Diagnosis Of Inflammatory Bowel Disease Research Articles

The always evolving diagnosis and management of Clostridioides difficile colitis: What you need to know

ABSTRACT The diagnosis, pharmacologic management, and surgical options for Clostridioides difficile infection (CDI) are rapidly evolving, which presents a challenge for the busy surgeon to remain up to date on the latest clinical guidelines. This review provides an evidence-based practical guide for CDI management tailored to the needs of surgeons and surgical intensivists. Historically, the diagnosis of CDI relied on slow cell culture cytotoxicity neutralization assays, but now, the rapidly resulting nucleic acid amplification tests and enzyme immunoassays have become mainstream. In terms of antibiotic therapy, metronidazole and oral vancomycin were the main “workhorse” antibiotics in the early 2000s, but large randomized controlled trials have now demonstrated that fidaxomicin produces superior results. Regarding surgical intervention, total abdominal colectomy was once the only procedure of choice; however, diverting loop ileostomy with colonic lavage is emerging as a viable alternative. Finally, novel adjuncts such as fecal microbiota transplantation and targeted therapy against toxin B (bezlotoxumab) are playing an increasingly important role in the management of CDI.

The Current Role of Imaging in the Diagnosis of Inflammatory Bowel Disease and Detection of Its Complications: A Systematic Review.

Inflammatory bowel disease (IBD) encompasses complex gastrointestinal (GI) conditions, primarily Crohn's disease (CD) and ulcerative colitis (UC), requiring precise imaging for effective diagnosis and management of complications. This systematic review aimed to evaluatethe current role of imaging modalities in diagnosing IBD and detecting related complications. Thereview adhered to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We performed a literature search using text words and controlled vocabulary applying Boolean operators "AND," "OR," with various combinations on databases such as PubMed, Embase, and Cochrane Library. The search targeted open-access articles involving humans, with full-text available, and published in the English Language from 2005 to 2024. The quality of the included studies was assessed using the Cochrane Risk-of-Bias (RoB) checklist. Our search process identified 127 recordsfrom Cochrane (39), Embase (29), and PubMed (59). After removing 98 irrelevant records, 29 underwent further screening. Five were excluded as they involved irrelevant problems or outcomes, leaving us with 24 reports with full text, all of which were accessible. Following the eligibility assessment, two more reports were excluded due to inaccessibility, and 22 studies were included in the final analysis. The risk of bias and methodological quality assessment revealed that out of 22 studies analyzed, five (23%) had a high risk of bias, while 13 (59%) were classified as moderate risk, and four (18%) showed low risk. This distribution highlights a predominance of moderate-risk studies in research on imaging in IBD, emphasizing the need for enhanced study designs in future investigations. Our findings revealed the varying effectiveness of imaging modalities in diagnosing complications of CD and UC. Magnetic resonance enterography (MRE) stands out as the preferred method for CD due to its high sensitivity and noninvasive nature. In contrast, colonoscopy remains the gold standard for UC, providing direct visualization of mucosal lesions. While techniques like ultrasound and capsule endoscopy offer valuable insights, they havelimitations that may affect their utility in certain cases.

Prevalence of anxiety and depression disorders in patients with inflammatory bowel disease in a city in southern Brazil

Inflammatory bowel disease is a chronic disease with symptoms and possible complications that can bring disability to the patient and trigger impairment in mental health such as depression and anxiety disorder. Objective: To evaluate the prevalence of Anxiety and Depression Disorder in patients with IBD in the Inflammatory Bowel Disease outpatient clinic of UFPEL. Methodology: Applied socio-economic questionnaire, M.I.N.I. instrument and collection of data from the medical record during the medical consultation. In patients attending the FAMED-UFPEL outpatient clinic with a diagnosis of Inflammatory bowel disease and over 16 years of age in the period from 06/01/2021 to 02/28/2022. Results: During the exposed period, 59 patients diagnosed with IBD were evaluated, being 37 (62.7%) with Crohn's Disease and 22 (37.3%) with Ulcerative Colitis, the average age was 46 years. In the current study, disease activity was evaluated using the Mayo Score for patients with ulcerative colitis with a result with no statistical significance for depression (p:0,494) and anxiety disorder (p:0,484). The Harvey Bradshaw Score was used in patients with Crohn's Disease that also has no statistical relevance for depression (p:0.969) and anxiety disorder (p:0.380). In the present study, 29.4% of patients had Ulcerative Colitis and recurrent depressive episode and 54.2% of patients had generalized anxiety disorder. Conclusion: there is a high prevalence of mood disorders in the population studied, it is emphasized the need for the active search of these diagnoses in this population, offering adequate treatment of the pathologies found with a view to better quality of life.

From inflammation to depression: key biomarkers for IBD-related major depressive disorder.

Inflammatory bowel disease (IBD) is a chronic, inflammatory, and autoimmune disorder, and its incidence of comorbid with major depressive disorder (MDD) is significantly higher than the general population. However, many patients lack proper recognition and necessary psychological health treatments. We aimed to identify potential biomarkers and mechanisms involved in the development of IBD comorbid with MDD (IBD-MDD). We utilized IBD and MDD-related datasets from the GEO database for differential gene expression analysis, protein-protein interaction (PPI) and pathway enrichment analysis, random forest algorithm, LASSO regression analysis, and construction of a disease prediction model. We assessed the accuracy of the model using ROC curve, explored potential mechanisms through immune infiltration analysis, and validated candidate biomarkers using peripheral blood samples from patients in our center's cohort. We identified 484 IBD-related secreted proteins and 142 key module genes associated with MDD. PPI analysis revealed two crucial modules primarily involved in inflammation and immune regulation. We identified four diagnostic genes (HGF, SPARC, ADAM12, and MMP8) from the 21 shared genes between IBD-related secreted proteins and MDD key module genes, constructed a nomogram model and confirmed its accuracy using ROC curve from an external independent dataset. Immune infiltration analysis revealed significant associations between the four diagnostic genes, and cellular immune dysregulation in MDD. Finally, we validated the expression patterns of the four diagnostic genes in our cohort. Our study discovered four candidate biomarkers for IBD-MDD, providing new insights for the diagnosis and therapeutic intervention of serum-based IBD comorbid with MDD.

Inflammatory bowel disease in Pakistan: Low prevalence or underdiagnosis?

Inflammatory bowel disease (IBD) has a low prevalence in the Global South, including Pakistan. While genetics and gut flora, influenced by diet and the environment, can contribute to this, we are exploring the possibility of underdiagnosis. Lack of facilities trained in IBD, scarcity of medications, limited health insurance for specialist referral and the current epidemic of abdominal tuberculosis could be the cause. The increasing diagnosis of IBD among Pakistani immigrants and colorectal carcinoma among the young population might be the result of this. Timely referrals by primary care physicians to gastroenterologists, along with the growing use of newer technologies such as abdominal ultrasound for diagnosis can help mitigate the challenge of low or late diagnosis of this chronic condition.

Early subclinical stages of the inflammatory bowel diseases - insights from human and animal studies.

The inflammatory bowel diseases (IBD) occur in genetically susceptible individuals that mount inappropriate immune responses to their microbiota leading to chronic intestinal inflammation. The natural history of IBD progression begins with early subclinical stages of disease that occur before clinical diagnosis. Improved understanding of those early subclinical stages could lead to new or improved strategies for IBD diagnosis, prognostication or prevention. Here we review our current understanding of the early subclinical stages of IBD in humans including studies from first-degree relatives of IBD patients and members of the general population who go on to develop IBD. We also discuss representative mouse models of IBD that can be used to investigate disease dynamics and host-microbiota relationships during these early stages. In particular, we underscore how mouse models of IBD that develop disease later in life with variable penetrance may present valuable opportunities to discern early subclinical mechanisms of disease before histological inflammation and other severe symptoms become apparent.

Clinical analysis and identification of pediatric patients with colonic ulceration

BackgroundA wide variety of diseases mimic inflammatory bowel disease (IBD). This study aimed to reduce the misdiagnosis among children with colonic ulcers.MethodsEighty-six pediatric patients with colonic ulcers detected by colonoscopy were enrolled in the retrospective study. Children were divided into different groups according to the final diagnosis. The clinical characteristics, laboratory examinations, endoscopic findings, and histopathological results were compared.ResultsIBD (n = 37) was just responsible for 43% of patients with colonic ulceration. Other diagnosis included autoimmune diseases (n = 9), infectious enteritis (n = 13), gastrointestinal allergy (n = 8), and other diseases (n = 19). Comparing IBD and non-IBD groups, children with IBD had a higher frequency of symptoms like weight loss/failure to thrive (P < 0.001), perianal lesions (P = 0.001), and oral ulcers (P = 0.022), and higher expression levels of platelet (P = 0.006), neutrophil-to-lymphocyte ratio (NLR) (P = 0.001), erythrocyte sedimentation rate (P < 0.001), C-reactive protein (P < 0.001), Immunoglobulin G (P = 0.012), Interleukin-1β (P = 0.003), Interleukin-6 (P = 0.024) and TNF-α (P = 0.026), and a wider ulcer distribution in the lower gastrointestinal tract (LGIT) (P < 0.001). Expression levels of hemoglobin (P < 0.001) and albumin (P = 0.001) were lower in IBD patients. Multivariate analysis showed hemoglobin, NLR, Score of ulceration in LGIT, and pseudopolyps contributing to the diagnosis of pediatric IBD with colonic ulcers.ConclusionsWe displayed potential indicators to help diagnose pediatric IBD differentiating from other disorders with colonic ulcers more prudently.

Food Insecurity Is Common in Patients with Inflammatory Bowel Disease and Is Associated with Increased Ultra-Processed Food Intake

Background/Objectives: Food insecurity (FI) is defined as the lack of consistent access to enough food for an active and healthy life. FI affects over 30 million Americans and is associated with poor clinical outcomes and impaired quality of life and drives significant health inequities. Despite the rising prevalence of FI and the federal focus on improving access to healthy food, there is a paucity of research on FI in patients with inflammatory bowel disease (IBD). Therefore, the goal of this study was to define FI in a cohort of IBD patients and determine whether FI was associated with changes in dietary patterns, including specifically an increase in ultra-processed food (UPF) consumption in this high-risk patient population. Methods: This was a single-center, retrospective cohort study of patients with a diagnosis of IBD who were 18 years of age or older and who were seen in a nutrition focused clinic. Patients were screened for FI using the Hunger Vital Sign™, a 2-question validated FI screening tool and underwent a 24-h dietary recall. The degree of food processing was assessed using the NOVA Food Classification System. Results: Among 128 patients with IBD, we observed that FI is increasingly prevalent, with 45% of patients reporting difficulty with sufficient grocery access at least “sometimes” in the last 12 months and 10% reporting decreased food access “often” in the prior year. In addition, the patients at high-risk for FI were significantly more likely to eat NOVA 4 UPFs (54% vs. 27%, p = 0.001) and were significantly less likely to eat NOVA 1 unprocessed foods (32% vs. 61%, p = 0.001) as compared to those not at risk for FI. Finally, only a small percentage of those at highest risk for FI were enrolled in a federal food assistance program for grocery support. Conclusions: The prevalence of FI is increasing in patients with IBD and is associated with reduced dietary quality.

Aphthous lesions turned out to be neonatal very early-onset inflammatory bowel disease: a case report

Neonatal diagnosis of inflammatory bowel disease (IBD) proves challenging due to its non-specific symptoms. A term-born neonate showing states of inflammation and aphthae was treated for sepsis and candidiasis before being diagnosed with interleukin-10 receptor deficiency and consecutive IBD. The patient was finally successfully treated by stem cell transplantation. The case illustrates the difficulties of the diagnostic course in IBD as it may mimic other diseases and emphasizes the importance of considering rare differential diagnoses early in the diagnostic process.

Association of Childhood Abuse with Incident Inflammatory Bowel Disease.

A link between inflammatory bowel disease (IBD), stressful life events and psychological factors has previously been reported. Our objective was to examine the relationship between childhood emotional, physical, and sexual abuse and risk of IBD using a large cohort of female health professionals. We included participants in the Nurses' Health Study II who completed the Physical and Emotional Abuse Subscale of the Childhood Trauma Questionnaire and the Sexual Maltreatment Scale of the Parent-Child Conflict Tactics Scale in 2001. Diagnosis of IBD was determined by self-report and confirmed independently by two physicians through review of medical records. We used Cox proportional hazard modeling to estimate the risk of Crohn's disease (CD) and ulcerative colitis (UC) while adjusting for covariates. Among 68,167 women followed from 1989 until 2017, there were 146 incident cases of CD and 215 incident cases of UC. Compared to women with no history of abuse, the adjusted hazard ratios of CD were 1.16 (95% CI 0.67 - 2.02) for mild, 1.58 (95% CI 0.92 - 2.69) for moderate, and 1.95 (95% CI 1.22 - 3.10) for severe abuse (Ptrend = 0.002). We did not observe an association between childhood abuse and risk of UC. Women who reported early life severe abuse had an increased risk of CD. These data add to the growing body of evidence on the critical role of early life stressors in development of CD.

Early-Life Infections, Antibiotics and Later Risk of Childhood and Early Adult-Onset Inflammatory Bowel Disease: Pooled Analysis of Two Scandinavian Birth Cohorts.

Childhood antibiotic use has been associated with inflammatory bowel disease (IBD), although the potential contribution of infection frequency remains uncertain. To explore the association between early-life infections, antibiotics and IBD development. We used population-based data from ABIS (Sweden) and MoBa (Norway) cohorts following children from birth (1997-2009) until 2021. Prospectively collected questionnaires identified infection frequency (any, gastrointestinal and respiratory) and antibiotics (any, penicillin and non-penicillin) until age 3. IBD diagnosis required ≥ 2 records in national health registries. Cohort-specific hazard ratios (aHR), adjusted for parental education, smoking and IBD were estimated and pooled using a random-effects model. Antibiotic analyses were adjusted for infection frequency. There were 103,046 children (11,872 ABIS and 91,174 MoBa), contributing to 1,663,898 person-years of follow-up, during which 395 were diagnosed with IBD. The frequency of any infection at 0 to < 1 and 1 to < 3 years showed a pooled aHR of 1.01 (95% confidence interval [CI] = 0.96-1.07) and 1.00 (95% CI = 0.99-1.01) per additional infection for IBD. Adjusting for infections, any versus no antibiotics in the first year was associated with IBD (pooled aHR = 1.33 [95% CI = 1.01-1.76]). The aHR for additional antibiotic course was 1.17 (95% CI = 0.96-1.44), driven by penicillin (per additional course, aHR = 1.28 [95% CI = 1.02-1.60]). Although antibiotics at 1 to < 3 years did not show an association with IBD or Crohn's disease, non-penicillin antibiotics were associated with ulcerative colitis (per additional course, aHR = 1.95 [95% CI = 1.38-2.75]). Early-life antibiotic use was, a significant risk factor for childhood and early adult-onset IBD, independent of infection frequency.

Advancements in the use of AI in the diagnosis and management of inflammatory bowel disease.

Inflammatory bowel disease (IBD) causes chronic inflammation of the colon and digestive tract, and it can be classified as Crohn's disease (CD) and Ulcerative colitis (UC). IBD is more prevalent in Europe and North America, however, since the beginning of the 21st century it has been increasing in South America, Asia, and Africa, leading to its consideration as a worldwide problem. Optical colonoscopy is one of the crucial tests in diagnosing and assessing the progression and prognosis of IBD, as it allows a real-time optical visualization of the colonic wall and ileum and allows for the collection of tissue samples. The accuracy of colonoscopy procedures depends on the expertise and ability of the endoscopists. Therefore, algorithms based on Deep Learning (DL) and Convolutional Neural Networks (CNN) for colonoscopy images and videos are growing in popularity, especially for the detection and classification of colorectal polyps. The performance of this system is dependent on the quality and quantity of the data used for training. There are several datasets publicly available for endoscopy images and videos, but most of them are solely specialized in polyps. The use of DL algorithms to detect IBD is still in its inception, most studies are based on assessing the severity of UC. As artificial intelligence (AI) grows in popularity there is a growing interest in the use of these algorithms for diagnosing and classifying the IBDs and managing their progression. To tackle this, more annotated colonoscopy images and videos will be required for the training of new and more reliable AI algorithms. This article discusses the current challenges in the early detection of IBD, focusing on the available AI algorithms, and databases, and the challenges ahead to improve the detection rate.

Post-Discharge Outcomes of Elderly Patients Hospitalized for Inflammatory Bowel Disease Flare Complicated by Clostridioides difficile Infection.

Elderly hospitalized patients with inflammatory bowel disease (IBD) flare and concurrent Clostridioides difficile infection (CDI) are considered at high risk of IBD-related complications. We aimed to evaluate the short, intermediate, and long-term post-discharge complications among these patients. A retrospective multicenter cohort study assessing outcomes of elderly individuals (≥60 years) hospitalized for an IBD flare who were tested for CDI (either positive or negative) and discharged. The primary outcome was the 3-months post-discharge IBD-related complication rates defined as: steroid dependency, re-admissions (emergency department or hospitalization), IBD-related surgery, or mortality. We assessed post-discharge IBD-related complications within 6-months and mortality at 12-months among secondary outcomes. Risk factors for complication were assessed by multivariable logistic regression. In a cohort of 654 patients hospitalized for IBD (age 68.9 [interquartile range {IQR}]:63.9-75.2) years, 60.9% ulcerative colitis), 23.4% were CDI-positive. Post-discharge complication rates at 3 and 6-months, and 12-months mortality, did not differ significantly between CDI-positive and CDI-negative patients (32% vs. 33.1%, p=0.8; 40.5% vs. 42.5%, p=0.66; and 4.6% vs. 8%, p=0.153, respectively). The Charlson comorbidity index was the only significant risk factor for complications within 3-months (aOR 1.1), whereas mesalamine (5-aminosalicylic acid [5-ASA]) use was protective (aOR 0.6). An ulcerative colitis diagnosis was the sole risk factor for complication at 6-months (aOR 1.5). CDI did not significantly impact outcomes or interact with IBD type. In elderly IBD patients hospitalized for IBD flare and subsequently discharged, a concurrent CDI infection was not associated with post-discharge IBD-related complications or mortality up to 1-year.

The Gut Microbiome Advances Precision Medicine and Diagnostics for Inflammatory Bowel Diseases

The gut microbiome emerges as an integral component of precision medicine because of its signature variability among individuals and its plasticity, which enables personalized therapeutic interventions, especially when integrated with other multiomics data. This promise is further fueled by advances in next-generation sequencing and metabolomics, which allow in-depth high-precision profiling of microbiome communities, their genetic contents, and secreted chemistry. This knowledge has advanced our understanding of our microbial partners, their interaction with cellular targets, and their implication in human conditions such as inflammatory bowel disease (IBD). This explosion of microbiome data inspired the development of next-generation therapeutics for treating IBD that depend on manipulating the gut microbiome by diet modulation or using live products as therapeutics. The current landscape of artificial microbiome therapeutics is not limited to probiotics and fecal transplants but has expanded to include community consortia, engineered probiotics, and defined metabolites, bypassing several limitations that hindered rapid progress in this field such as safety and regulatory issues. More integrated research will reveal new therapeutic targets such as enzymes or receptors mediating interactions between microbiota-secreted molecules that drive or modulate diseases. With the shift toward precision medicine and the enhanced integration of host genetics and polymorphism in treatment regimes, the following key questions emerge: How can we effectively implement microbiomics to further personalize the treatment of diseases like IBD, leveraging proven and validated microbiome links? Can we modulate the microbiome to manage IBD by altering the host immune response? In this review, we discuss recent advances in understanding the mechanism underpinning the role of gut microbes in driving or preventing IBD. We highlight developed targeted approaches to reverse dysbiosis through precision editing of the microbiome. We analyze limitations and opportunities while defining the specific clinical niche for this innovative therapeutic modality for the treatment, prevention, and diagnosis of IBD and its potential implication in precision medicine.

A novel, portable, and cost-effective turbidimetric sensor for sensitive alkaline phosphatase activity assay

The development of enzyme activity analysis methods is critical for precise and rapid assessments of enzyme activity levels within biological systems, facilitating a more profound comprehension of physiological functions and disease mechanisms. Alkaline phosphatase (ALP) participates in various physiological processes involving phosphate ester hydrolysis. Altered ALP activity levels are often indicative of different diseases, underscoring the necessity for accurate ALP activity determination in medical diagnostics. This study innovatively applies turbidity as a physical variable, proposing a turbidimetric sensor based on an enhanced ammonium molybdate reagent for phosphate analysis. By integrating this with the ALP substrate p-nitrophenyl phosphate, a turbidimetric sensor was devised and employed for ALP activity analysis. The proposed turbidimetric sensor demonstrated high sensitivity both for phosphate (0.18 μmol/L) and ALP activity (0.03 mU/mL) assay. In practical applications, this turbidimetric sensor has been effectively employed to detect ALP activity in mouse feces, showcasing its potential for auxiliary diagnosis of inflammatory bowel disease. Significantly, this novel turbidity-based approach offers not only swift and straightforward procedures but also remarkable portability and cost-efficiency. Requiring solely a handheld turbidimeter and eliminating the need for bulky instruments, this approach holds significant potential for point-of-care testing applications.

DeepPhylo: Phylogeny-Aware Microbial Embeddings Enhanced Predictive Accuracy in Human Microbiome Data Analysis.

Microbial data analysis poses significant challenges due to its high dimensionality, sparsity, and compositionality. Recent advances have shown that integrating abundance and phylogenetic information is an effective strategy for uncovering robust patterns and enhancing the predictive performance in microbiome studies. However, existing methods primarily focus on the hierarchical structure of phylogenetic trees, overlooking the evolutionary distances embedded within them. This study introduces DeepPhylo, a novel method that employs phylogeny-aware amplicon embeddings to effectively integrate abundance and phylogenetic information. DeepPhylo improves both the unsupervised discriminatory power and supervised predictive accuracy of microbiome data analysis. Compared to the existing methods, DeepPhylo demonstrates superiority in informing biologically relevant insights across five real-world microbiome use cases, including clustering of skin microbiomes, prediction of host chronological age and gender, diagnosis of inflammatory bowel disease (IBD) across 15 studies, and multilabel disease classification.

Knowledge, attitudes, and practices of endoscopy among gastroenterologists in diagnosis and management of inflammatory bowel disease in China: a multicenter cross-sectional study

BackgroundThe aim was to assess the knowledge, attitudes, and practices (KAPs) of endoscopy among gastroenterologists in the diagnosis and management of IBD in China.MethodsA multicenter cross-sectional KAP study was performed. The questionnaire was developed and improved using feedback and opinions from a team of experienced IBD specialist professors and then distributed and collected online. In addition, eight fellow gastroenterologists participated in an IBD endoscopy training program were asked to review endoscopic images, and the consistency of the endoscopic scores before and after training was calculated.ResultsA total of 193 participants from 12 provincial-level administrative regions encompassing both the Northern and Southern parts of China completed the study questionnaire. The median age of the participants was 40 (36, 45) years, with the majority being female (70.5%). The median professional experience as gastroenterologists was 11 (7, 17) years, while the median experience as endoscopists was 8 (3, 15) years. The median knowledge score was 8 out of 10 points for single-choice questions; however, most gastroenterologists believed that some concepts in these endoscopic indices were vague, including those regarding deep ulcerations, ulcerated surfaces, affected surfaces and narrowing in open-answer questions. The UCEIS and SES-CD were considered most consistent with clinical activity score in the evaluation of UC and CD, respectively. IBD subspecialists and gastroenterologists who had previously received IBD endoscopy screening training were more likely to use endoscopic indices (p<0.001, p = 0.029, respectively). The Rutgeerts score demonstrated the most significant improvement in consistency before and after training, from 0.407 (95% CI: 0.025–0.999) to 0.909 (95% CI: 0.530–1.000).ConclusionsWe propose the elucidation of ambiguous definitions in endoscopic indices, enhancement of training, and the application of innovative technology to enhance the application of endoscopic evaluation and endoscopic indices in clinical practice.

Is CMV DNAemia an early marker of CMV colitis in patients with active ulcerative colitis?

Cytomegalovirus (CMV) colonic reactivation worsens the prognosis of patients with active ulcerative colitis. Blood CMV-DNA reactivation is strongly associated with CMV colitis. Prompt diagnosis and treatment of CMV colitis can avoid surgery in most cases.

Pathologist-level diagnosis of ulcerative colitis inflammatory activity level using an automated histological grading method

Background and AimsInflammatory bowel disease (IBD) is a global disease that is evolving with increasing incidence. However, there are few works on computationally assisted diagnosis of IBD based on pathological images. Therefore, based on the UK and Chinese IBD diagnostic guidelines, our study established an artificial intelligence-assisted diagnostic system for histologic grading of inflammatory activity in ulcerative colitis (UC). MethodsWe proposed an efficient deep-learning (DL) method for grading inflammatory activity in whole-slide images (WSIs) of UC pathology. Our model was constructed using 603 UC WSIs from Nanjing Drum Tower Hospital for model train set and internal test set. We collected 212 UC WSIs from Zhujiang Hospital as an external test set. Initially, the pre-trained ResNet50 model on the ImageNet dataset was employed to extract image patch features from UC patients. Subsequently, a multi-instance learning (MIL) approach with embedded self-attention was utilized to aggregate tissue image patch features, representing the entire WSI. Finally, the model was trained based on the aggregated features and WSI annotations provided by senior gastrointestinal pathologists to predict the level of inflammatory activity in UC WSIs. ResultsIn the task of distinguishing the presence or absence of inflammatory activity, the Area Under Curve (AUC) value in the internal test set is 0.863 (95% confidence interval [CI] 0.829, 0.898), with a sensitivity of 0.913 (95% [CI] 0.866, 0.961), and specificity of 0.816 (95% [CI] 0.771, 0.861). The AUC in the external test set is 0.947 (95% confidence interval [CI] 0.939, 0.955), with a sensitivity of 0.889 (905% [CI] 0.837, 0.940), and specificity of 0.858 (95% [CI] 0.777, 0.939). For distinguishing different levels of inflammatory activity in UC, the average Macro-AUC in the internal test set and the external test set are 0.827 (95% [CI] 0.803, 0.850) and 0.908 (95% [CI] 0.882, 0.935). the average Micro-AUC in the internal test set and the external test set are 0.816 (95% [CI] 0.792, 0.840) and 0.898 (95% [CI] 0.869, 0.926). ConclusionsComparative analysis with diagnoses made by pathologists at different expertise levels revealed that the algorithm reached a proficiency comparable to the pathologist with 5 years of experience. Furthermore, our algorithm performed superior to other MIL algorithms.

Enhancing radiologist's detection: an imaging-based grading system for differentiating Crohn's disease from ulcerative colitis

BackgroundDelayed diagnosis of inflammatory bowel disease (IBD) is common, there is still no effective imaging system to distinguish Crohn's Disease (CD) and Ulcerative Colitis (UC) patients.MethodsThis multicenter retrospective study included IBD patients at three centers between January 2012 and May 2022. The intestinal and perianal imaging signs were evaluated. Visceral fat information from CT images was extracted, including the ratio of visceral to subcutaneous fat volume (VSR), fat distribution, and attenuation values. The valuable indicators were screened out in the derivation cohort by binary logistic regression and receiver working curve (ROC) analysis to construct an imaging report and data system for IBD (IBD-RADS), which was tested in the validation cohort.ResultsThe derivation cohort included 606 patients (365 CD, 241 UC), and the validation cohort included 155 patients (97 CD, 58 UC). Asymmetric enhancement (AE) (OR = 87.75 [28.69, 268.4]; P < 0.001), perianal fistula (OR = 4.968 [1.807, 13.66]; P = 0.002) and VSR (OR = 1.571 [1.087, 2.280]; P = 0.04) were independent predictors of CD. VSR improved the efficiency of imaging signs (AUC: 0.929 vs. 0.901; P < 0.001), with a threshold greater than 0.97 defined as visceral fat predominance (VFP). In IBD-RADS, AE was the major criterion, VFP and perianal fistula were auxiliary criteria, and intestinal fistula, limited small bowel disease, and skip distribution were special favoring items as their 100% specificity. Grade 3 to 5 correctly classified most CD patients (derivation: 96.5% (352/365), validation: 98.0% (95/97)), and 98% of those were eventually diagnosed with CD (derivation: 97.8% (352/360), validation: 98.0% (95/97)).ConclusionsIBD-RADS can help radiologists distinguish between CD and UC in patients with suspected IBD.