Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists.

BACKGROUND : We aimed to compare the accuracy of the optical diagnosis of diminutive colorectal polyps, including sessile serrated lesions (SSLs), between a computer-aided diagnosis (CADx) system and endoscopists during real-time colonoscopy. METHODS : We developed the POLyp Artificial Recognition (POLAR) system, which was capable of performing real-time characterization of diminutive colorectal polyps. For pretraining, the Microsoft-COCO dataset with over 300 000 nonpolyp object images was used. For training, eight hospitals prospectively collected 2637 annotated images from 1339 polyps (i. e. publicly available online POLAR database). For clinical validation, POLAR was tested during colonoscopy in patients with a positive fecal immunochemical test (FIT), and compared with the performance of 20 endoscopists from eight hospitals. Endoscopists were blinded to the POLAR output. Primary outcome was the comparison of accuracy of the optical diagnosis of diminutive colorectal polyps between POLAR and endoscopists (neoplastic [adenomas and SSLs] versus non-neoplastic [hyperplastic polyps]). Histopathology served as the reference standard. RESULTS : During clinical validation, 423 diminutive polyps detected in 194 FIT-positive individuals were included for analysis (300 adenomas, 41 SSLs, 82 hyperplastic polyps). POLAR distinguished neoplastic from non-neoplastic lesions with 79 % accuracy, 89 % sensitivity, and 38 % specificity. The endoscopists achieved 83 % accuracy, 92 % sensitivity, and 44 % specificity. The optical diagnosis accuracy between POLAR and endoscopists was not significantly different (P = 0.10). The proportion of polyps in which POLAR was able to provide an optical diagnosis was 98 % (i. e. success rate). CONCLUSIONS : We developed a CADx system that differentiated neoplastic from non-neoplastic diminutive polyps during endoscopy, with an accuracy comparable to that of screening endoscopists and near-perfect success rate.

Irrigating Acetic Acid Solution During Colonoscopy for the Detection of Sessile Serrated Neoplasia: A Randomized Controlled Trial.

BACKGROUND: Misdiagnosed sessile serrated lesions (SSLs) are important precursors for interval colorectal cancers. AIMS: We investigated the usage of acetic acid (AA) solution for improving the detection of SSLs in the right colon in a randomized controlled trial. METHODS: A tandem observation of the right colon was performed in 412 consecutive patients. A first inspection was performed under white light high-definition endoscopy. In the AA group, a low concentration vinegar solution (AA: 0.005%) irrigated by a water pump in the right colon was compared with a plain solution of normal saline (NS) in the diagnostic yield of SSLs during the second inspection. Secondary outcomes in overall polyp detection were measured. RESULTS: Qualitative comparisons showed significant differences in the detection rates of all polyps except adenomas, with remarkable improvement in the demonstration of advanced (> 20 mm), SSLs, and hyperplastic polyps during the second inspection of the right colon using the AA solution. Significant improvement was also noted in the AA group, as far as the mean number of polyps/patient detected, not only in SSLs (AA group: 0.14 vs. NS group: 0.01, P < 0.001), but also in all histological types and all size-categories in the right colon. Small (≤ 9 mm) polyps were detected at a higher rate in the sigmoid colon expanding the effect of the method in the rest of the colon. CONCLUSION: AA-assisted colonoscopy led to a significant increase in SSLs detection rate in the right colon in a safe, quick, and effective manner.

Comparison of the Uptake of Screening Colonoscopy between Physicians and the General Population in Greece.

AIM: To evaluate the uptake of screening colonoscopy among physicians as compared to the general population. METHODS: Asymptomatic physicians, aged 45-67 years, at average risk for colorectal cancer (CRC), working in the participating National Health System hospitals were asked to complete a questionnaire regarding the uptake of screening colonoscopy. The results were compared to those in a background healthy population, aged 50-75 years, inhabitants of a Greek county, who were offered a free access to a screening colonoscopy program for CRC. High-risk adenomas were those ≥10 mm in diameter or any adenoma, regardless of size, with villous histology or high-grade dysplasia. RESULTS: Overall, 267 of 782 physicians and 402 of 6,534 nonphysicians underwent a screening colonoscopy (uptake rates 34.2 and 6.2% respectively, p = 0.00001). Screening colonoscopy has yielded 4 adenocarcinomas (1.6%), 14 high-risk adenomas (5.5%), and 61 low-risk adenomas (25.7%) in the physicians' group. Corresponding figures in the nonphysician arm were 4 (1), 26 (6.5), and 107 (26.6%), respectively. The main reason among physicians for nonadherence was indifference/negligence (n = 213). CONCLUSION: The proportion of physicians undergoing screening colonoscopy for CRC is significantly higher compared to the general population; however, it does remain suboptimal.

Discriminative power of visual attributes in dermatology.

BACKGROUND/PURPOSE: Visual characteristics such as color and shape of skin lesions play an important role in the diagnostic process. In this contribution, we quantify the discriminative power of such attributes using an information theoretical approach. METHODS: We estimate the probability of occurrence of each attribute as a function of the skin diseases. We use the distribution of this probability across the studied diseases and its entropy to define the discriminative power of the attribute. The discriminative power has a maximum value for attributes that occur (or do not occur) for only one disease and a minimum value for those which are equally likely to be observed among all diseases. RESULTS: Verrucous surface, red and brown colors, and the presence of more than 10 lesions are among the most informative attributes. A ranking of attributes is also carried out and used together with a naive Bayesian classifier, yielding results that confirm the soundness of the proposed method. CONCLUSION: proposed measure is proven to be a reliable way of assessing the discriminative power of dermatological attributes, and it also helps generate a condensed dermatological lexicon. Therefore, it can be of added value to the manual or computer-aided diagnostic process.

Prevalence and predictors of arthralgia after initiation of vedolizumab in patients with inflammatory bowel disease: a retrospective cohort study.

OBJECTIVES: Vedolizumab is a mAb used for the treatment of moderate to severe ulcerative colitis and Crohn's disease. There is evidence that administration of vedolizumab has been associated with either new onset or reactivation of extra-intestinal manifestations, among which arthralgia is the most prominent. We aimed to study the incidence, characteristics and predictors for the occurrence of arthralgias in patients with inflammatory bowel disease (IBD) who receive vedolizumab. METHODS: A retrospective cohort study was implemented in patients with IBD. The occurrence of new-onset and recurrent arthralgias were recorded. Multivariate Cox proportional-hazards models were used to identify factors associated with the endpoints of interest. RESULTS: A total of 115 vedolizumab-treated IBD patients (male = 50.4%; ulcerative colitis = 70.4%; median follow-up = 12.7 months) participated. New-onset arthralgia occurred in 20.9%, and recurrent in 46.7% (45 patients at risk). Among patients with ulcerative colitis, multivariate Cox's proportional-hazards models showed, that new onset arthralgia was significantly associated with extensive colitis (hazard ratio = 2.91; 95% confidence interval, 1.04-8.12). Of 15 patients with concomitant treatment of azathioprine, no one manifested new-onset arthralgia (X2P = 0.03; Fisher's exact test P = 0.038). No predictors were identified for recurrent arthralgia. CONCLUSION: Arthralgias is a common manifestation of vedolizumab treatment. Patients with extensive ulcerative colitis demonstrate a higher risk for new-onset arthralgia, whereas, concomitant treatment with azathioprine appears to be protective. These associations may be mediated by re-directed lymphocyte trafficking and may support concomitant immunomodulator administration in specific patient subpopulations who commence treatment with vedolizumab.

Prospective comparison of an adult, an intermediate pediatric and a long pediatric colonoscope in the training process of gastrointestinal fellows to achieve high-quality practice in colonoscopy.

Background: Few data are available on the influence of colonoscope type on the training process and quality of colonoscopy. We conducted this prospective observational cohort study to investigate scope suitability for starting colonoscopy training, in relation to technical competence, quality indicators, and the patient's comfort during diagnostic colonoscopy. Methods: A total of 126 consecutive patients were enrolled in the study and assigned to one of 3 groups: adult colonoscope ([AC], n=41); intermediate pediatric colonoscope ([IPC], n=43); and long pediatric colonoscope ([LPC], n=42). Primary outcomes were completeness of the examination and minutes to the cecum. Secondary outcomes included patient tolerance, position change, use of abdominal compression, loop formation, kind of loop, and overall difficulty of the procedure. Results: Cecal intubation rates were not statistically different between the groups: AC/87.8%; IPC/81.4%; and LPC/92.8%. Terminal ileal intubation rate differed significantly among the 3 groups (P=0.015) with LPC having the higher rate (66.7% vs. 60.9%/AC and 37.2%/IPC). There were significant differences in positional changes (fewer with LPC/1.36 vs. AC/2.15 and IPC/2.09, P=0.027) and midazolam administered doses (lower with LPC/0.52 vs. AC/1.07 and IPC/0.93, P=0.032). Loop formation with subsequent resolution was significantly associated with more pain for the patient with all of the 3 colonoscope types. Conclusions: The LPC performs better in trainee hands than AC and IPC in terms of reaching competency, and quality indicators show less discomfort for the patients during colonoscopic procedures (lower midazolam dose and fewer positional changes). It could be considered the most suitable scope for starting high-quality colonoscopy training.

A rare case of duodenal-type follicular lymphoma in rectum appearing as hyperplastic polyp with metachronous appearance in duodenum and stomach.

Hyperplastic polyps consist a very frequent finding in colonoscopy having a very low potential to malignancy. According to the international guidelines, it is recommended that all polyps should be resected except for diminutive (≤ 5 mm) rectal and rectosigmoid polyps which are predicted with confidence to be hyperplastic. Therefore, in departments where optical diagnosis can be ensured, a "resect and discard" strategy may be implemented for diminutive polyps. In our case, a duodenal-type follicular lymphoma was detected in a 5 mm rectum polyp with hyperplastic appearance. After 4 months, the lymphoma was detected also in stomach and duodenum. Under therapy with Rituximab, she is in remission. To our knowledge, there has never been reported such a case in the literature. Furthermore, it alerts us that we should be very cautious with the optical diagnosis and the "resect and discard strategy".

Next move in movement disorders (NEMO): developing a computer-aided classification tool for hyperkinetic movement disorders.

INTRODUCTION: Our aim is to develop a novel approach to hyperkinetic movement disorder classification, that combines clinical information, electromyography, accelerometry and video in a computer-aided classification tool. We see this as the next step towards rapid and accurate phenotype classification, the cornerstone of both the diagnostic and treatment process. METHODS AND ANALYSIS: The Next Move in Movement Disorders (NEMO) study is a cross-sectional study at Expertise Centre Movement Disorders Groningen, University Medical Centre Groningen. It comprises patients with single and mixed phenotype movement disorders. Single phenotype groups will first include dystonia, myoclonus and tremor, and then chorea, tics, ataxia and spasticity. Mixed phenotypes are myoclonus-dystonia, dystonic tremor, myoclonus ataxia and jerky/tremulous functional movement disorders. Groups will contain 20 patients, or 40 healthy participants. The gold standard for inclusion consists of interobserver agreement on the phenotype among three independent clinical experts. Electromyography, accelerometry and three-dimensional video data will be recorded during performance of a set of movement tasks, chosen by a team of specialists to elicit movement disorders. These data will serve as input for the machine learning algorithm. Labels for supervised learning are provided by the expert-based classification, allowing the algorithm to learn to predict what the output label should be when given new input data. Methods using manually engineered features based on existing clinical knowledge will be used, as well as deep learning methods which can detect relevant and possibly new features. Finally, we will employ visual analytics to visualise how the classification algorithm arrives at its decision. ETHICS AND DISSEMINATION: Ethical approval has been obtained from the relevant local ethics committee. The NEMO study is designed to pioneer the application of machine learning of movement disorders. We expect to publish articles in multiple related fields of research and patients will be informed of important results via patient associations and press releases.