Current technologies for the endoscopic assessment of duodenal villous pattern in celiac disease

Optimising the Diagnosis of Adult Coeliac Disease: Current Evidence and Future Directions

Coeliac disease is a common autoimmune disorder that affects nearly 1% of the general population. Current diagnostic strategies involve active case finding, serological tests, and endoscopy with biopsies. However, many patients with coeliac disease remain undiagnosed due to a wide gap between clinical guidelines and real-world practice in the diagnosis of adult coeliac disease. This highlights the need for increased education, training, and targeted quality-improvement interventions to optimise the diagnosis of coeliac disease.

Celiac disease diagnosis from endoscopic images based on multi-scale adaptive hybrid architecture model

Objective. Celiac disease (CD) has emerged as a significant global public health concern, exhibiting an estimated worldwide prevalence of approximately 1%. However, existing research pertaining to domestic occurrences of CD is confined mainly to case reports and limited case analyses. Furthermore, there is a substantial population of undiagnosed patients in the Xinjiang region. This study endeavors to create a novel, high-performance, lightweight deep learning model utilizing endoscopic images from CD patients in Xinjiang as a dataset, with the intention of enhancing the accuracy of CD diagnosis.Approach. In this study, we propose a novel CNN-Transformer hybrid architecture for deep learning, tailored to the diagnosis of CD using endoscopic images. Within this architecture, a multi-scale spatial adaptive selective kernel convolution feature attention module demonstrates remarkable efficacy in diagnosing CD. Within this module, we dynamically capture salient features within the local channel feature map that correspond to distinct manifestations of endoscopic image lesions in the CD-affected areas such as the duodenal bulb, duodenal descending segment, and terminal ileum. This process serves to extract and fortify the spatial information specific to different lesions. This strategic approach facilitates not only the extraction of diverse lesion characteristics but also the attentive consideration of their spatial distribution. Additionally, we integrate the global representation of the feature map obtained from the Transformer with the locally extracted information via convolutional layers. This integration achieves a harmonious synergy that optimizes the diagnostic prowess of the model.Main results. Overall, the accuracy, specificity, F1-Score, and precision in the experimental results were 98.38%, 99.04%, 98.66% and 99.38%, respectively.Significance. This study introduces a deep learning network equipped with both global feature response and local feature extraction capabilities. This innovative architecture holds significant promise for the accurate diagnosis of CD by leveraging endoscopic images captured from diverse anatomical sites.

Computer-Based Diagnosis of Celiac Disease by Quantitative Processing of Duodenal Endoscopy Images

Celiac disease (CD) is a lifelong chronic autoimmune systemic disease that primarily affects the small bowel of genetically susceptible individuals. The diagnostics of adult CD currently rely on specific serology and the histological assessment of duodenal mucosa on samples taken by upper digestive endoscopy. Because of several pitfalls associated with duodenal biopsy sampling and histopathology, and considering the pediatric no-biopsy diagnostic criteria, a biopsy-avoiding strategy has been proposed for adult CD diagnosis also. Several endoscopic changes have been reported in the duodenum of CD patients, as markers of villous atrophy (VA), with good correlation with serology. In this setting, an opportunity lies in the automated detection of these endoscopic markers, during routine endoscopy examinations, as potential case-finding of unsuspected CD. We collected duodenal endoscopy images from 18 CD newly diagnosed CD patients and 16 non-CD controls and applied machine learning (ML) and deep learning (DL) algorithms on image patches for the detection of VA. Using histology as standard, high diagnostic accuracy was seen for all algorithms tested, with the layered convolutional neural network (CNN) having the best performance, with 99.67% sensitivity and 98.07% positive predictive value. In this pilot study, we provide an accurate algorithm for automated detection of mucosal changes associated with VA in CD patients, compared to normally appearing non-atrophic mucosa in non-CD controls, using histology as a reference.

Computer-Based Diagnosis of Celiac Disease by Quantitative Processing of Duodenal Endoscopy Images

Celiac disease (CD) is a lifelong chronic autoimmune systemic disease that primarily affects the small bowel of genetically susceptible individuals. The diagnostics of adult CD currently rely on specific serology and the histological assessment of duodenal mucosa on samples taken by upper digestive endoscopy. Because of several pitfalls associated with duodenal biopsy sampling and histopathology, and considering the pediatric no-biopsy diagnostic criteria, a biopsy-avoiding strategy has been proposed for adult CD diagnosis also. Several endoscopic changes have been reported in the duodenum of CD patients, as markers of villous atrophy (VA), with good correlation with serology. In this setting, an opportunity lies in the automated detection of these endoscopic markers, during routine endoscopy examinations, as potential case-finding of unsuspected CD. We collected duodenal endoscopy images from 18 CD newly diagnosed CD patients and 16 non-CD controls and applied machine learning (ML) and deep learning (DL) algorithms on image patches for the detection of VA. Using histology as standard, high diagnostic accuracy was seen for all algorithms tested, with the layered convolutional neural network (CNN) having the best performance, with 99.67% sensitivity and 98.07% positive predictive value. In this pilot study, we provide an accurate algorithm for automated detection of mucosal changes associated with VA in CD patients, compared to normally appearing non-atrophic mucosa in non-CD controls, using histology as a reference.

Spatially adaptive blind deconvolution methods for optical coherence tomography

Optical coherence tomography (OCT) is a powerful noninvasive imaging technique for detecting microvascular abnormalities. Following optical imaging principles, an OCT image will be blurred in the out-of-focus domain. Digital deconvolution is a commonly used method for image deblurring. However, the accuracy of traditional digital deconvolution methods, e.g., the Richardson-Lucy method, depends on the prior knowledge of the point spread function (PSF), which varies with the imaging depth and is difficult to determine. In this paper, a spatially adaptive blind deconvolution framework is proposed for recovering clear OCT images from blurred images without a known PSF. First, a depth-dependent PSF is derived from the Gaussian beam model. Second, the blind deconvolution problem is formalized as a regularized energy minimization problem using the least squares method. Third, the clear image and imaging depth are simultaneously recovered from blurry images using an alternating optimization method. To improve the computational efficiency of the proposed method, an accelerated alternating optimization method is proposed based on the convolution theorem and Fourier transform. The proposed method is numerically implemented with various regularization terms, including total variation, Tikhonov, and l₁ norm terms. The proposed method is used to deblur synthetic and experimental OCT images. The influence of the regularization term on the deblurring performance is discussed. The results show that the proposed method can accurately deblur OCT images. The proposed acceleration method can significantly improve the computational efficiency of blind demodulation methods.

Utility of narrow band imaging in predicting histology in celiac disease

BACKGROUND

Narrow band imaging (NBI) with magnification better visualizes the duodenal microsurface and mucosal vascularity. NBI delineates villous atrophy better than conventional white light endoscopy.

AIMS

This study was conducted to evaluate the diagnostic accuracy of narrow band imaging with magnification (NBI-ME) in celiac disease (CD).

METHODS

In this prospective study, consecutive patients of suspected CD and controls were subjected to tissue transglutaminase antibody test and endoscopic evaluation initially with white light followed by NBI-ME, and biopsies were taken from duodenum. Duodenal villous patterns on NBI were interpreted as normal, blunted distorted, and absent. Severity of villous atrophy was reported according to the modified Marsh criteria.

RESULTS

One hundred and twenty-two patients (mean age of 27.53 ± 13.37 years and a male to female ratio of 1:1.26) and 40 controls were studied. The sensitivity and specificity of NBI-ME in predicting villous atrophy were found to be 95.54% and 90%, respectively. The specificity and negative predictive value of NBI-ME in predicting villous atrophy amongst controls was 100% and 97.5%, respectively. Abnormal findings (blunted and absent villous patterns) combined with elevated transglutaminase antibody (> 5-fold) were found to have high accuracy in predicting villous atrophy.

CONCLUSION

NBI with magnification has high sensitivity and specificity in predicting villous atrophy in patients with celiac disease.

Salt-sensitive increase in macrophages in the kidneys of Dahl SS rats

Studies of Dahl salt-sensitive (SS) rats have shown that renal CD3⁺ T cells and ED-1⁺ macrophages are involved in the development of salt-sensitive hypertension and renal damage. The present study demonstrated that the increase in renal immune cells, which accompanies renal hypertrophy and albuminuria in high-salt diet-fed Dahl SS rats, is absent in Sprague-Dawley and SSBN13 rats that are protected from the SS disease phenotype. Flow cytometric analysis demonstrated that >70% of the immune cells in the SS kidney are M1 macrophages. PCR profiling of renal myeloid cells showed a salt-induced upregulation in 9 of 84 genes related to Toll-like receptor signaling, with notable upregulation of the Toll-like receptor 4/CD14/MD2 complex. Because of the prominent increase in macrophages in the SS kidney, we used liposome-encapsulated clodronate (Clod) to deplete macrophages and assess their contribution to salt-sensitive hypertension and renal damage. Dahl SS animals were administered either Clod-containing liposomes (Clod-Lipo), Clod, or PBS-containing liposomes as a vehicle control. Clod-Lipo treatment depleted circulating and splenic macrophages by ∼50%; however, contrary to our hypothesis, Clod-Lipo-treated animals developed an exacerbated salt-sensitive response with respect to blood pressure and albuminuria, which was accompanied by increased renal T and B cells. Interestingly, those treated with Clod also demonstrated an exacerbated phenotype, but it was less severe than Clod-Lipo-treated animals and independent of changes to the number of renal immune cells. Here, we have shown that renal macrophages in Dahl SS animals sustain a M1 proinflammatory phenotype in response to increased dietary salt and highlighted potential adverse effects of Clod-Lipo macrophage depletion.

Chronic autoimmune disorders are increased in coeliac disease: A case-control study

Coeliac disease (CD) is an autoimmune disorder of the small bowel associated with increased risk of additional autoimmune diseases (ADs).To investigate the prevalence of ADs in a population of adult coeliac patients.This was a retrospective case-control study. Data from coeliac patients and controls referred to a tertiary center between 2013 and 2016 were collected. The frequency of ADs and the unadjusted and adjusted odds ratios (ORs) for age, gender, disease duration, and body mass index with their 95% confidence intervals (CIs) were evaluated.Two hundred fifty-five patients with CD (median age 37.1 years; 206 women) were matched with 250 controls. ADs were more frequent (35.3%) in coeliac patients than in controls (15.2%). Adjusted ORs for the presence of only 1, at least 1, and more than 1 AD were 3.13 (95% CI 1.81-5.42, P < .0001), 3.31 (95% CI 2.00-5.46, P < .0001), and 3.93 (95% CI 1.49-10.36, P = .006), respectively. Hashimoto thyroiditis was the most prevalent AD (24.3% vs. 10%) OR = 2.55 (95% CI 1.39-4.70, P < .0001), followed by psoriasis (4.3% vs. 1.6%), type 1 diabetes (2.7% vs. 0.4%), and Sjögren syndrome (2.4% vs. 0.4%).These findings suggest a need for a careful surveillance of autoimmune status, especially for Hashimoto thyroiditis in patients with celiac disease.

Novel diagnostic techniques for celiac disease

The diagnosis of celiac disease has long been based on the demonstration of gluten-induced small-bowel mucosal damage. However, due to the constantly increasing disease prevalence and limitations in the histology-based criteria there is a pressure towards more serology-based diagnostics. The serological tools are being improved and new non-invasive methods are being developed, but the constantly refined endoscopic and histologic techniques may still prove helpful. Moreover, growing understanding of the disease pathogenesis has led researchers to suggest completely novel approaches to celiac disease diagnostics regardless of disease activity. In this review, we will elucidate the most recent development and possible future innovations in the diagnostic techniques for celiac disease.