Explore the vast range of titles available.

Oral Squamous Cell Carcinoma (OSCC) is a common type of cancer of the oral epithelium. Despite their high impact on mortality, sufficient screening methods for early diagnosis of OSCC often lack accuracy and thus OSCCs are mostly diagnosed at a late stage. Early detection and accurate outline estimation of OSCCs would lead to a better curative outcome and a reduction in recurrence rates after surgical treatment. Confocal Laser Endomicroscopy (CLE) records sub-surface micro-anatomical images for in vivo cell structure analysis. Recent CLE studies showed great prospects for a reliable, real-time ultrastructural imaging of OSCC in situ . We present and evaluate a novel automatic approach for OSCC diagnosis using deep learning technologies on CLE images. The method is compared against textural feature-based machine learning approaches that represent the current state of the art. For this work, CLE image sequences (7894 images) from patients diagnosed with OSCC were obtained from 4 specific locations in the oral cavity, including the OSCC lesion. The present approach is found to outperform the state of the art in CLE image recognition with an area under the curve (AUC) of 0.96 and a mean accuracy of 88.3% (sensitivity 86.6%, specificity 90%).

Linked color imaging (LCI) has been shown to be effective in multiple randomized controlled trials for enhanced colorectal polyp detection. Recently, artificial intelligence (AI) with deep learning through convolutional neural networks has dramatically improved and is increasingly recognized as a promising new technique for enhancing colorectal polyp detection. This study aims to evaluate a newly developed computer-aided detection (CAD) system in combination with LCI for colorectal polyp detection. First, a convolutional neural network was trained for colorectal polyp detection in combination with the LCI technique using a dataset of anonymized endoscopy videos. For validation, 240 polyps within fully recorded endoscopy videos in LCI mode, covering the entire spectrum of adenomatous histology, were used. Sensitivity (true-positive rate per lesion) and false-positive frames in a full procedure were assessed. The new CAD system used in LCI mode could process at least 60 frames per second, allowing for real-time video analysis. Sensitivity (true-positive rate per lesion) was 100%, with no lesion being missed. The calculated false-positive frame rate was 0.001%. Among the 240 polyps, 34 were sessile serrated lesions. The detection rate for sessile serrated lesions with the CAD system used in LCI mode was 100%. The new CAD system used in LCI mode achieved a 100% sensitivity per lesion and a negligible false-positive frame rate. Note that the new CAD system used in LCI mode also specifically allowed for detection of serrated lesions in all cases. Accordingly, the AI algorithm introduced here for the first time has the potential to dramatically improve the quality of colonoscopy.

The use of antibodies against tumour necrosis factor (TNF) has markedly improved the treatment of Crohn's disease, but only certain patients respond to therapy. Here, Raja Atreya and colleagues have developed an approach using topical fluorescent antibodies to TNF and confocal laser endomicroscopy to evaluate the expression of transmembrane TNF (mTNF) in the intestinal mucosa of patients with active Crohn's disease in order to identify patients likely to respond to subsequent treatment with the anti-TNF therapy, adalimumab. As antibodies to tumor necrosis factor (TNF) suppress immune responses in Crohn's disease by binding to membrane-bound TNF (mTNF), we created a fluorescent antibody for molecular mTNF imaging in this disease. Topical antibody administration in 25 patients with Crohn's disease led to detection of intestinal mTNF + immune cells during confocal laser endomicroscopy. Patients with high numbers of mTNF + cells showed significantly higher short-term response rates (92%) at week 12 upon subsequent anti-TNF therapy as compared to patients with low amounts of mTNF + cells (15%). This clinical response in the former patients was sustained over a follow-up period of 1 year and was associated with mucosal healing observed in follow-up endoscopy. These data indicate that molecular imaging with fluorescent antibodies has the potential to predict therapeutic responses to biological treatment and can be used for personalized medicine in Crohn's disease and autoimmune or inflammatory disorders.

Introduction: Since the advent of artificial intelligence (AI) in clinical studies, luminal gastrointestinal endoscopy has made great progress, especially in the detection and characterization of neoplastic and preneoplastic lesions. Several studies have recently shown the potential of AI-driven endoscopy for the investigation of inflammatory bowel disease (IBD). This systematic review provides an overview of the current position and future potential of AI in IBD endoscopy. Methods: A systematic search was carried out in PubMed and Scopus up to 2 December 2020 using the following search terms: artificial intelligence, machine learning, computer-aided, inflammatory bowel disease, ulcerative colitis (UC), Crohn’s disease (CD). All studies on human digestive endoscopy were included. A qualitative analysis and a narrative description were performed for each selected record according to the Joanna Briggs Institute methodologies and the PRISMA statement. Results: Of 398 identified records, 18 were ultimately included. Two-thirds of these (12/18) were published in 2020 and most were cross-sectional studies (15/18). No relevant bias at the study level was reported, although the risk of publication bias across studies cannot be ruled out at this early stage. Eleven records dealt with UC, five with CD and two with both. Most of the AI systems involved convolutional neural network, random forest and deep neural network architecture. Most studies focused on capsule endoscopy readings in CD (n = 5) and on the AI-assisted assessment of mucosal activity in UC (n = 10) for automated endoscopic scoring or real-time prediction of histological disease. Discussion: AI-assisted endoscopy in IBD is a rapidly evolving research field with promising technical results and additional benefits when tested in an experimental clinical scenario. External validation studies being conducted in large and prospective cohorts in real-life clinical scenarios will help confirm the added value of AI in assessing UC mucosal activity and in CD capsule reading. Plain language summary Artificial intelligence for inflammatory bowel disease endoscopy Artificial intelligence (AI) is a promising technology in many areas of medicine. In recent years, AI-assisted endoscopy has been introduced into several research fields, including inflammatory bowel disease (IBD) endoscopy, with promising applications that have the potential to revolutionize clinical practice and gastrointestinal endoscopy. We have performed the first systematic review of AI and its application in the field of IBD and endoscopy. A formal process of paper selection and analysis resulted in the assessment of 18 records. Most of these (12/18) were published in 2020 and were cross-sectional studies (15/18). No relevant biases were reported. All studies showed positive results concerning the novel technology evaluated, so the risk of publication bias cannot be ruled out at this early stage. Eleven records dealt with UC, five with CD and two with both. Most studies focused on capsule endoscopy reading in CD patients (n = 5) and on AI-assisted assessment of mucosal activity in UC patients (n = 10) for automated endoscopic scoring and real-time prediction of histological disease. We found that AI-assisted endoscopy in IBD is a rapidly growing research field. All studies indicated promising technical results. When tested in an experimental clinical scenario, AI-assisted endoscopy showed it could potentially improve the management of patients with IBD. Confirmatory evidence from real-life clinical scenarios should be obtained to verify the added value of AI-assisted IBD endoscopy in assessing UC mucosal activity and in CD capsule reading.

Acute graft versus host disease (aGvHD) is an important, life-threatening complication after allogeneic hematopoietic stem cell transplantation (alloHSCT). To investigate the value of multiple simultaneous colon biopsies in improving diagnostic accuracy in patients with aGvHD, we retrospectively analyzed 157 patients after alloHSCT. The biopsies were evaluated individually using three established histological grading systems (Lerner, Sale, and Melson). The maximum, minimum, median, and mean histological aGvHD grades were calculated for each patient, and the results were correlated with the Glucksberg grade of clinical manifestation of GvHD, steroid therapy status, and outcome. We found that multiple colon biopsies enhanced diagnostic sensitivity. Moreover, higher histological grades correlated with steroid therapy initiation and refractoriness; the latter particularly occurred when advanced damage was present in all samples and healthy colon mucosa was reduced or absent. On multivariate analysis, the minimal Lerner and Glucksberg grades for intestinal aGvHD were significantly associated with steroid treatment failure. Ninety-nine patients died. The median survival was 285 days after the biopsies were taken. Fifteen patients died from relapse of their underling disorder and 84 from other causes, mostly infection (53 patients) and GvHD (14 patients). Multivariate analysis revealed a significant association between none-relapse mortality and the mean Lerner grade, minimum Melson grade, Glucksberg organ stage, and platelet counts. Thus, we found the Lerner system to be superior to the other grading methods in most instances and histologic evaluation of multiple simultaneously obtained biopsies from the colon to result in a higher diagnostic yield, which helps plan systemic steroid treatment while predicting treatment response and outcome.

IntroductionIn light-emitting diode (LED) and LASER colonoscopy, linked color imaging (LCI) and blue light/laser imaging (BLI) are used for lesion detection and characterization worldwide. We analyzed the difference of LCI and BLI images of colorectal lesions between LED and LASER in a multinational study.MethodsWe prospectively observed lesions with white light imaging (WLI), LCI, and BLI using both LED and LASER colonoscopies from January 2020 to August 2021. Images were graded by 27 endoscopists from nine countries using the polyp visibility score: 4 (excellent), 3 (good), 2 (fair), and 1 (poor) and the comparison score (LED better/similar/LASER better) for WLI/LCI/BLI images of each lesion.ResultsFinally, 32 lesions (polyp size: 20.0 ± 15.2 mm) including 9 serrated lesions, 13 adenomas, and 10 T1 cancers were evaluated. The polyp visibility scores of LCI/WLI for international and Japan-expert endoscopists were 3.17 ± 0.73/3.17 ± 0.79 (p = 0.92) and 3.34 ± 0.78/2.84 ± 1.22 (p < 0.01) for LED and 3.30 ± 0.71/3.12 ± 0.77 (p < 0.01) and 3.31 ± 0.82/2.78 ± 1.23 (p < 0.01) for LASER. Regarding the comparison of lesion visibility about between LED and LASER colonoscopy in international endoscopists, a significant difference was achieved not for WLI, but for LCI. The rates of LED better/similar/LASER better for brightness under WLI were 54.5%/31.6%/13.9% (International) and 75.0%/21.9%/3.1% (Japan expert). Those under LCI were 39.2%/35.4%/25.3% (International) and 31.3%/53.1%/15.6% (Japan expert). There were no significant differences in the diagnostic accuracy and the comparison score of BLI images between LED and LASER.ConclusionsThe differences of lesion visibility for WLI/LCI/BLI between LED and LASER in international endoscopists could be compared to those in Japanese endoscopists.

Despite major technical advancements, endoscopic surveillance for detecting premalignant lesions in Barrett's esophagus is challenging because of their flat appearance with only subtle morphological changes. Molecular endoscopic imaging (MEI) using nanoparticles (NPs), coupled with fluorescently labeled antibody permits visualization of disease-specific molecular alterations. The aim of this ex vivo study was to assess the diagnostic applicability of MEI with NPs to detect Barrett's metaplasia. Seven patients undergoing endoscopic surveillance of known Barrett's esophagus were recruited. Freshly resected biopsy specimens were incubated with NPs coupled with FITC labeled Muc-2 antibodies and examined with MEI. Fluorescence intensity from Barrett's mucosa and control specimens were compared, followed by histological confirmation. Fluorescence signals, indicating the presence of goblet cells, were noted for traditional MEI using Muc-2 antibodies in Barrett's intestinal metaplasia. Significantly stronger fluorescence signals were achieved with NPs coupled with FITC-conjugated Muc-2 antibodies. The results of MEI with NPs for the prediction of Barrett's metaplasia correlated with the final histopathological examination in all the cases. Highly-specific NPs detected Barrett's metaplasia more efficiently than conventional MEI in this first feasibility study. MEI was as effective as standard histopathology for identifying Muc-2 containing goblet cells for diagnosis of Barrett's metaplasia. (DRKS-ID: DRKS00017747)

Purpose:Probe-based confocal laser endomicroscopy (pCLE) is a subcellular in vivo imaging technique capable of producing images that enable diagnosis of malign structural modifications in epithelial tissue. Images acquired with pCLE are, however, often tainted by significant artifacts that impair diagnosis. This is especially detrimental for automated image analysis, which is why said images are often excluded from recognition pipelines.MethodsWe present an approach for the automatic detection of motion artifacts in pCLE images and apply this methodology to a data set of 15 thousand images of epithelial tissue acquired in the oral cavity and the vocal folds. The approach is based on transfer learning from intermediate endpoints within a pre-trained Inception v3 network with tailored preprocessing. For detection within the non-rectangular pCLE images, we perform pooling within the activation maps of the network and evaluate this at different network depths.ResultsWe achieved area under the ROC curve values of 0.92 with the proposed method, compared to 0.80 for the best feature-based machine learning approach. Our overall accuracy with the presented approach is 94.8%.ConclusionOver traditional machine learning approaches with state-of-the-art features, we achieved significantly improved overall performance.

Background High quality bowel preparation prior to colonoscopy can be difficult to achieve in the inpatient setting. Hospitalized patients are at risk for extended hospital stays and low diagnostic yield due to inadequate bowel preparation. The Pure-Vu System is a novel device intended to fit over existing colonoscopes to improve intra-colonoscopy bowel preparation. The objective of the REDUCE study was to conduct the first inpatient study to evaluate optimization of bowel preparation quality following overnight preparation when using the Pure-Vu System during colonoscopy. Methods This multicenter, prospective feasibility study enrolled hospitalized subjects undergoing colonoscopy. Subjects recorded the clarity of their last bowel movement using a 5-point scale prior to colonoscopy. After one night of preparation, all enrolled subjects underwent colonoscopy utilizing the Pure-Vu System. The primary endpoint was improvement of colon cleanliness from baseline to post-cleansing with the Pure-Vu System as assessed by the improvement in Boston Bowel Preparation Scale (BBPS). An exploratory analysis was conducted to assess whether the clarity of the last bowel movement could predict inadequate bowel preparation. Results Ninety-four subjects were included. BBPS analyses showed significant improvements in bowel preparation quality across all evaluable colon segments after cleansing with Pure-Vu, including left colon (1.74 vs 2.89; p < 0.0001), transverse colon (1.74 vs 2.91; p < 0.0001), and the right colon (1.41 vs 2.88; p < 0.0001). Prior to Pure-Vu, adequate cleansing (BBPS scores of ≥ 2) were reported in 60%, 62%, and 47% for the left colon, transverse colon, and right colon segments, respectively. After intra-colonoscopy cleansing with the Pure-Vu System, adequate colon preparation was reported in 100%, 99%, and 97% of the left colon, transverse colon, and right colon segments, respectively. Subjects with lower bowel movement clarity scores were more likely to have inadequate bowel preparation prior to cleansing with Pure-Vu. Conclusions In this feasibility study, the Pure-Vu System appears to be effective in significantly improving bowel preparation quality in hospitalized subjects undergoing colonoscopy. Clarity of last bowel movement may be useful indicator in predicting poor bowel preparation. Larger studies powered to evaluate clinical outcomes, hospital costs, and blinded BBPS assessments are required to evaluate the significance of these findings. Trial registration Evaluation of the Bowel Cleansing in Hospitalized Patients Using Pure-Vu System (NCT03503162).

Background: Although colonoscopy is the gold standard for colorectal cancer screening, colonic looping may make complete colonoscopy challenging. Commonly available stiffening device colonoscopy has been described as helpful but not effective enough to prevent looping. In this context the effect on cecal intubation time and rate was described differently in various studies and in some studies had no impact on cecal intubation time at all. The aim of this study was to evaluate whether a novel colonoscope with gradual stiffness (Fujifilm EC760R-V/I- flexibility adjuster, Tokyo, Japan) using four significantly different grades of stiffness can be an alternative to established devices in terms of loop prevention, cecal intubation rate and time, adverse events, and patient/examiner satisfaction. Methods: Consecutive patients without previous colorectal surgery were analyzed retrospectively. Colonoscopy was performed with the new colonoscope and performance characteristics, including time to cecum, withdrawal time, total examination time, and patient and endoscopist satisfaction were recorded. Results: Among 180 consecutive procedures, 98.3% of examinations were complete to the cecum. The endoscopic flexibility adjuster was used in 150 of 180 cases (83.3%). Overall, the device was scored by the examiner as helpful to prevent looping in 146 of the 150 cases (97.7%). Mean cecal intubation time was 6.5 min, with 35% of examination performed in under 5 min with a mean withdrawal time of 7 min. Mean total examination time was 18 min. Patient satisfaction was rated as high in all examinations performed. Conclusion: The new flexibility adjuster colonoscope was shown to be helpful in loop prevention, allowed for fast and successful cecal intubation, and led to a high rate of patients satisfaction.