Search

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. [ABSTRACT FROM AUTHOR]

Assessment of the anatomical colorectal segment of polyps during colonoscopy is important for treatment and follow-up strategies, but is largely operator dependent. This feasibility study aimed to assess whether, using images of a magnetic endoscope imaging (MEI) positioning device, a deep learning approach can be useful to objectively divide the colorectum into anatomical segments. Models based on the VGG-16 based convolutional neural network architecture were developed to classify the colorectum into anatomical segments. These models were pre-trained on ImageNet data and further trained using prospectively collected data of the POLAR study in which endoscopists were using MEI (3930 still images and 90,151 video frames). Five-fold cross validation with multiple runs was used to evaluate the overall diagnostic accuracies of the models for colorectal segment classification (divided into a 5-class and 2-class colorectal segment division). The colorectal segment assignment by endoscopists was used as the reference standard. For the 5-class colorectal segment division, the best performing model correctly classified the colorectal segment in 753 of the 1196 polyps, corresponding to an overall accuracy of 63%, sensitivity of 63%, specificity of 89% and kappa of 0.47. For the 2-class colorectal segment division, 1112 of the 1196 polyps were correctly classified, corresponding to an accuracy of 93%, sensitivity of 93%, specificity of 90% and kappa of 0.82. The diagnostic performance of a deep learning approach for colorectal segment classification based on images of a MEI device is yet suboptimal (clinicaltrials.gov: NCT03822390). [ABSTRACT FROM AUTHOR]

BACKGROUND : The European Society of Gastrointestinal Endoscopy (ESGE) has developed a core curriculum for high quality optical diagnosis training for practice across Europe. The development of easy-to-measure competence standards for optical diagnosis can optimize clinical decision-making in endoscopy. This manuscript represents an official Position Statement of the ESGE aiming to define simple, safe, and easy-to-measure competence standards for endoscopists and artificial intelligence systems performing optical diagnosis of diminutive colorectal polyps (1 - 5 mm). METHODS : A panel of European experts in optical diagnosis participated in a modified Delphi process to reach consensus on Simple Optical Diagnosis Accuracy (SODA) competence standards for implementation of the optical diagnosis strategy for diminutive colorectal polyps. In order to assess the clinical benefits and harms of implementing optical diagnosis with different competence standards, a systematic literature search was performed. This was complemented with the results from a recently performed simulation study that provides guidance for setting alternative competence standards for optical diagnosis. Proposed competence standards were based on literature search and simulation study results. Competence standards were accepted if at least 80 % agreement was reached after a maximum of three voting rounds. RECOMMENDATION 1:  In order to implement the leave-in-situ strategy for diminutive colorectal lesions (1-5 mm), it is clinically acceptable if, during real-time colonoscopy, at least 90 % sensitivity and 80 % specificity is achieved for high confidence endoscopic characterization of colorectal neoplasia of 1-5 mm in the rectosigmoid. Histopathology is used as the gold standard.Level of agreement 95 %. RECOMMENDATION 2:  In order to implement the resect-and-discard strategy for diminutive colorectal lesions (1-5 mm), it is clinically acceptable if, during real-time colonoscopy, at least 80 % sensitivity and 80 % specificity is achieved for high confidence endoscopic characterization of colorectal neoplasia of 1-5 mm. Histopathology is used as the gold standard.Level of agreement 100 %. CONCLUSION : The developed SODA competence standards define diagnostic performance thresholds in relation to clinical consequences, for training and for use when auditing the optical diagnosis of diminutive colorectal polyps. [ABSTRACT FROM AUTHOR]

1:  ESGE suggests that high definition endoscopy, and dye or virtual chromoendoscopy, as well as add-on devices, can be used in average risk patients to increase the endoscopist's adenoma detection rate. However, their routine use must be balanced against costs and practical considerations.Weak recommendation, high quality evidence. 2:  ESGE recommends the routine use of high definition systems in individuals with Lynch syndrome.Strong recommendation, high quality evidence. 3:  ESGE recommends the routine use, with targeted biopsies, of dye-based pancolonic chromoendoscopy or virtual chromoendoscopy for neoplasia surveillance in patients with long-standing colitis.Strong recommendation, moderate quality evidence. 4:  ESGE suggests that virtual chromoendoscopy and dye-based chromoendoscopy can be used, under strictly controlled conditions, for real-time optical diagnosis of diminutive (≤ 5 mm) colorectal polyps and can replace histopathological diagnosis. The optical diagnosis has to be reported using validated scales, must be adequately photodocumented, and can be performed only by experienced endoscopists who are adequately trained, as defined in the ESGE curriculum, and audited.Weak recommendation, high quality evidence. 5:  ESGE recommends the use of high definition white-light endoscopy in combination with (virtual) chromoendoscopy to predict the presence and depth of any submucosal invasion in nonpedunculated colorectal polyps prior to any treatment. Strong recommendation, moderate quality evidence. 6:  ESGE recommends the use of virtual or dye-based chromoendoscopy in addition to white-light endoscopy for the detection of residual neoplasia at a piecemeal polypectomy scar site. Strong recommendation, moderate quality evidence. 7:  ESGE suggests the possible incorporation of computer-aided diagnosis (detection and characterization of lesions) to colonoscopy, if acceptable and reproducible accuracy for colorectal neoplasia is demonstrated in high quality multicenter in vivo clinical studies. Possible significant risks with implementation, specifically endoscopist deskilling and over-reliance on artificial intelligence, unrepresentative training datasets, and hacking, need to be considered. Weak recommendation, low quality evidence. [ABSTRACT FROM AUTHOR]

Background: Optical diagnosis can replace histopathology of diminutive (1 - 5 mm) polyps if surveillance intervals based on optical diagnosis of polyps have ≥ 90 % agreement with intervals based on polyp histology and if the negative predictive value (NPV) for predicting neoplastic histology in the rectosigmoid is ≥ 90 %. This study aims to assess whether small (6 - 9 mm) polyps can be included in optical diagnosis strategies.Method: This is a post-hoc analysis of a prospective multicenter study in which 27 endoscopists, all performing endoscopies for the Dutch screening program, were trained in optical diagnosis. For 1 year, endoscopists recorded the predicted histology for all lesions detected using narrow-band imaging during 3144 consecutive colonoscopies after a positive fecal immunochemical test, along with confidence levels. Surveillance interval agreement and NPV were calculated for high confidence predictions for polyps of 1 - 9 mm and compared with histopathology. Surveillance interval agreement was calculated using the European Society of Gastrointestinal Endoscopy surveillance guideline.Results: Surveillance interval agreement was 95.4 % (confidence interval [CI] 94.2 % - 96.4 %), and NPV for predicting neoplastic histology in the rectosigmoid 90.0 % (CI 87.3 % - 92.2 %). The reduction in histology (45.9 % vs. 30.5 %) and the proportion of patients who could have received direct surveillance advice (15.6 % vs. 7.3 %) was higher when small polyps were included (P < 0.001). T1 cancer was found in seven small polyps (0.33 %), five of which would have been discarded without histopathology.Conclusion: Including small polyps in the optical diagnosis strategy improves its efficacy while maintaining performance thresholds. However, there is a small risk of missing T1 cancers when small polyps are included in the optical diagnosis strategy. [ABSTRACT FROM AUTHOR]

In 2019, the European Society of Gastrointestinal Endoscopy (ESGE) stated that virtual chromoendoscopy (e. g. narrow-band imaging) and dye-based chromoendoscopy can be used, under strictly controlled conditions, for real-time optical diagnosis of diminutive polyps performed by experienced endoscopists who are adequately trained [3]. Effects of training and feedback on accuracy of predicting rectosigmoid neoplastic lesions and selection of surveillance intervals by endoscopists performing optical diagnosis of diminutive polyps. Although small polyps have a relatively low risk of harboring advanced histology, T1 cancers do occur in polyps 5-9 mm in size and these small lesions are often not recognized as such by the endoscopist [8]. [Extracted from the article]

Background and study aims: Serrated polyps of the large intestine comprise a heterogeneous group of lesions with distinct histological and malignant features. The aim of the study was to estimate the prevalence of serrated polyp subtypes in a cohort of individuals undergoing screening colonoscopy, and to identify associations between the detection of serrated polyp subtypes and advanced neoplasia. Patients and methods: Data on serrated polyps, adenomas, and cancerswere collected from participants of a randomized screening trial that compared colonoscopy with computed tomography colonography. Only data from participants in the colonoscopy arm were used. Logistic regression analyses were performed to identify associations between patients' age, sex, and prevalence of the different types of serrated polyps and to identify associations between the detection of these polyps and advanced neoplasia (defined as an adenoma ⩾10mm, villous component, high grade dysplasia or colorectal cancer). Results: A total of 1426 screen-naïve individuals (51% male) with a median age of 60 years (IQR 55-65) were included. The prevalence of hyperplastic polyps, sessile serrated adenomas/polyps (SSA/Ps), and traditional serrated adenomas (TSAs) was 23.8 %, 4.8 %, and 0.1 %, respectively. SSA/Ps comprised 7.3% of all polyps. No differences based on age or sex were observed in the prevalence of SSA/Ps. Proximal and large (⩾10 mm) hyperplastic polyps, as well as proximal and large (⩾10mm) SSA/Ps, were associated with synchronous advanced neoplasia. Conclusions: Serrated polyps, including SSA/Ps, were frequently encountered in routine screening colonoscopies. Large and proximal hyperplastic polyps, as well large and proximal SSA/Ps, were associated with advanced neoplasia. [ABSTRACT FROM AUTHOR]

Serrated polyposis syndrome is associated with an increased colorectal cancer risk. Although the underlying genetic cause of the condition is unknown, first-degree relatives of patients with serrated polyposis have an increased risk for colorectal cancer compared with the general population. This suggests an inheritable component. Since other hereditary polyposis syndromes are often associated with an expanded extracolonic tumour spectrum, our aim was to determine the extra colonic cancer risks for patients with serrated polyposis and their first-degree relatives and compare these risks with the general population. Serrated polyposis index patients from 5 medical centres were included. Demographic data concerning age, sex and reported malignancies were ascertained by reviewing medical charts and histopathology reports. Family history was obtained by examining pedigree records from the department of Clinical Genetics. Incidence rates of extracolonic malignancies were compared with the general population through a person-year analysis, adjusted for age and sex. Population-based incidence data were derived from the Eindhoven Cancer Registry. A total of 105 patients with serrated polyposis and 341 first-degree relatives were included. Among the patients with serrated polyposis, 9 extracolonic cancers were observed, compared to 13 expected malignancies in the general population (RR 0.69 95 % CI 0.36–1.33; p = 0.27). Among the first-degree relatives, 44 extracolonic malignancies were observed, compared to 48 expected malignancies (RR 0.92 95 % CI 0.69–1.24; p = 0.60). In this study, the overall incidence of extracolonic malignancies in patients with serrated polyposis and their first-degree relatives was not increased. Large international studies are required to confirm these results. [ABSTRACT FROM AUTHOR]

Main recommendations: The following recommendations for post-polypectomy endoscopic surveillance should be applied only after a high quality baseline colonoscopy with complete removal of all detected neoplastic lesions. 1 In the low risk group (patients with 1-2 tubular adenomas<10mm with low grade dysplasia), the ESGE recommends participation in existing national screening programmes 10 years after the index colonoscopy. If no screening programme is available, repetition of colonoscopy 10 years after the index colonoscopy is recommended (strong recommendation, moderate quality evidence). 2 In the high risk group (patients with adenomas with villous histology or high grade dysplasia or ⩾10mm in size, or ⩾3 adenomas), the ESGE recommends surveillance colonoscopy 3 years after the index colonoscopy (strong recommendation, moderate quality evidence). Patients with 10 or more adenomas should be referred for genetic counselling (strong recommendation, moderate quality evidence). 3 In the high risk group, if no high risk adenomas are detected at the first surveillance examination, the ESGE suggests a 5-year interval before a second surveillance colonoscopy (weak recommendation, low quality evidence). If high risk adenomas are detected at first or subsequent surveillance examinations, a 3-year repetition of surveillance colonoscopy is recommended (strong recommendation, low quality evidence). 4 The ESGE recommends that patients with serrated polyps <10mm in size with no dysplasia should be classified as low risk (weak recommendation, low quality evidence). The ESGE suggests that patients with large serrated polyps (⩾10mm) or those with dysplasia should be classified as high risk (weak recommendation, low quality evidence). 5 The ESGE recommends that the endoscopist is responsible for providing a written recommendation for the post-polypectomy surveillance schedule (strong recommendation, low quality evidence). [ABSTRACT FROM AUTHOR]