targeted optical biopsies in the setting of IBD. Additionally, CLE has been used to assess vascular permeability and epithelial barrier function that could correlate with prolonged clinical remission, increased resection-free survival, and lower hospitalization rates. Moreover, the dynamic evaluation of the functional characteristics of the intestinal barrier presents an advantage over the endoscopic examination as it has the potential to select patients at risk of relapses. Along with mucosal healing, histological or transmural remission, the recovery of the intestinal barrier function emerges as a possible target that could be included in the future therapeutic strategies for IBD.

The Evaluation of Transmural Healing by Low-dose Computed Tomography Enterography in Patients with Crohn's Disease

Objective Transmural healing (TH) has been attracting attention as a new therapeutic target for Crohn's disease, but there are few clinical data on TH in Japan. We introduced low-dose computed tomography enterography (CTE) as a monitoring method for Crohn's disease and retrospectively investigated the accuracy of evaluating TH by CTE. Methods Among Crohn's disease patients who underwent low-dose CTE at our hospital from January 2009 to March 2021, 122 patients who underwent colonoscopy or balloon endoscopy within 2 weeks were included. Results of radiological and endoscopic examinations were reviewed independently by radiologists and gastrointestinal endoscopists, respectively. The concordance rate of the diagnosis between CTE and endoscopy was evaluated. Results Twenty-six patients (21.3%) achieved TH, and the kappa index was 0.743. On comparing the TH and non-TH groups, the Crohn's disease activity index (p=0.02), endoscopic healing rate (p<0.001), serum albumin (p=0.043), and serum C-reactive protein level (p=0.018) showed significant differences. Among the 122 patients, 69 (56.5%) showed concordance between the diagnosis of CTE and endoscopy, and 22 (18.0%) achieved both TH and endoscopic healing. Conclusion This study provides real-world data on Crohn's disease evaluated with low-dose CTE in Japan. The TH criterion used in this study has a high kappa coefficient and can be used reproducibly in many institutions.

Enteric nervous system and inflammatory bowel diseases: Correlated impacts and therapeutic approaches through the P2X7 receptor

The enteric nervous system (ENS) consists of thousands of small ganglia arranged in the submucosal and myenteric plexuses, which can be negatively affected by Crohn's disease and ulcerative colitis - inflammatory bowel diseases (IBDs). IBDs are complex and multifactorial disorders characterized by chronic and recurrent inflammation of the intestine, and the symptoms of IBDs may include abdominal pain, diarrhea, rectal bleeding, and weight loss. The P2X7 receptor has become a promising therapeutic target for IBDs, especially owing to its wide expression and, in the case of other purinergic receptors, in both human and model animal enteric cells. However, little is known about the actual involvement between the activation of the P2X7 receptor and the cascade of subsequent events and how all these activities associated with chemical signals interfere with the functionality of the affected or treated intestine. In this review, an integrated view is provided, correlating the structural organization of the ENS and the effects of IBDs, focusing on cellular constituents and how therapeutic approaches through the P2X7 receptor can assist in both protection from damage and tissue preservation.

Transmural healing as a therapeutic goal in Crohn's disease: a systematic review

Transmural healing is associated with substantial improvements in disease-related outcomes for patients with Crohn's disease, but there is no single validated definition of transmural healing to date. We did a systematic review to summarise the available definitions and to evaluate the effect of transmural healing on disease-related outcomes for patients with Crohn's disease by searching PubMed, Cochrane Library, and Web of Science for interventional and non-interventional studies. Seventeen studies were included, reporting rates of transmural healing in between 14·0% and 42·4% of patients. Transmural healing was assessed with magnetic resonance enterography, bowel sonography, or CT enterography. Most studies used bowel wall thickness, with 3 mm or less as the most frequent cutoff, to define transmural healing. Vascularisation assessed by doppler ultrasound and absence of complications or contrast enhancement were also used for this definition. Transmural healing was significantly associated with improvements in disease-related outcomes. In addition, there was a good correlation between transmural healing, mucosal healing, and selected biomarkers. We conclude that bowel wall thickness is the most frequently used item to evaluate transmural healing, which is associated with improvements in long-term outcomes of Crohn's disease and should be considered as a new treatment target.

Small bowel radiology

PURPOSE OF REVIEW

Recent advances in computed tomography (CT), ultrasound (US), magnetic resonance imaging (MRI), and nuclear radiology have improved the diagnosis and characterization of small bowel pathology. Our purpose is to highlight the current status and recent advances in multimodality noninvasive imaging of the small bowel.

RECENT FINDINGS

CT and MR enterography are established techniques for small bowel evaluation. Dual-energy CT is a novel technique that has shown promise for the mesenteric ischemia and small bowel bleeding. Advanced US techniques and MRI sequences are being investigated to improve assessment of bowel inflammation, treatment response assessment, motility, and mural fibrosis. Novel radiotracers and scanner technologies have made molecular imaging the new reference standard for small bowel neuroendocrine tumors. Computational image analysis and artificial intelligence (AI) have the potential to augment physician expertise, reduce errors and variability in assessment of the small bowel on imaging.

SUMMARY

Advances in translational imaging research coupled with progress in imaging technology have led to a wider adoption of cross-sectional imaging for the evaluation and management of small bowel entities. Ongoing developments in image acquisition and postprocessing techniques, molecular imaging and AI have the strongest potential to transform the care and outcomes of patients with small bowel diseases.

Endoscopic imaging in inflammatory bowel disease: current developments and emerging strategies

INTRODUCTION

Developments in enhanced and magnified endoscopy have signified major advances in endoscopic imaging of ileocolonic pathology in inflammatory bowel disease (IBD). Artificial intelligence is increasingly being used to augment the benefits of these advanced techniques. Nevertheless, treatment of IBD patients is frustrated by high rates of non-response to therapy, while delayed detection and failures to detect neoplastic lesions impede successful surveillance. A possible solution is offered by molecular imaging, which adds functional imaging data to mucosal morphology assessment through visualizing biological parameters. Other label-free modalities enable visualization beyond the mucosal surface without the need of tracers.

AREAS COVERED

A literature search up to May 2020 was conducted in PubMed/MEDLINE in order to find relevant articles that involve the (pre-)clinical application of high-definition white light endoscopy, chromoendoscopy, artificial intelligence, confocal laser endomicroscopy, endocytoscopy, molecular imaging, optical coherence tomography, and Raman spectroscopy in IBD.

EXPERT OPINION

Enhanced and magnified endoscopy have enabled an improved assessment of the ileocolonic mucosa. Implementing molecular imaging in endoscopy could overcome the remaining clinical challenges by giving practitioners a real-time in vivo view of targeted biomarkers. Label-free modalities could help optimize the endoscopic assessment of mucosal healing and dysplasia detection in IBD patients.

Application of Polymeric Nano-Materials in Management of Inflammatory Bowel Disease

Inflammatory Bowel Disease (IBD) is an umbrella term used to describe disorders that involve Crohn's disease (CD), ulcerative colitis (UC) and pouchitis. The disease occurrence is more prevalent in the working group population which not only hampers the well being of an individual but also has negative economical impact on society. The current drug regime used therapy is very costly owing to the chronic nature of the disease leading to several side effects. The condition gets more aggravated due to the lower concentration of drug at the desired site. Therefore, in the present scenario, a therapy is needed which can maximize efficacy, adhere to quality of life, minimize toxicity and doses, be helpful in maintaining and stimulating physical growth of mucosa with minimum disease complications. In this aspect, nanotechnology intervention is one promising field as it can act as a carrier to reduce toxicity, doses and frequency which in turn help in faster recovery. Moreover, nanomedicine and nanodiagnostic techniques will further open a new window for treatment in understanding pathogenesis along with better diagnosis which is poorly understood till now. Therefore the present review is more focused on recent advancements in IBD in the application of nanotechnology.

The Role of the Radiologist in Determining Disease Severity in Inflammatory Bowel Diseases

Crohn's disease and ulcerative colitis are chronic inflammatory diseases that lead to progressive bowel damage including the development of stricturing and penetrating complications. Increasingly, cross-sectional imaging with computed tomography or magnetic resonance scans have emerged as leading tools to: (1) assess disease activity; (2) monitor response to therapy or disease recurrence; and (3) identify disease-related complications. Several validated radiological scoring systems have been developed to quantify cross-sectional and longitudinal inflammatory burden in these diseases and to monitor response to treatment. Bowel ultrasound is also a simple and inexpensive tool but is operator dependent in its performance.

Magnetic resonance enterography features of small bowel Crohn's disease activity: an inter-rater reliability study of small bowel active inflammation in clinical practice setting

OBJECTIVE

The aim of this study is to determine the interrater agreement in a clinical practice environment for the most commonly used magnetic resonance enterography (MRE) features of Crohn's disease (CD).

METHODS

CD patients with MRE's before and after treatment were retrospectively identified using search queries over a 7-year period (May 2017-September 2017). MRE features of CD comprising components of multiple CD scoring indices were scored by radiologists in the same segment of bowel. Agreement for nominal categorical and continuous variables was assessed using a κ and interclass correlation coefficients, respectively.

RESULTS

80 scans comprised the study population. Moderate interrater agreement was seen in both the pre- and post-treatment MRE's for presence of diffusion restriction (к = 0.43, 0.48; pre- and post-treatment), stricturing disease (к = 0.51, 0.52), overall degree of severity (к = 0.49, 0.59). Substantial agreement was seen in pre- and post-treatment scans for length of involvement (interclass correlation coefficient = 0.67, 0.61). The presence of mucosal ulceration had no agreement (к = -0.07, -0.042).

CONCLUSION

Many MRE features of active CD comprising the major CD scoring indices are reproducible when interpreted by non-CD focused abdominal radiologists. However, the presence of mucosal ulcerations had no agreement and may need more investigation before including this feature as a driver in therapeutic decision making.

ADVANCES IN KNOWLEDGE

Demonstrates the unreliability of mucosal ulceration by non-CD focused abdominal radiologists, targeting a potential area for future education. Key Points The majority of MRE findings incorporated in to many CD scoring indices have fair to moderate inter-rater agreement even when read by non-MRE expert radiologists. Substantial agreement was seen in the length of involved bowel, but this feature is only incorporated in to one of the CD scoring indices. Presence of mucosal ulcerations had no interrater agreement in our study-a feature which is heavily weighted by several CD scoring indices. Research should be focused bridging those features which have poor interrater agreement.