Exploring the interior of 3D endoluminal lesions in the air spaces by a novel electronic biopsy technique: A preliminary study of endoluminal colon lesions.

To explore the interior of a lesion in a 3D endoluminal view, this study investigates the application of an 'electronic biopsy' (EB) technique to computed tomographic colonography (CTC) for further differentiation and 2D image correlation of endoluminal lesions in the air spaces. A retrospective study of sixty-two various endoluminal lesions from thirty patients (13 males, 17 females; age range, 31 to 90 years) was approved by our institutional review board and evaluated. The endoluminal lesions were segmented using gray-level threshold and reconstructed into isosurfaces using a marching cube algorithm. EB allows users to interactively erode and apply grey-level mapping (GM) to the surface of the region of interest (ROI) in 3D CTC. Radiologists conducted the clinical evaluation, and the resulting data were analyzed. EB significantly improves 3D gray-level presentation for evaluating the surface and inside of endoluminal lesions over that of SR, GM or target GM (TGM) (P < 0.01) with preservation of the 3D spatial effect. Moreover, 3D to 2D image correlation were achieved in any layer of the lesion using EB as did GM/TGM on the surface. The specificity and diagnostic accuracy of EB are significantly greater than those of SR (P < 0.01). These performance can be better further with GM/TGM and reach the best with EB (specificity, 89.3-92.9%; accuracy, 95.2-96.8%). EB can be used in CTC to improve the differentiation of endoluminal lesions. EB increases 3D to 2D image correlations of the lesions on or beneath the lesion surface.

Polyps and Polyposis Syndromes in Children: Novel Endoscopic Considerations.

Polypectomy is the most common therapeutic endoscopic intervention in children. Management of sporadic juvenile polyps is limited to polypectomy to resolve symptoms, whereas polyposis syndromes pose a multidisciplinary challenge with broader ramifications. In preparation for polypectomy, there are key patient, polyp, endoscopy unit, and provider characteristics that factor into the likelihood of success. Younger age and multiple medical comorbidities increase the risk of adverse outcomes, classified as intraoperative, immediate postoperative, and delayed postoperative complications. Novel techniques, including cold snare polypectomy, can significantly decrease adverse events but a more structured training process for polypectomy in pediatric gastroenterology is needed.

Interactive training versus self-driven training in the prediction of colorectal polyp histology by trainees using the NICE classification.

BACKGROUND: The COVID-19 pandemic has impacted endoscopic training of the Narrow Band Imaging International Colorectal Endoscopic (NICE) classification, which could accurately predict pathology of colorectal polyps. This study aimed to evaluate the diagnostic performance by trainees of self-driven training vs. interactive training in the prediction of colorectal polyp histology. METHODS: This was a prospective randomized controlled study at five academic centers from January 1, 2021 to May 31, 2021. Trainees with no previous formal training of narrow band imaging or blue light imaging for prediction of colorectal polyp histology were randomly allocated to the self-driven training group or interactive training group. Before and after the training, all trainees were given 20 selected cases of colorectal polyp for testing. Their diagnostic performance was analyzed. RESULTS: Overall, the two training groups showed similar accuracy of NICE classification (79.3% vs. 78.1%; P = 0.637), vessel analysis (77.8% vs. 77.6%, P = 0.939), and surface pattern analysis (78.1% vs. 76.9%, P = 0.616). The accuracy of color analysis in the interactive training group was better (74.4% vs. 80.0%, P = 0.027). For high-confidence predictions, the self-driven training group showed higher accuracy of NICE classification (84.8% vs. 78.7%, P < 0.001) but no difference for analysis of color (79.6% vs. 81.0%), vessel pattern (83.0% vs. 78.5%), and surface pattern (81.8% vs. 78.5%). CONCLUSIONS: Overall, self-driven training showed comparable accuracy of NICE classification, vessel pattern, and surface pattern to interactive training, but lower accuracy of color analysis. This method showed comparable effectiveness and is more applicable than interactive training. It is worth spreading during the COVID-19 pandemic. Trial registration Name of the registry: Chinese Clinical Trial Registry, Trial registration number: ChiCTR2000031659, Date of registration: 06/04/2020, URL of trial registry record: http://www.chictr.org.cn/showproj.aspx?proj=51994.

Malignant polyps in the COVID-19 era: a population-based analysis.

BACKGROUND: Malignant polyps represent the early development of colorectal adenocarcinoma. During 2020, there was widescale rationing of health-care resources in response to the COVID-19 pandemic. In particular there was deferral of some colonoscopy procedures required for timely malignant polyp detection. This study sought to assess how these deferrals affected the diagnosis of malignant polyps. METHODS: A population wide analysis was performed of 2079 malignant polyps, diagnosed in Queensland, Australia from 2011 to 2020. A regression analysis, with 95% prediction intervals, was produced to determine whether there was a significant impact on the number of malignant polyps diagnosed in 2020 compared to previous years. Univariate statistical analysis of patient, procedural, and pathological variables was also performed. RESULTS: In 2020 there were 211 malignant polyps diagnosed, which was significantly lower than was predicted by the univariate regression analysis (r2  = 0.85, 95% prediction interval: 255.07-323.91, P < 0.001). These malignant polyps were less likely to be diagnosed in a private setting (P < 0.001), and exhibited significantly less depth of submucosal invasion (P = 0.017). There was no significant difference in the management strategy (polypectomy, resection or trans-anal resection) between 2011 and 2019 and 2020. CONCLUSION: Because of the significant decrease in the number of malignant polyps, and the natural history of the disease, it is expected that there will be an increase in more advanced colorectal adenocarcinomas presenting in 2021 and beyond. This has implications for healthcare resources, particularly in light of the ongoing strain on health departments as a result of the COVID-19 pandemic.

Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice.

The performance of artificial intelligence-aided colonoscopy (AIAC) in a real-world setting has not been described. We compared adenoma and polyp detection rates (ADR/PDR) in a 6-month period before (pre-AIAC) and after introduction of AIAC (GI Genius, Medtronic) in all endoscopy suites in our large-volume center. The ADR and PDR in the AIAC group was lower compared with those in the pre-AIAC group (30.3% vs 35.2%, P < 0.001; 36.5% vs 40.9%, P = 0.004, respectively); procedure time was significantly shorter in the AIAC group. In summary, introduction of AIAC did not result in performance improvement in our large-center cohort, raising important questions on AI-human interactions in medicine.

Third Asia-Pacific consensus recommendations on colorectal cancer screening and postpolypectomy surveillance.

The Asia-Pacific region has the largest number of cases of colorectal cancer (CRC) and one of the highest levels of mortality due to this condition in the world. Since the publishing of two consensus recommendations in 2008 and 2015, significant advancements have been made in our knowledge of epidemiology, pathology and the natural history of the adenoma-carcinoma progression. Based on the most updated epidemiological and clinical studies in this region, considering literature from international studies, and adopting the modified Delphi process, the Asia-Pacific Working Group on Colorectal Cancer Screening has updated and revised their recommendations on (1) screening methods and preferred strategies; (2) age for starting and terminating screening for CRC; (3) screening for individuals with a family history of CRC or advanced adenoma; (4) surveillance for those with adenomas; (5) screening and surveillance for sessile serrated lesions and (6) quality assurance of screening programmes. Thirteen countries/regions in the Asia-Pacific region were represented in this exercise. International advisors from North America and Europe were invited to participate.

A Novel Convolutional Neural Network Model as an Alternative Approach to Bowel Preparation Evaluation Before Colonoscopy in the COVID-19 Era: A Multicenter, Single-Blinded, Randomized Study.

INTRODUCTION: Adequate bowel preparation is key to a successful colonoscopy, which is necessary for detecting adenomas and preventing colorectal cancer. We developed an artificial intelligence (AI) platform using a convolutional neural network (CNN) model (AI-CNN model) to evaluate the quality of bowel preparation before colonoscopy. METHODS: This was a colonoscopist-blinded, randomized study. Enrolled patients were randomized into an experimental group, in which our AI-CNN model was used to evaluate the quality of bowel preparation (AI-CNN group), or a control group, which performed self-evaluation per routine practice (control group). The primary outcome was the consistency (homogeneity) between the results of the 2 methods. The secondary outcomes included the quality of bowel preparation according to the Boston Bowel Preparation Scale (BBPS), polyp detection rate, and adenoma detection rate. RESULTS: A total of 1,434 patients were enrolled (AI-CNN, n = 730; control, n = 704). No significant difference was observed between the evaluation results ("pass" or "not pass") of the groups in the adequacy of bowel preparation as represented by BBPS scores. The mean BBPS scores, polyp detection rate, and adenoma detection rate were similar between the groups. These results indicated that the AI-CNN model and routine practice were generally consistent in the evaluation of bowel preparation quality. However, the mean BBPS score of patients with "pass" results were significantly higher in the AI-CNN group than in the control group, indicating that the AI-CNN model may further improve the quality of bowel preparation in patients exhibiting adequate bowel preparation. DISCUSSION: The novel AI-CNN model, which demonstrated comparable outcomes to the routine practice, may serve as an alternative approach for evaluating bowel preparation quality before colonoscopy.

Effect of enhanced personal protective equipment on colonoscopy performance and pain linked to procedure during the COVID-19 pandemic.

Background and study aim: During the COVID-19 pandemic, the use of standard personal protective equipment (SPPE) reduces transmission risks during endoscopic procedures. Our aim was to assess the effect of enhanced personal protective equipment (EPPE) on colonoscopy performance and pain linked to the procedure compared with SPPE. Patients and methods: During two similar periods with three-month duration (in 2019 and in 2020 during the COVID-19 pandemic), electronic medical records and colonoscopy reports were investigated for sequential patients undergoing colonoscopy. SPPE was used in 2019 and EPPE in 2020. The patients' clinical data and information related to the procedure were collected and analyzed. Primary outcomes were the duration to intubate the cecum, total procedure duration and patient pain score at the end of the procedure. Secondary outcomes were adenoma detection rate (ADR), polyp detection rate (PDR) and cecal intubation rate (CIR). Results: A total of 426 patients with colonoscopy performed were analyzed. The demographic features and indications for colonoscopy were similar for patients in both groups. The EPPE group had higher values for the parameters assessed as primary endpoints of cecal intubation time, withdrawal time, total procedure time and pain at the end of the procedure compared to the SPPE group and the differences were statistically significant. Conclusion: Our findings show that though the use of EPPE negatively affected colonoscopy performance and patient pain at the end of the procedure, it had no effect on the colonoscopy quality indices such as ADR, PDR and CIR.

Colonoscopic-Assisted Laparoscopic Wedge Resection for Colonic Lesions: A Prospective Multicenter Cohort Study (LIMERIC-Study).

OBJECTIVE: The aim of this study was to evaluate the safety and efficacy of a modified CAL-WR. SUMMARY BACKGROUND DATA: The use of segmental colectomy in patients with endoscopically unresectable colonic lesions results in significant morbidity and mortality. CAL-WR is an alternative procedure that may reduce morbidity. METHODS: This prospective multicenter study was performed in 13 Dutch hospitals between January 2017 and December 2019. Inclusion criteria were (1) colonic lesions inaccessible using current endoscopic resection techniques (judged by an expert panel), (2) non-lifting residual/recurrent adenomatous tissue after previous polypectomy or (3) an undetermined resection margin after endoscopic removal of a low-risk pathological T1 (pT1) colon carcinoma. Thirty-day morbidity, technical success rate and radicality were evaluated. RESULTS: Of the 118 patients included (56% male, mean age 66 years, standard deviation ± 8 years), 66 (56%) had complex lesions unsuitable for endoscopic removal, 34 (29%) had non-lifting residual/recurrent adenoma after previous polypectomy and 18 (15%) had uncertain resection margins after polypectomy of a pT1 colon carcinoma. CAL-WR was technically successful in 93% and R0 resection was achieved in 91% of patients. Minor complications (Clavien-Dindo i-ii) were noted in 7 patients (6%) and an additional oncologic segmental resection was performed in 12 cases (11%). Residual tissue at the scar was observed in 5% of patients during endoscopic follow-up. CONCLUSIONS: CAL-WR is an effective, organ-preserving approach that results in minor complications and circumvents the need for major surgery. CAL-WR, therefore, deserves consideration when endoscopic excision of circumscribed lesions is impossible or incomplete.

Post-polypectomy colonoscopy surveillance: Can we improve the diagnostic yield?

Although adenomas and serrated polyps are the preneoplastic lesions of colorectal cancer, only few of them will eventually progress to cancer. This review provides a comprehensive overview of the present and future of post-polypectomy colonoscopy surveillance. Post-polypectomy surveillance guidelines have recently been updated and all share the aim towards more selective and less frequent surveillance. We have examined these current guidelines and compared the recommendations of each of them. To improve the diagnostic yield of post-polypectomy surveillance it is important to find predictors of metachronous polyps that better identify high-risk individuals of developing advanced neoplasia. For this reason, we have also conducted a literature review of the molecular biomarkers of metachronous advanced colorectal polyps. Finally, we have discussed future directions of post-polypectomy surveillance and identified possible strategies to improve the use of endoscopic resources with the COVID-19 pandemic.

Multiclassification of Endoscopic Colonoscopy Images Based on Deep Transfer Learning.

With the continuous improvement of human living standards, dietary habits are constantly changing, which brings various bowel problems. Among them, the morbidity and mortality rates of colorectal cancer have maintained a significant upward trend. In recent years, the application of deep learning in the medical field has become increasingly spread aboard and deep. In a colonoscopy, Artificial Intelligence based on deep learning is mainly used to assist in the detection of colorectal polyps and the classification of colorectal lesions. But when it comes to classification, it can lead to confusion between polyps and other diseases. In order to accurately diagnose various diseases in the intestines and improve the classification accuracy of polyps, this work proposes a multiclassification method for medical colonoscopy images based on deep learning, which mainly classifies the four conditions of polyps, inflammation, tumor, and normal. In view of the relatively small number of data sets, the network firstly trained by transfer learning on ImageNet was used as the pretraining model, and the prior knowledge learned from the source domain learning task was applied to the classification task about intestinal illnesses. Then, we fine-tune the model to make it more suitable for the task of intestinal classification by our data sets. Finally, the model is applied to the multiclassification of medical colonoscopy images. Experimental results show that the method in this work can significantly improve the recognition rate of polyps while ensuring the classification accuracy of other categories, so as to assist the doctor in the diagnosis of surgical resection.

Re-initiation of CT colonography services during the COVID-19 pandemic: Preliminary evaluation of safety.

OBJECTIVE: The COVID-19 pandemic has led to cancellation and deferral of many cancer investigations, including CT colonography (CTC). In May 2020, BSGAR and SCoR issued guidelines outlining steps for conduct of CTC in the early recovery phase. We evaluated the implementation of these in four English hospital trusts. METHODS: Ethical permission was not required for this multicentre service evaluation. We identified patients undergoing CTC over a 2-month period from May to July 2020 at four Trusts. We recorded demographics, scan indications, colonic findings, and incidental lung base changes compatible with COVID-19. A subset of patients were contacted via telephone to document new symptoms 2 weeks following their scan. Staff were contacted to determine if any acquired COVID-19 during the period. RESULTS: 224 patients (118 male, 52.7%) were scanned during the period. In 55 patients (24.6%), CTC showed a ≥6 mm polyp. 33 of 224 (14.7%) scans showed incidental lung base changes felt unrelated to COVID-19, and only one patient had changes indeterminate for COVID-19; no classic COVID-19 pulmonary changes were found. Of 169 patients with telephone follow-up, none reported any new symptoms of COVID-19 (cough, fever, anosmia, ageusia) within 14 days of CTC. None of the 86 staff contacted developed COVID-19. CONCLUSION: We found no cases of patients or staff acquiring COVID-19 infection following CTC; and no evidence of significant asymptomatic COVID-19 patients attending for CTC appointments based on lung base changes. ADVANCES IN KNOWLEDGE: Our findings suggest that current practice is unlikely to contribute significantly to spread of SARS-nCOV2. Cancer and significant polyp detection rates were high, underlining the importance of maintaining service provision.

Adoption of Multi-society Guidelines Facilitates Value-Based Reduction in Screening and Surveillance Colonoscopy Volume During COVID-19 Pandemic.

BACKGROUND: COVID-19 has caused a backlog of endoscopic procedures; colonoscopy must now be prioritized to those who would benefit most. We determined the proportion of screening and surveillance colonoscopies appropriate for rescheduling to a future year through strict adoption of US Multi-Society Task Force (USMSTF) guidelines. METHODS: We conducted a single-center observational study of patients scheduled for "open-access colonoscopy"-ordered by a primary care provider without being seen in gastroenterology clinic-over a 6-week period during the COVID-19 pandemic. Each chart was reviewed to appropriately assign a surveillance year per USMSTF guidelines including demographics, colonoscopy history and family history. When guidelines recommended a range of colonoscopy intervals, both a "conservative" and "liberal" guideline adherence were assessed. RESULTS: We delayed 769 "open-access" screening or surveillance colonoscopies due to COVID-19. Between 14.8% (conservative) and 20.7% (liberal), colonoscopies were appropriate for rescheduling to a future year. Conversely, 415 (54.0%) patients were overdue for colonoscopy. Family history of CRC was associated with being scheduled too early for both screening (OR 3.9; CI 1.9-8.2) and surveillance colonoscopy (OR 2.6, CI 1.0-6.5). The most common reasons a colonoscopy was inappropriately scheduled this year were failure to use new surveillance colonoscopy intervals (28.9%), incorrectly applied family history guidelines (27.2%) and recommending early surveillance colonoscopy after recent normal colonoscopy (19.3%). CONCLUSION: Up to one-fifth of patients scheduled for "open-access" colonoscopy can be rescheduled into a future year based on USMSTF guidelines. Rigorously applying guidelines could judiciously allocate colonoscopy resources as we recover from the COVID-19 pandemic.