Colonoscopy Data Research Articles

Risk of colorectal cancer among fecal immunochemical test-positive individuals by timing of previous colonoscopy: A multicenter analysis.

The risk of colorectal cancer among fecal immunochemistry test-positive individuals who had undergone previous colonoscopies remains unclear. Therefore, this study aimed to determine the differences in the risk of colorectal cancer among fecal immunochemistry test-positive individuals according to the timing of their previous colonoscopies. This multicenter, retrospective, observational study was conducted in Japan as a subgroup analysis of the J-SCOUT study (UMIN000040690), which integrated and analyzed a database comprising all colonoscopies performed at participating Japanese institutions between 2010 and 2020. This study used colonoscopy data of fecal immunochemistry test-positive individuals aged ≥20years from three facilities that entered the timing of previous colonoscopies into the endoscopy database. Histologically confirmed advanced neoplasia was the study's primary outcome. Multivariate logistic regression analysis was used to calculate the odds ratios for each variable. In total, 11,143 fecal immunochemistry test-positive patients underwent colonoscopy during the study period. Of these, 10,160 patients were included in the analysis after excluding those who met the exclusion criteria. The overall advanced neoplasia detection rate was 9.38% (953/10,160; 95% confidence interval: 8.82-9.96%). Compared with the first colonoscopy, the odds ratios for advanced neoplasia in individuals who underwent colonoscopies 1, 2, 3, 4, 5, >5, and ≥10years previously were 0.27, 0.15, 0.06, 0.10, 0.29, 0.31, and 0.31, respectively. The detection rates of advanced neoplasia were low among the fecal immunochemistry test-positive individuals who had undergone colonoscopy, particularly in the past 5years.

The Utility of Multitarget Stool DNA Testing for Colorectal Cancer Screening After a Normal Colonoscopy.

Multitarget stool DNA (MT-sDNA) tests (here, Cologuard®) are currently used in average-risk patients as a primary method of screening for colorectal cancer. However, MT-sDNA testing has also been used in patients who previously underwent colonoscopy who wish to avoid repeat colonoscopy. Here, in a large primary care practice setting, our aim was to evaluate the diagnostic performance of MT-sDNA testing in patients with a previously normal colonoscopy. This retrospective cohort study included 5827 patients from 35 different primary locations in South Carolina. Patients aged 45 and above with a previously documented normal, high-quality colonoscopy prior to the MT-sDNA test date were included. High-risk patients and those with a previous negative MT-sDNA result were excluded. Of 5827 ordered MT-sDNA tests, 248 patients had a prior normal colonoscopy. The average time from initial colonoscopy to MT-sDNA testing was 7.3years. Of the 63 patients who had a positive MT-sDNA test, 41 patients (65%) completed follow-up colonoscopy and 40 patients had complete colonoscopy data. Of these 40 patients, 12 patients (30%) had advanced adenomas and none had colorectal cancer. Compared to patients without a previous colonoscopy, patients with prior colonoscopies had fewer adenomas of all types (1.6 vs 2.4) and fewer advanced adenomas (1.4 vs 2.0). Patients with a previously negative colonoscopy and subsequent positive MT-sDNA test were found to have a high rate of advanced adenomas on follow-up colonoscopy (30%). Thus, in patients with a previously negative colonoscopy, MT-sDNA testing may be a reasonable alternative screening option.

Colorectal Neuroendocrine Neoplasm Detection Rate During Colonoscopy: Results From Large-Scale Data of Colonoscopies in Japan.

This study investigated the detection rate of colorectal neuroendocrine neoplasms (NENs) using large-scale colonoscopy data. This cross-sectional analysis used large-scale data from a Japanese multicenter observational study of colonoscopies performed from 2010 to 2020. Among 82,005 colonoscopy cases, colorectal NENs were identified in 71 (67 of which were neuroendocrine tumors), with a detection rate of 0.087% (95% confidence interval: 0.069-0.109). Most were small rectal lesions, with only 4 >10 mm in size and 3 located in the colon. The detection rate of colorectal NENs during colonoscopy is substantially higher than expected.

Fatty acid desaturase insertion-deletion polymorphism rs66698963 predicts colorectal polyp prevention by the n–3 fatty acid eicosapentaenoic acid: a secondary analysis of the seAFOod polyp prevention trial

BackgroundA fatty acid desaturase (FADS) insertion-deletion (Indel) polymorphism (rs66698963) influences the expression of FADS1, which controls the synthesis of n–6 highly unsaturated fatty acid (HUFA) arachidonic acid (AA). The anti-inflammatory activity of the n–3 HUFA eicosapentaenoic acid (EPA) may be explained by competition with AA for proinflammatory lipid mediator synthesis. A precision medicine approach based on stratification by FADS Indel genotype could identify individuals, who benefit from greatest disease risk reduction by n–3 HUFAs. ObjectivesWe tested the hypothesis that the FADS insertion (I) allele predicts colorectal polyp risk reduction in a secondary analysis of the randomized, placebo-controlled, 2×2 factorial seAFOod polyp prevention trial of EPA 2000 mg daily and aspirin 300 mg daily for 12 mo (ISRCTN05926847). MethodsParticipant Indel genotype was determined by polymerase chain reaction (PCR) blind to trial outcomes. Colorectal polyp outcomes were included in negative binomial (polyp number) and logistic (polyp detection rate [PDR; percentage with one or more polyps]) regression models comparing each active intervention with its placebo. Presence of ≥1 Indel I allele and an interaction term (I allele × active intervention) were covariates. ResultsIn 528 participants with colonoscopy and FADS Indel data, EPA use irrespective of Indel genotype, was not associated with reduced colorectal polyp number (incidence rate ratio [IRR]: 0.92; 95% confidence interval: 0.74, 1.16), mirroring original seAFOod trial analysis. However, the presence of ≥1 I allele identified EPA users with a significant reduction in colorectal polyp number (IRR: 0.50 [0.28, 0.90]), unlike aspirin, for which there was no interaction. Similar findings were obtained for the PDR. ConclusionsThe FADS Indel I allele identified individuals, who displayed colorectal polyp prevention by EPA with a similar effect size to aspirin. Assessment of rs66698963 as a biomarker of therapeutic response to n–3 HUFAs in other populations and healthcare settings is warranted.The seAFOod polyp prevention trial and STOP-ADENOMA study were registered at International Standard Randomised Controlled Trial Number registry as ISRCTN05926847.

WSPolyp-SAM: Weakly Supervised and Self-Guided Fine-Tuning of SAM for Colonoscopy Polyp Segmentation

Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully supervised, requiring extensive, precise, manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains challenging to train large-scale segmentation models when confronted with limited colonoscopy data. To address these issues, we introduce the general segmentation foundation model—the Segment Anything Model (SAM)—into the field of medical image segmentation. Fine-tuning the foundation model is an effective approach to tackle sample scarcity. However, current SAM fine-tuning techniques still rely on precise annotations. To overcome this limitation, we propose WSPolyp-SAM, a novel weakly supervised approach for colonoscopy polyp segmentation. WSPolyp-SAM utilizes weak annotations to guide SAM in generating segmentation masks, which are then treated as pseudo-labels to guide the fine-tuning of SAM, thereby reducing the dependence on precise annotation data. To improve the reliability and accuracy of pseudo-labels, we have designed a series of enhancement strategies to improve the quality of pseudo-labels and mitigate the negative impact of low-quality pseudo-labels. Experimental results on five medical image datasets demonstrate that WSPolyp-SAM outperforms current fully supervised mainstream polyp segmentation networks on the Kvasir-SEG, ColonDB, CVC-300, and ETIS datasets. Furthermore, by using different amounts of training data in weakly supervised and fully supervised experiments, it is found that weakly supervised fine-tuning can save 70% to 73% of annotation time costs compared to fully supervised fine-tuning. This study provides a new perspective on the combination of weakly supervised learning and SAM models, significantly reducing annotation time and offering insights for further development in the field of colonoscopy polyp segmentation.

Colorectal polyps in young adults: a retrospective review of colonoscopy data from Toowoomba and the Darling Downs.

Polyps are the predominant precursors of colorectal cancer. In the past three decades, the incidence and mortality rates of colorectal cancer have been increasing in adults younger than 50 years. The aim of this clinical audit was to evaluate the prevalence, characteristics and clinical associations of polyps in adults aged 18-49 years presenting to an established private gastroenterology clinic in the Toowoomba Darling Downs region. The audit included data from 353 patient records held by the Toowoomba Gastroenterology Clinic. Data extracted from patient medical records through the Medical Director program software contained structured endoscopy/colonoscopy and histology reports of excised lesions of patients presenting to the clinic. The extract involved identifying all patients aged 18-49 years in the database from January 2019 to March 2022. Patients were screened based on audit inclusion and exclusion criteria. Patients were risk stratified for recommended surveillance intervals as per Australian Clinical Guidelines. Of the sample population, 33.4% were identified with polyps and 22.4% were identified with neoplastic polyps (NPs). A total of 6.7% of 18- to 29-year-old patients were identified with intermediate risk for colorectal cancer (CRC) screening, and 19.8% and 19.3% of 30- to 39-year-old and 40- to 49-year-old patients identified with intermediate or high risk for CRC screening respectively. Increased age, greater size of polyps and surveillance of previous polyps were associated with increased NP prevalence. Data from this audit supported the temporal trend of increasing prevalence of polyps in adults younger than 50 years. Patient cohorts aged 30-39 and 40-49 years may benefit from earlier first colonoscopies. Findings could be the impetus for future research in young adults presenting for colonoscopy.

ChatGPT4 Outperforms Endoscopists for Determination of Postcolonoscopy Rescreening and Surveillance Recommendations

Large language models including Chat Generative Pretrained Transformers version 4 (ChatGPT4) improve access to artificial intelligence, but their impact on the clinical practice of gastroenterology is undefined. This study compared the accuracy, concordance, and reliability of ChatGPT4 colonoscopy recommendations for colorectal cancer rescreening and surveillance with contemporary guidelines and real-world gastroenterology practice. History of present illness, colonoscopy data, and pathology reports from patients undergoing procedures at 2 large academic centers were entered into ChatGPT4 and it was queried for the next recommended colonoscopy follow-up interval. Using the McNemar test and inter-rater reliability, we compared the recommendations made by ChatGPT4 with the actual surveillance interval provided in the endoscopist's procedure report (gastroenterology practice) and the appropriate US Multisociety Task Force (USMSTF) guidance. The latter was generated for each case by an expert panel using the clinical information and guideline documents as reference. Text input of de-identified data into ChatGPT4 from 505 consecutive patients undergoing colonoscopy between January 1 and April 30, 2023, elicited a successful follow-up recommendation in 99.2% of the queries. ChatGPT4 recommendations were in closer agreement with the USMSTF Panel (85.7%) than gastroenterology practice recommendations with the USMSTF Panel (75.4%) (P < .001). Of the 14.3% discordant recommendations between ChatGPT4 and the USMSTF Panel, recommendations were for later screening in 26 (5.1%) and for earlier screening in 44 (8.7%) cases. The inter-rater reliability was good for ChatGPT4 vs USMSTF Panel (Fleiss κ, 0.786; 95% CI, 0.734-0.838; P < .001). Initial real-world results suggest that ChatGPT4 can define routine colonoscopy screening intervals accurately based on verbatim input of clinical data. Large language models have potential for clinical applications, but further training is needed for broad use.

Periprosthetic Joint Infection in Patients With Arthroplasty Undergoing Perioperative Colonoscopy

Periprosthetic joint infection (PJI) is a rare but devastating complication. Most patients undergoing total joint arthroplasty (TJA) also need routine screening colonoscopy, in which transient bacteremia may be a potential source for hematogenous PJI. Patients and surgeons must decide on an optimal time span or sequence for these 2 generally elective procedures, but no such guidelines currently exist. To evaluate associations of colonoscopy with the risk of post-TJA PJI for the development of clinical practice recommendations for colonoscopy screening in patients undergoing TJA. This retrospective cohort study of Military Health System (MHS) beneficiaries older than 45 years who underwent TJA from January 1, 2010, to December 31, 2016, used propensity score matching and logistic regression to evaluate associations of colonoscopy with PJI risk. Statistical analyses were conducted between January and October 2023. Colonoscopy status was defined by Current Procedural Terminology code for diagnostic colonoscopy within 6 months before or 6 months after TJA. Periprosthetic joint infection status was defined by a PJI International Classification of Diseases code within 1 year after TJA and within 1 year from the post-TJA index colonoscopy date. Analyses included 243 671 patients (mean [SD] age, 70.4 [10.0] years; 144 083 [59.1%] female) who underwent TJA in the MHS from 2010 to 2016. In the preoperative colonoscopy cohort, 325 patients (2.8%) had PJI within 1 year postoperatively. In the postoperative colonoscopy cohort, 138 patients (1.8%) had PJI within 1 year from the index colonoscopy date. In separate analyses of colonoscopy status within 6 months before and 6 months after TJA, younger age, male sex, and several chronic health conditions (diabetes, kidney disease, and pulmonary disease) were each associated with higher PJI risk. However, no association was found with PJI risk for perioperative colonoscopy preoperatively (adjusted odds ratio, 1.10; 95% CI, 0.98-1.23) or postoperatively (adjusted odds ratio, 0.90; 95% CI, 0.74-1.08). In this large retrospective cohort of patients undergoing TJA, perioperative screening colonoscopy was not associated with PJI and should not be delayed for periprocedural risk. However, health conditions were independently associated with PJI and should be medically optimized.

Efficacy and safety of biological treatment for inflammatory bowel disease in elderly patients: Results from a GETECCU cohort

IntroductionBiological therapies used for the treatment of inflammatory bowel disease (IBD) have shown to be effective and safe, although these results were obtained from studies involving mostly a young population, who are generally included in clinical trials. The aim of our study was to determine the efficacy and safety of the different biological treatments in the elderly population. MethodsMulticenter study was carried out in the GETECCU group. Patients diagnosed with IBD and aged over 65 years at the time of initiating biological therapy (infliximab, adalimumab, golimumab, ustekinumab or vedolizumab) were retrospectively included.Among the patients included, clinical response was assessed after drug induction (12 weeks of treatment) and at 52 weeks. Patients’ colonoscopy data in week 52 were assessment, where available. Regarding complications, development of oncological events during follow-up and infectious processes occurring during biological treatment were collected (excluding bowel infection by cytomegalovirus). ResultsA total of 1090 patients were included. After induction, at approximately 12–14 weeks of treatment, 419 patients (39.6%) were in clinical remission, 502 patients (47.4%) had responded without remission and 137 patients (12.9%) had no response.At 52 weeks of treatment 442 patients (57.1%) had achieved clinical remission, 249 patients had responded without remission (32.2%) and 53 patients had no response to the treatment (6.8%). Before 52 weeks, 129 patients (14.8%) had discontinued treatment due to inefficacy, this being significantly higher (p<0.0001) for Golimumab – 9 patients (37.5%) – compared to the other biological treatments analyzed.With respect to tumor development, an oncological event was observed in 74 patients (6.9%): 30 patients (8%) on infliximab, 23 (7.14%) on adalimumab, 3 (11.1%) on golimumab, 10 (6.4%) on ustekinumab, and 8 (3.8%) on vedolizumab. The incidence was significantly lower (p=0.04) for the vedolizumab group compared to other treatments.As regards infections, these occurred in 160 patients during treatment (14.9%), with no differences between the different biologicals used (p=0.61): 61 patients (19.4%) on infliximab, 39 (12.5%) on adalimumab, 5 (17.8%) on golimumab, 22 (14.1%) on ustekinumab, and 34 (16.5%) on vedolizumab. ConclusionsBiological drug therapies have response rates in elderly patients similar to those described in the general population, Golimumab was the drug that was discontinued most frequently due to inefficacy.In our experience, tumor development was more frequent in patients who used anti-TNF therapies compared to other targets, although its incidence was generally low and that this is in line with younger patients based on previous literature.

Examining the Association Between the COVID-19 Pandemic and the Rate of Diagnostic Tests for Breast, Cervical, and Colorectal Cancer in Manitoba, Canada.

Background: Strategies to minimize the impact of the COVID-19 pandemic led to a reduction in diagnostic testing. It is important to assess the magnitude and duration of this impact to plan ongoing care and avoid long-lasting impacts of the pandemic. Objective: We examined the association between the COVID-19 pandemic and the rate of diagnostic tests for breast, cervical, and colorectal cancer in Manitoba, Canada. Design and Participants: A population-based, cross-sectional study design with an interrupted time series analysis was used that included diagnostic tests from January 1, 2015 until August 31, 2022. Setting: Manitoba, Canada. Main Outcomes: Outcomes included mammogram, breast ultrasound, colposcopy, and colonoscopy rates per 100,000. Cumulative and percent cumulative differences between the fitted and counterfactual number of tests were estimated. Mean, median, and 90th percentile number of days from referral to colonoscopy date by referral type (elective, semiurgent, urgent) were determined. Results: In April 2020, following the declaration of the COVID-19 public health emergency, bilateral mammograms decreased by 77%, unilateral mammograms by 70%, breast ultrasounds by 53%, colposcopies by 63%, and colonoscopies by 75%. In Winnipeg (the largest urban center in the province), elective and semiurgent colonoscopies decreased by 76% and 39%, respectively. There was no decrease in urgent colonoscopies. As of August 2022, there were an estimated 7270 (10.7%) fewer bilateral mammograms, 2722 (14.8%) fewer breast ultrasounds, 836 (3.3%) fewer colposcopies, and 11 600 (13.8%) fewer colonoscopies than expected in the absence of COVID-19. As of December 2022, in Winnipeg, there were an estimated 6030 (23.9%) fewer elective colonoscopies, 313 (2.6%) fewer semiurgent colonoscopies, and 438 (27.3%) more urgent colonoscopies. Conclusions: In Manitoba, the COVID-19 pandemic was associated with sizable decreases in diagnostic tests for breast, colorectal, and cervical cancer. Two and a half years later, there remained large cumulative deficits in bilateral mammograms, breast ultrasounds, and colonoscopies.

P944 Ustekinumab in refractory Ulcerative Colitis: single-center, real-world experience

Abstract Background Ustekinumab, an anti-interleukin 12/23 agent, was approved by the European Medicines Agency in 2019 as a treatment for moderate-to-severe ulcerative colitis (UC). Limited real-world data is available regarding the utilization of ustekinumab in UC, particularly medication persistence and escalation, which are indicators of medication performance in real-world settings. Our aim was to describe our experience with ustekinumab in refractory UC patients. Methods This was an observational single-center study on UC patients who received at least one intravenous dose of ustekinumab 16 weeks before data analysis due to active UC (Simple clinical colitis activity index (SCCAI)&amp;gt;5). Data regarding disease activity prior to and post-induction were analyzed. Patients were followed up until the last ustekinumab administration. Clinical response to therapy was assessed at 16, 24,52 weeks, and the end of follow-up. Response was defined as SCCAI&amp;lt;4, and remission as SCCAI≤2. Dose adjustment or IV maintenance was considered part of the treatment regimen. Patients who discontinued ustekinumab due to lack of therapeutic effect or worsening of UC were considered failures. When available, colonoscopy data was analyzed. Results Forty-seven patients who received ustekinumab for refractory UC were included. Thirty-eight percent were female, and 34% were former smokers. Median age was 46 [37.5-61.5]; 62% had extensive disease, and 15% had perianal disease. Ninety-three percent received at least one biologic before ustekinumab, and 24% had received a JAK inhibitor. Thirty-eight patients required dose escalation, and 11 were on maintenance IV. Clinical response at week 16 was achieved in 74% and remission in 46%. At 24 and 52 weeks, 65% and 61% were in remission, respectively. At the end of follow-up, 59% of patients had endoscopic remission (Endoscopic Mayo score ≤ 1). Sixty percent continued treatment during a mean follow-up of 12 months [6-21]. No variable was associated with risk of discontinuation. No serious adverse events were reported. Discontinuation of treatment was due to treatment failure in all cases. Conclusion Ustekinumab was effective for induction and maintenance in our cohort of UC patients, although a significant proportion required dose escalation. Drug persistence was higher than 50% during the follow-up. The safety profile of ustekinumab was similar to that in controlled studies and other real-world studies.

Clinical and epidemiological features of ulcerative colitis in children of the Rostov region

Russian data on the prevalence of inflammatory bowel diseases (IBD), including ulcerative colitis (UC), confirm the general global trend towards an increase in IBD, taking into account age-related as well as regional characteristics, which determined the purpose of this study. The purpose of the study. To evaluate the clinical and epidemiological features of the course of ulcerative colitis in children of Rostov-on-Don. Materials and methods. We observed 42 children aged from 1 to 14 years with a diagnosis of UC, which was made on the basis of anamnesis, clinical picture, laboratory test results, colonoscopy data, and morphological examination of the colon mucosa. UC activity was assessed taking into account the PUCAI index. Results. For the period from 2014 to 2023 On the basis of the pediatric somatic department of city hospital No. 20 in Rostov-on-Don, UC was diagnosed in 42 children aged 1 to 14 years, which amounted to 1.48% of the total number of patients with chronic intestinal diseases (2822 people). There was an increase in the incidence of ulcerative colitis from 2014 to 2023 (from 0.32% to 2.52%) with maximum values in 2021-2023. Conclusion. Clinical and epidemiological studies have shown an increase in the incidence of UC in children of Rostov-on-Don over the past 10 years. It has been established that ulcerative colitis is more often detected in the preschool group of children. The incidence of ulcerative colitis was higher in boys than in girls. A high degree of family history of children with UC was revealed for diseases of the digestive system, delivery by Caesarean section, artificial feeding in the first year of life, and acute intestinal infections. In the UC clinic, milder, erased forms of the disease dominated, which determined the later diagnosis of the disease at the prehospital stage.

A digital intake tool to avert outpatient visits in a FIT-based colorectal cancer screening population: study protocol of a multicentre, prospective non-randomized trial - the DIT-trial

BackgroundCurrently all participants of the Dutch colorectal cancer (CRC) screening program with a positive faecal immunochemical test (FIT) are seen at the outpatient clinic to assess their health status, receive information on colonoscopy and CRC risk, and provide informed consent. However, for many patients this information could probably also safely be exchanged in an online setting, in order to reduce the burden for patients, healthcare system, and environment. In this study we will evaluate if a face-to-face pre-colonoscopy consultation can be replaced by a Digital Intake Tool (DIT) in a CRC screening population.MethodsThis is a prospective multicentre single-arm, non-randomized study with a non-inferiority design. The DIT will triage a total of 1000 participants and inform them about CRC risk, colonoscopy, sedation, and provide bowel preparation instructions. Participants identified as high-risk (i.e., red-triaged) will be contacted by phone or scheduled for an appointment at the outpatient clinic. The primary outcome measure will be adequate bowel preparation rate, defined as the proportion of participants with a Boston Bowel Preparation (BBPS) score ≥ 6. To compare our primary outcome, we will use colonoscopy data from 1000 FIT positive participants who visited the outpatient clinic for pre-colonoscopy consultation. Secondary outcomes will include participation rate, colonoscopy adherence rate, patient experience in terms of satisfaction and anxiety, knowledge transfer, number of outpatient visits that can be averted by the DIT, and cost-effectiveness of the tool. Ethical approval was obtained from the Medical Ethical Committee of the Erasmus Medical Center (MEC-2021-0098).DiscussionThis study aims to assess if a face-to-face pre-colonoscopy consultation can be replaced by an eHealth assessment and education tool in a FIT-based CRC screening program. In case favourable results are established, the intervention evaluated in this study could significantly impact CRC screening programs, benefiting both patients and healthcare systems on a (inter)national scale. Additionally, it would enable more personalized care as the DIT can be easily customized and made feasible in other languages, thereby enhancing healthcare accessibility.Trial registrationDutch Trial Register: NL9315, date of registration: March 8th, 2021.

Incidence, characteristics, and predictive factors of post-colonoscopy colorectal cancer.

Post-colonoscopy colorectal cancer (PCCRC) is colorectal cancer (CRC) diagnosed after a colonoscopy in which no cancer is found. As PCCRC has become an important quality indicator, we determined its rates, characteristics, and index colonoscopy-related predictive factors. We carried out a multicenter, observational, retrospective study between 2015 and 2018. Rates were calculated for PCCRC developing up to 10years after colonoscopy. PCCRC was categorized according to the most plausible explanation using World Endoscopy Organization methodology. Our PCCRC population was compared to a control cohort without CRC matched 1:4 by sex, age, index colonoscopy date, indication, endoscopist, and hospital. One hundred seven PCCRC and 2508 detected CRC were diagnosed among 101,524 colonoscopy (0.1%), leading to rates of 0.4%, 2.2%, 3.1%, and 4.1% at 1, 3, 5, and 10years, respectively. PCCRC was in right (42.4%), left (41.4%), and transverse (16.4%) colon with 31.5% at stage I, 24.7% stage II, 32.6% stage III, and 11.2% stage IV. Twenty point three percent were classified as incomplete resection, 5.4% as unresected lesions, 48.6% as missed lesions with adequate colonoscopy, and 25.7% as missed lesions with inadequate colonoscopy. The median time from colonoscopy to PCCRC was 42months. Previous inadequate preparation (OR 3.05, 95%CI 1.73-5.36) and piecemeal polypectomy (OR 19.89, 95%CI 8.67-45.61) were independently associated with PCCRC. In our population, 4.1% of CRC cases were PCCRC. Most of these lesions were in right colon and attributable to lesions not visualized despite adequate bowel cleansing. Previous inadequate cleansing and piecemeal polypectomy were associated with PCCRC.

Food-Related Quality of Life Is Impaired in Latinx and Non-Latinx Patients With Inflammatory Bowel Disease

Anxiety over food choices and symptoms related to food consumption diminish quality of life (QoL) in inflammatory bowel disease (IBD) patients. However, the specific factors that impact QoL among IBD patients remain unclear. In this study, we analyzed the relationships of demographic and disease factors with food-related QoL (FRQoL) in a large, diverse US cohort of IBD patients. In this cross-sectional analysis of 1108 IBD patients aged ≥18 years, we measured FRQoL with the 29-item Food-Related Quality of Life Questionnaire (FR-QoL-29) and disease activity with the Harvey-Bradshaw index in Crohn's disease (CD) patients or the Simple Clinical Colitis Activity Index in ulcerative colitis (UC) patients. Latinx immigrants completed a Spanish translation of the FR-QoL-29. A subset of patients had colonoscopy and inflammatory marker data available. We used univariate, multivariate, and subgroup analyses to examine the factors that influence FRQoL. In our cohort, 55% of IBD patients self-identified as Latinx. Latinx and non-Latinx patients had similar FR-QoL-29 scores. Female patients had significantly lower FRQoL than male patients (P= .001). Increasing age and IBD duration correlated with higher FRQoL (P < .0001). In UC patients, higher Simple Clinical Colitis Activity Index scores (P < .0001), higher Mayo scores (P= .0009), and longer disease duration (P= .03) predicted significantly lower FRQoL. Disease activity and FRQoL were not significantly related in CD patients. This is the largest study to date to examine FRQoL in American IBD patients, and the first to include Latinx patients. Disease-related factors had a greater impact on FRQoL than ethnicity. Clinical and endoscopic disease activity had a more detrimental impact on FRQoL in UC than in CD. Diet intervention studies are needed to alleviate symptoms and improve FRQoL in the IBD population.

Semi-Supervised Detection Model Based on Adaptive Ensemble Learning for Medical Images.

Introducing deep learning technologies into the medical image processing field requires accuracy guarantee, especially for high-resolution images relayed through endoscopes. Moreover, works relying on supervised learning are powerless in the case of inadequate labeled samples. Therefore, for end-to-end medical image detection with overcritical efficiency and accuracy in endoscope detection, an ensemble-learning-based model with a semi-supervised mechanism is developed in this work. To gain a more accurate result through multiple detection models, we propose a new ensemble mechanism, termed alternative adaptive boosting method (Al-Adaboost), combining the decision-making of two hierarchical models. Specifically, the proposal consists of two modules. One is a local region proposal model with attentive temporal-spatial pathways for bounding box regression and classification, and the other one is a recurrent attention model (RAM) to provide more precise inferences for further classification according to the regression result. The proposal Al-Adaboost will adjust the weights of labeled samples and the two classifiers adaptively, and the nonlabel samples are assigned pseudolabels by our model. We investigate the performance of Al-Adaboost on both the colonoscopy and laryngoscopy data coming from CVC-ClinicDB and the affiliated hospital of Kaohsiung Medical University. The experimental results prove the feasibility and superiority of our model.

Post-Chemotherapy Clinical Perianal Infection Features in Patients with Acute Leukemia

Objective: This study aims to examine the incidence of post-chemotherapy perianal infection and its influencing factors in patients with acute leukemia.&lt;br&gt;Methods: A total of 243 patients with acute leukemia who underwent chemotherapy in the Three Gorges Hospital affiliated to Chongqing University, China, between January 2019 and December 2020 were selected as study subjects. In the present retrospective study, patients with post-chemotherapy perianal infection were monitored, and the perianal infection rate and clinical features of perianal infection were determined. Categorical variables were compared using the Chi-square test, and the influencing factors of post-chemotherapy perianal infection in patients with acute leukemia were evaluated using logistic analysis.&lt;br&gt;Results: A total of 24 patients (9.88%) with acute leukemia suffered post-chemotherapy perianal infection. Age, basic perianal disease (hemorrhoids) history, constipation, diarrhea, duration of agranulocytosis, and length of hospital stay were compared among the patients. Perianal disease classification, perianal ultrasound, colonoscopy, postoperative pathology, and other clinical data were compared and discussed in relation to the occurrence and development of the disease. The results showed that there were no significant differences in perianal infection degrees between genders and among different types of leukemia (p &gt; 0.05). There were no statistically significant differences in age, pain score, minimum white blood cell count, deficiency duration, and length of hospital stay among patients with different degrees of infection. The Spearman rank correlation test showed that the perianal infection degree was positively correlated with the highest hypersensitive C-reactive protein (hs-CRP) level (p &lt; 0.05). The difference was statistically significant; the higher the maximum hs-CRP/procalcitonin levels, the more serious the perianal infection.&lt;br&gt;Conclusions: Perianal infections are common in the procession of chemotherapy or myelosuppression. This is worthy of clinical recognition. Early recognition of perianal infection and the strengthening of infection risk factor control may be beneficial to improving the subjective feelings of patients with acute leukemia undergoing chemotherapy.

GAN Inversion for Data Augmentation to Improve Colonoscopy Lesion Classification.

A major challenge in applying deep learning to medical imaging is the paucity of annotated data. This study explores the use of synthetic images for data augmentation to address the challenge of limited annotated data in colonoscopy lesion classification. We demonstrate that synthetic colonoscopy images generated by Generative Adversarial Network (GAN) inversion can be used as training data to improve polyp classification performance by deep learning models. We invert pairs of images with the same label to a semantically rich and disentangled latent space and manipulate latent representations to produce new synthetic images. These synthetic images maintain the same label as the input pairs. We perform image modality translation (style transfer) between white light and narrow-band imaging (NBI). We also generate realistic synthetic lesion images by interpolating between original training images to increase the variety of lesion shapes in the training dataset. Our experiments show that GAN inversion can produce multiple colonoscopy data augmentations that improve the downstream polyp classification performance by 2.7% in F1-score and 4.9% in sensitivity over other methods, including state-of-the-art data augmentation. Testing on unseen out-of-domain data also showcased an improvement of 2.9% in F1-score and 2.7% in sensitivity. This approach outperforms other colonoscopy data augmentation techniques and does not require re-training multiple generative models. It also effectively uses information from diverse public datasets, even those not specifically designed for the targeted downstream task, resulting in strong domain generalizability. Project code and model: https://github.com/DurrLab/GAN-Inversion.

Self-supervised representation learning using feature pyramid siamese networks for colorectal polyp detection

Colorectal cancer is a leading cause of cancer-related deaths globally. In recent years, the use of convolutional neural networks in computer-aided diagnosis (CAD) has facilitated simpler detection of early lesions like polyps during real-time colonoscopy. However, the majority of existing techniques require a large training dataset annotated by experienced experts. To alleviate the laborious task of image annotation and utilize the vast amounts of readily available unlabeled colonoscopy data to further improve the polyp detection ability, this study proposed a novel self-supervised representation learning method called feature pyramid siamese networks (FPSiam). First, a feature pyramid encoder module was proposed to effectively extract and fuse both local and global feature representations among colonoscopic images, which is important for dense prediction tasks like polyp detection. Next, a self-supervised visual feature representation containing the general feature of colonoscopic images is learned by the siamese networks. Finally, the feature representation will be transferred to the downstream colorectal polyp detection task. A total of 103 videos (861,400 frames), 100 videos (24,789 frames), and 60 videos (15,397 frames) in the LDPolypVideo dataset are used to pre-train, train, and test the performance of the proposed FPSiam and its counterparts, respectively. The experimental results have illustrated that our FPSiam approach obtains the optimal capability, which is better than that of other state-of-the-art self-supervised learning methods and is also higher than the method based on transfer learning by 2.3 mAP and 3.6 mAP for two typical detectors. In conclusion, FPSiam provides a cost-efficient solution for developing colorectal polyp detection systems, especially in conditions where only a small fraction of the dataset is labeled while the majority remains unlabeled. Besides, it also brings fresh perspectives into other endoscopic image analysis tasks.

Impact of COVID-19 Pandemic on Performance of Gastrointestinal Endoscopy.

Non-time-sensitive gastrointestinal endoscopy was deferred because of the risk of exposure to coronavirus disease 2019 (COVID-19), but no population-based studies have quantified the adverse impact on gastrointestinal procedures. This study examined the impact of the COVID-19 pandemic on the performance of esophagogastroduodenoscopy (EGD), colonoscopy, ERCP, and abdominal ultrasonography (US) in South Korea. This nationwide, population-based study compared the claim data of EGD, colonoscopy, ERCP, and abdominal US in 2020 and 2021 (COVID-19 era) with those in 2019 (before the COVID-19 era). During the first year (2020) of the COVID-19 pandemic, the annual claim data of EGD and colonoscopy were reduced by 6.3% and 6.9%, respectively, but those of ERCP and abdominal US were increased by 1.0% and 2.9%, compared to those in 2019. During the first surge (March and April 2020) of COVID-19, the monthly claim data of EGD, colonoscopy, ERCP, and abdominal US were reduced by 28.8%, 43.8%, 5.1%, and 21.6%, respectively, in March 2020, and also reduced by 17.2%, 32.8%, 4.4%, and 9.5%, respectively, in April 2020, compared to those in March and April 2019. During March and April 2020, the monthly claims of ERCP, compared with those in 2019, declined less significantly than those of EGD and colonoscopy (both p<0.001). The claims of EGD and colonoscopy were reduced more significantly than those of ERCP and abdominal US during the COVID-19 pandemic because ERCPs are time-sensitive procedures and abdominal USs are non-aerosolized procedures.