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.

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

Methods

Results

Conclusions

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.

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".

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.

Convergence of Position Auctions under Myopic Best-Response Dynamics

We study the dynamics of multiround position auctions, considering both the case of exogenous click-through rates and the case in which click-through rates are determined by an endogenous consumer search process. In both contexts, we demonstrate that dynamic position auctions converge to their associated static, envy-free equilibria. Furthermore, convergence is efficient, and the entry of low-quality advertisers does not slow convergence. Because our approach predominantly relies on assumptions common in the sponsored search literature, our results suggest that dynamic position auctions converge more generally.