RESUMO
BACKGROUND AND AIM: Randomised trials show improved polyp detection with computer-aided detection (CADe), mostly of small lesions. However, operator and selection bias may affect CADe's true benefit. Clinical outcomes of increased detection have not yet been fully elucidated. METHODS: In this multicentre trial, CADe combining convolutional and recurrent neural networks was used for polyp detection. Blinded endoscopists were monitored in real time by a second observer with CADe access. CADe detections prompted reinspection. Adenoma detection rates (ADR) and polyp detection rates were measured prestudy and poststudy. Histological assessments were done by independent histopathologists. The primary outcome compared polyp detection between endoscopists and CADe. RESULTS: In 946 patients (51.9% male, mean age 64), a total of 2141 polyps were identified, including 989 adenomas. CADe was not superior to human polyp detection (sensitivity 94.6% vs 96.0%) but outperformed them when restricted to adenomas. Unblinding led to an additional yield of 86 true positive polyp detections (1.1% ADR increase per patient; 73.8% were <5 mm). CADe also increased non-neoplastic polyp detection by an absolute value of 4.9% of the cases (1.8% increase of entire polyp load). Procedure time increased with 6.6±6.5 min (+42.6%). In 22/946 patients, the additional detection of adenomas changed surveillance intervals (2.3%), mostly by increasing the number of small adenomas beyond the cut-off. CONCLUSION: Even if CADe appears to be slightly more sensitive than human endoscopists, the additional gain in ADR was minimal and follow-up intervals rarely changed. Additional inspection of non-neoplastic lesions was increased, adding to the inspection and/or polypectomy workload.
RESUMO
BACKGROUND: Computer-aided diagnosis (CADx) allows prediction of polyp histology during colonoscopy, which may reduce unnecessary removal of nonneoplastic polyps. However, the potential benefits and harms of CADx are still unclear. PURPOSE: To quantify the benefit and harm of using CADx in colonoscopy for the optical diagnosis of small (≤5-mm) rectosigmoid polyps. DATA SOURCES: Medline, Embase, and Scopus were searched for articles published before 22 December 2023. STUDY SELECTION: Histologically verified diagnostic accuracy studies that evaluated the real-time performance of physicians in predicting neoplastic change of small rectosigmoid polyps without or with CADx assistance during colonoscopy. DATA EXTRACTION: The clinical benefit and harm were estimated on the basis of accuracy values of the endoscopist before and after CADx assistance. The certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework. The outcome measure for benefit was the proportion of polyps predicted to be nonneoplastic that would avoid removal with the use of CADx. The outcome measure for harm was the proportion of neoplastic polyps that would be not resected and left in situ due to an incorrect diagnosis with the use of CADx. Histology served as the reference standard for both outcomes. DATA SYNTHESIS: Ten studies, including 3620 patients with 4103 small rectosigmoid polyps, were analyzed. The studies that assessed the performance of CADx alone (9 studies; 3237 polyps) showed a sensitivity of 87.3% (95% CI, 79.2% to 92.5%) and specificity of 88.9% (CI, 81.7% to 93.5%) in predicting neoplastic change. In the studies that compared histology prediction performance before versus after CADx assistance (4 studies; 2503 polyps), there was no difference in the proportion of polyps predicted to be nonneoplastic that would avoid removal (55.4% vs. 58.4%; risk ratio [RR], 1.06 [CI, 0.96 to 1.17]; moderate-certainty evidence) or in the proportion of neoplastic polyps that would be erroneously left in situ (8.2% vs. 7.5%; RR, 0.95 [CI, 0.69 to 1.33]; moderate-certainty evidence). LIMITATION: The application of optical diagnosis was only simulated, potentially altering the decision-making process of the operator. CONCLUSION: Computer-aided diagnosis provided no incremental benefit or harm in the management of small rectosigmoid polyps during colonoscopy. PRIMARY FUNDING SOURCE: European Commission. (PROSPERO: CRD42023402197).
Assuntos
Pólipos do Colo , Colonoscopia , Diagnóstico por Computador , Humanos , Pólipos do Colo/patologia , Pólipos do Colo/diagnóstico por imagem , Neoplasias Colorretais/patologia , Neoplasias Colorretais/diagnósticoRESUMO
Purpose: To describe the clinical, electrophysiological and genetic spectrum of inherited retinal diseases associated with variants in the PRPH2 gene. Methods: A total of 241 patients from 168 families across 15 sites in 9 countries with pathogenic or likely pathogenic variants in PRPH2 were included. Records were reviewed for age at symptom onset, visual acuity, full-field ERG, fundus colour photography, fundus autofluorescence (FAF), and SD-OCT. Images were graded into six phenotypes. Statistical analyses were performed to determine genotype-phenotype correlations. Results: The median age at symptom onset was 40 years (range, 4-78 years). FAF phenotypes included normal (5%), butterfly pattern dystrophy, or vitelliform macular dystrophy (11%), central areolar choroidal dystrophy (28%), pseudo-Stargardt pattern dystrophy (41%), and retinitis pigmentosa (25%). Symptom onset was earlier in retinitis pigmentosa as compared with pseudo-Stargardt pattern dystrophy (34 vs 44 years; P = 0.004). The median visual acuity was 0.18 logMAR (interquartile range, 0-0.54 logMAR) and 0.18 logMAR (interquartile range 0-0.42 logMAR) in the right and left eyes, respectively. ERG showed a significantly reduced amplitude across all components (P < 0.001) and a peak time delay in the light-adapted 30-Hz flicker and single-flash b-wave (P < 0.001). Twenty-two variants were novel. The central areolar choroidal dystrophy phenotype was associated with 13 missense variants. The remaining variants showed marked phenotypic variability. Conclusions: We described six distinct FAF phenotypes associated with variants in the PRPH2 gene. One FAF phenotype may have multiple ERG phenotypes, demonstrating a discordance between structure and function. Given the vast spectrum of PRPH2 disease our findings are useful for future clinical trials.
Assuntos
Eletrorretinografia , Periferinas , Fenótipo , Distrofias Retinianas , Acuidade Visual , Humanos , Periferinas/genética , Pessoa de Meia-Idade , Adulto , Masculino , Feminino , Adolescente , Distrofias Retinianas/genética , Distrofias Retinianas/fisiopatologia , Distrofias Retinianas/diagnóstico , Idoso , Acuidade Visual/fisiologia , Criança , Adulto Jovem , Pré-Escolar , Tomografia de Coerência Óptica , Mutação , Angiofluoresceinografia , Estudos de Associação Genética , Estudos Retrospectivos , Análise Mutacional de DNA , DNA/genética , LinhagemRESUMO
Detection and diagnosis of colon polyps are key to preventing colorectal cancer. Recent evidence suggests that AI-based computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems can enhance endoscopists' performance and boost colonoscopy effectiveness. However, most available public datasets primarily consist of still images or video clips, often at a down-sampled resolution, and do not accurately represent real-world colonoscopy procedures. We introduce the REAL-Colon (Real-world multi-center Endoscopy Annotated video Library) dataset: a compilation of 2.7 M native video frames from sixty full-resolution, real-world colonoscopy recordings across multiple centers. The dataset contains 350k bounding-box annotations, each created under the supervision of expert gastroenterologists. Comprehensive patient clinical data, colonoscopy acquisition information, and polyp histopathological information are also included in each video. With its unprecedented size, quality, and heterogeneity, the REAL-Colon dataset is a unique resource for researchers and developers aiming to advance AI research in colonoscopy. Its openness and transparency facilitate rigorous and reproducible research, fostering the development and benchmarking of more accurate and reliable colonoscopy-related algorithms and models.
Assuntos
Pólipos do Colo , Colonoscopia , Colonoscopia/métodos , Humanos , Pólipos do Colo/diagnóstico , Diagnóstico por Computador , Inteligência Artificial , Gravação em Vídeo , Neoplasias Colorretais/diagnósticoRESUMO
BACKGROUND: Post-fecal immunochemical test (FIT) colonoscopy represents a setting with an enriched prevalence of advanced adenomas. Due to an expected higher risk of colorectal cancer (CRC), postpolypectomy surveillance is recommended, generating a substantially increased load on endoscopy services. The aim of our study was to investigate postpolypectomy CRC risk in a screening population of FIT+ subjects after resection of low-risk adenomas (LRAs) or high-risk adenomas (HRAs). METHODS: We retrieved data from a cohort of patients undergoing postpolypectomy surveillance within a FIT-based CRC screening program in Italy between 2002 and 2017 and followed-up to December 2021. Main outcomes were postpolypectomy CRC incidence and mortality risks according to type of adenoma (LRA/HRA) removed at colonoscopy as well as morphology, size, dysplasia, and location of the index lesion. We adopted as comparators FIT+/colonoscopy-negative and FIT- patients. The absolute risk was calculated as the number of incident CRCs per 100,000 person-years of follow-up. We used Cox multivariable regression models to identify associations between CRC risks and patient- and polyp-related variables. RESULTS: Overall, we included 87,248 post-FIT+ colonoscopies (133 endoscopists). Of these, 42,899 (49.2%) were negative, 21,650 (24.8%) had an LRA, and 22,709 (26.0%) an HRA. After a median follow-up of 7.25 years, a total of 635 CRCs were observed. For patients with LRAs, CRC incidence (hazard ratio [HR], 1.18; 95% confidence interval [CI], 0.92-1.53) was not increased compared with the FIT+/colonoscopy-negative group, while for HRAs a significant increase in CRC incidence (HR, 1.53; 95% CI, 1.14-2.04) was found. The presence of 1 or more risk factors among proximal location, nonpedunculated morphology, and high-grade dysplasia explained most of this excess CRC risk in the HRA group (HR, 1.85; 95% CI, 1.36-2.52). Patients with only distal pedunculated polyps without high-grade dysplasia, representing 39.2% of HRA, did not have increased risk compared with the FIT- group (HR, 0.87; 95% CI, 0.59-1.28). CONCLUSIONS: CRC incidence is significantly higher in patients with HRAs diagnosed at colonoscopy. However, such excess risk does not appear to apply to patients with only distal pedunculated polyps without high-grade dysplasia, an observation that could potentially reduce the burden of surveillance in FIT programs.
Assuntos
Pólipos do Colo , Colonoscopia , Neoplasias Colorretais , Humanos , Masculino , Feminino , Neoplasias Colorretais/cirurgia , Neoplasias Colorretais/epidemiologia , Neoplasias Colorretais/patologia , Pessoa de Meia-Idade , Idoso , Itália/epidemiologia , Pólipos do Colo/cirurgia , Pólipos do Colo/patologia , Pólipos do Colo/epidemiologia , Incidência , Adenoma/cirurgia , Adenoma/epidemiologia , Adenoma/patologia , Medição de Risco , Detecção Precoce de Câncer/métodos , Fatores de Risco , Estudos RetrospectivosRESUMO
This ESGE Position Statement provides structured and evidence-based guidance on the essential requirements and processes involved in training in basic gastrointestinal (GI) endoscopic procedures. The document outlines definitions; competencies required, and means to their assessment and maintenance; the structure and requirements of training programs; patient safety and medicolegal issues. 1: ESGE and ESGENA define basic endoscopic procedures as those procedures that are commonly indicated, generally accessible, and expected to be mastered (technically and cognitively) by the end of any core training program in gastrointestinal endoscopy. 2: ESGE and ESGENA consider the following as basic endoscopic procedures: diagnostic upper and lower GI endoscopy, as well as a limited range of interventions such as: tissue acquisition via cold biopsy forceps, polypectomy for lesions ≤â10âmm, hemostasis techniques, enteral feeding tube placement, foreign body retrieval, dilation of simple esophageal strictures, and India ink tattooing of lesion location. 3: ESGE and ESGENA recommend that training in GI endoscopy should be subject to stringent formal requirements that ensure all ESGE key performance indicators (KPIs) are met. 4: Training in basic endoscopic procedures is a complex process and includes the development and acquisition of cognitive, technical/motor, and integrative skills. Therefore, ESGE and ESGENA recommend the use of validated tools to track the development of skills and assess competence. 5: ESGE and ESGENA recommend incorporating a multimodal approach to evaluating competence in basic GI endoscopic procedures, including procedural thresholds and the measurement and documentation of established ESGE KPIs. 7: ESGE and ESGENA recommend the continuous monitoring of ESGE KPIs during GI endoscopy training to ensure the trainee's maintenance of competence. 9: ESGE and ESGENA recommend that GI endoscopy training units fulfil the ESGE KPIs for endoscopy units and, furthermore, be capable of providing the dedicated personnel, infrastructure, and sufficient case volume required for successful training within a structured training program. 10: ESGE and ESGENA recommend that trainers in basic GI endoscopic procedures should be endoscopists with formal educational training in the teaching of endoscopy, which allows them to successfully and safely teach trainees.
Assuntos
Gastroenterologia , Humanos , Endoscopia Gastrointestinal/métodos , Endoscópios Gastrointestinais , Sociedades MédicasRESUMO
The implementation of FIT programs reduces incidence and mortality from CRC in the screened subjects. The ultimate efficacy for CRC morbidity and mortality prevention in a FIT program depends on the colonoscopy in FIT+ subjects that has the task of detecting and removing these advanced lesions. Recently, there has been growing evidence on factors that influence the quality of colonoscopy specifically withing organized FIT programs, prompting to dedicated interventions in order to maximize the benefit/harm ratio of post-FIT colonoscopy. This document focuses on the diagnostic phase of colonoscopy, providing indications on how to standardise colonoscopy in FIT+ subjects, regarding timing of examination, management of antithrombotic therapy, bowel preparation, competence and sedation.
Assuntos
Colonoscopia , Neoplasias Colorretais , Detecção Precoce de Câncer , Humanos , Colonoscopia/normas , Colonoscopia/métodos , Neoplasias Colorretais/diagnóstico , Detecção Precoce de Câncer/métodos , Detecção Precoce de Câncer/normas , Programas de Rastreamento/métodos , Programas de Rastreamento/normas , Catárticos/administração & dosagemRESUMO
BACKGROUND/AIMS: Endoscopic screening for gastric cancer (GC) is not recommended in low-intermediate incidence countries. Artificial intelligence (AI) has high accuracy in GC detection and might increase the cost-effectiveness of screening strategies. We aimed to assess the cost-effectiveness of AI for GC detection in settings with different GC incidence and different accuracies of AI systems. METHODS: Cost-effectiveness analysis (using Markov model) comparing different screening strategies (no screening versus single esophagogastroduodenoscopy (EGD) at 50 years versus stand-alone EGD every 5/10 years versus combined EGD and screening colonoscopy once or twice per decade in Netherlands, Italy and Portugal) with variable AI accuracy settings. The primary outcome was the incremental cost-effectiveness ratio of the different strategies versus no screening. Deterministic and probabilistic sensitivity analyses were conducted. RESULTS: Without AI, one single EGD at 50 years (Netherlands, Italy, Portugal), EGD combined with screening colonoscopy once per decade (Italy and Portugal) and EGD combined with screening colonoscopy twice per decade (Portugal) are cost-effective when compared with no screening. If AI increases the accuracy of EGD by at least 1% in comparison to the accuracy of white-light endoscopy accuracy (89%), combined screening twice per decade also becomes cost-effective in Italy. If AI accuracy reaches at least 96%, combined screening once per decade is also cost-effective in the Netherlands. DISCUSSION: In European countries, AI-assisted EGD may improve the cost-effectiveness of GC screening with combined EGD and screening colonoscopy. The actual effect of AI on cost-effectiveness may vary dependent on the accuracy and costs of the AI system.
Assuntos
Neoplasias Colorretais , Neoplasias Gástricas , Humanos , Análise Custo-Benefício , Análise de Custo-Efetividade , Inteligência Artificial , Detecção Precoce de Câncer , Colonoscopia , Neoplasias Colorretais/diagnóstico , Neoplasias Colorretais/epidemiologia , Neoplasias Colorretais/prevenção & controle , Europa (Continente) , Programas de Rastreamento , Neoplasias Gástricas/diagnóstico , Neoplasias Gástricas/epidemiologiaRESUMO
BACKGROUND AND AIMS: Benefits of computer-aided detection (CADe) in detecting colorectal neoplasia were shown in many randomized trials in which endoscopists' behavior was strictly controlled. However, the effect of CADe on endoscopists' performance in less-controlled setting is unclear. This systematic review and meta-analyses were aimed at clarifying benefits and harms of using CADe in real-world colonoscopy. METHODS: We searched MEDLINE, EMBASE, Cochrane, and Google Scholar from inception to August 20, 2023. We included nonrandomized studies that compared the effectiveness between CADe-assisted and standard colonoscopy. Two investigators independently extracted study data and quality. Pairwise meta-analysis was performed utilizing risk ratio for dichotomous variables and mean difference (MD) for continuous variables with a 95% confidence interval (CI). RESULTS: Eight studies were included, comprising 9782 patients (4569 with CADe and 5213 without CADe). Regarding benefits, there was a difference in neither adenoma detection rate (44% vs 38%; risk ratio, 1.11; 95% CI, 0.97 to 1.28) nor mean adenomas per colonoscopy (0.93 vs 0.79; MD, 0.14; 95% CI, -0.04 to 0.32) between CADe-assisted and standard colonoscopy, respectively. Regarding harms, there was no difference in the mean non-neoplastic lesions per colonoscopy (8 studies included for analysis; 0.52 vs 0.47; MD, 0.14; 95% CI, -0.07 to 0.34) and withdrawal time (6 studies included for analysis; 14.3 vs 13.4 minutes; MD, 0.8 minutes; 95% CI, -0.18 to 1.90). There was a substantial heterogeneity, and all outcomes were graded with a very low certainty of evidence. CONCLUSION: CADe in colonoscopies neither improves the detection of colorectal neoplasia nor increases burden of colonoscopy in real-world, nonrandomized studies, questioning the generalizability of the results of randomized trials.
RESUMO
We investigated the potential correlation between morphological and functional parameters describing the rarefaction and dysfunction of retinal ganglion cells (RGCs), located in the macula, in multiple sclerosis eyes with a history of optic neuritis (MS-ON). A total of 19 MS-ON eyes from 19 MS patients (mean age: 44.16 ± 4.66 years; 11 females and 8 males), with a mean disease duration of 10.06 ± 6.12 years and full recovery of visual acuity, and 30 age-similar (mean age: 45.09 ± 5.08 years) healthy eyes were submitted for ophthalmological evaluation using swept-source optical coherence tomography (SS-OCT) and multifocal photopic negative response (mfPhNR) to study the structural and functional features of localized RGCs. Both GCL+ thickness (via SS-OCT) and response amplitude density (RAD) (via mfPhNR) measurements were obtained from annular regions and ETDRS sectors. Morphological and electrophysiological data from the control and MS groups were compared by using an ANOVA test. GCL+ values were correlated with the corresponding RADs derived from almost superimposable areas using Pearson's tests (p < 0.01). In MS-ON eyes, the mean values of macular GCL+-T and mfPhNR RAD detected in all rings and ETDRS sectors were significantly reduced (p < 0.01) when compared with control ones. In addition, when plotting the GCL+-T and mfPhNR RAD individual data from MS-ON eyes, we found statistically significant linear correlations (p < 0.01) when considering responses from both rings and sectors. In conclusion, in MS-ON eyes, a topographical correlation between structural and functional impairment of macular RGCs occurs.
RESUMO
All endoscopic procedures are invasive and carry risk. Accordingly, all endoscopists should involve the patient in the decision-making process about the most appropriate endoscopic procedure for that individual, in keeping with a patient's right to self-determination and autonomy. Recognition of this has led to detailed guidelines on informed consent for endoscopy in some countries, but in many no such guidance exists; this may lead to variations in care and exposure to risk of litigation. In this document, the European Society of Gastrointestinal Endoscopy (ESGE) sets out a series of statements that cover best practice in informed consent for endoscopy. These statements should be seen as a minimum standard of practice, but practitioners must be aware of and adhere to the law in their own country. 1: Patients should give informed consent for all gastrointestinal endoscopic procedures for which they have capacity to do so. 2: The healthcare professional seeking consent for an endoscopic procedure should ensure that the patient has the capacity to consent to that procedure. 3: For patients who lack capacity, healthcare personnel should at all times try to engage with people close to the patient, such as family, friends, or caregivers, to achieve consensus on the appropriateness of performing the procedure. 4: Where a patient lacks capacity to provide informed consent, the best interest decision should be clearly documented in the medical record. This should include information about the capacity assessment, reason(s) that the decision cannot be delayed for capacity recovery (or if recovery is not expected), who has been consulted, and where relevant the form of authority for the decision. 5: There should be a systematic and transparent disclosure of the expected benefits and harms that may reasonably affect patient choice on whether or not to undergo any diagnostic or interventional endoscopic procedure. Information about possible alternatives, as well as the consequences of doing nothing, should also be provided when relevant. 6: The information provided on the benefit and harms of an endoscopic procedure should be adapted to the procedure and patient-specific risk factors, and the preferences of the patient should be central to the consent process. 7: The consent discussion should be undertaken by an individual who is familiar with the procedure and its risks, and is able to discuss these in the context of the individual patient. 8: Patients should confirm consent to an endoscopic procedure in a private, unrushed, and non-coercive environment. 9: If a patient requests that an endoscopic procedure be discontinued, the procedure should be paused and the patient's capacity for decision making assessed. If a competent patient continues to object to the procedure, or if a conclusive determination of capacity is not feasible, the examination should be terminated as soon as it is safe to do so. 10: Informed consent should be sufficiently detailed to cover all findings that can be reasonably anticipated during an endoscopic examination. The scope of this consent should not be expanded, nor a patient's implicit consent for additional interventions assumed, unless failure to proceed with such interventions would result in immediate and predictable harm to the patient.
Assuntos
Endoscopia Gastrointestinal , Consentimento Livre e Esclarecido , Humanos , Endoscopia Gastrointestinal/métodosRESUMO
BACKGROUND: Artificial intelligence computer-aided detection (CADe) of colorectal neoplasia during colonoscopy may increase adenoma detection rates (ADRs) and reduce adenoma miss rates, but it may increase overdiagnosis and overtreatment of nonneoplastic polyps. PURPOSE: To quantify the benefits and harms of CADe in randomized trials. DESIGN: Systematic review and meta-analysis. (PROSPERO: CRD42022293181). DATA SOURCES: Medline, Embase, and Scopus databases through February 2023. STUDY SELECTION: Randomized trials comparing CADe-assisted with standard colonoscopy for polyp and cancer detection. DATA EXTRACTION: Adenoma detection rate (proportion of patients with ≥1 adenoma), number of adenomas detected per colonoscopy, advanced adenoma (≥10 mm with high-grade dysplasia and villous histology), number of serrated lesions per colonoscopy, and adenoma miss rate were extracted as benefit outcomes. Number of polypectomies for nonneoplastic lesions and withdrawal time were extracted as harm outcomes. For each outcome, studies were pooled using a random-effects model. Certainty of evidence was assessed using the GRADE (Grading of Recommendations Assessment, Development and Evaluation) framework. DATA SYNTHESIS: Twenty-one randomized trials on 18 232 patients were included. The ADR was higher in the CADe group than in the standard colonoscopy group (44.0% vs. 35.9%; relative risk, 1.24 [95% CI, 1.16 to 1.33]; low-certainty evidence), corresponding to a 55% (risk ratio, 0.45 [CI, 0.35 to 0.58]) relative reduction in miss rate (moderate-certainty evidence). More nonneoplastic polyps were removed in the CADe than the standard group (0.52 vs. 0.34 per colonoscopy; mean difference [MD], 0.18 polypectomy [CI, 0.11 to 0.26 polypectomy]; low-certainty evidence). Mean inspection time increased only marginally with CADe (MD, 0.47 minute [CI, 0.23 to 0.72 minute]; moderate-certainty evidence). LIMITATIONS: This review focused on surrogates of patient-important outcomes. Most patients, however, may consider cancer incidence and cancer-related mortality important outcomes. The effect of CADe on such patient-important outcomes remains unclear. CONCLUSION: The use of CADe for polyp detection during colonoscopy results in increased detection of adenomas but not advanced adenomas and in higher rates of unnecessary removal of nonneoplastic polyps. PRIMARY FUNDING SOURCE: European Commission Horizon 2020 Marie Sklodowska-Curie Individual Fellowship.
Assuntos
Inteligência Artificial , Neoplasias Colorretais , Humanos , Neoplasias Colorretais/diagnóstico , Computadores , Colonoscopia , Bases de Dados FactuaisRESUMO
BACKGROUND: Texture and color enhancement imaging (TXI) was recently proposed as a substitute for standard high definition white-light imaging (WLI) to increase lesion detection during colonoscopy. This international, multicenter randomized trial assessed the efficacy of TXI in detection of colorectal neoplasia. METHODS: Consecutive patients aged ≥â40 years undergoing screening, surveillance, or diagnostic colonoscopies at five centers (Italy, Germany, Japan) between September 2021 and May 2022 were enrolled. Patients were randomly assigned (1:1) to TXI or WLI. Primary outcome was adenoma detection rate (ADR). Secondary outcomes were adenomas per colonoscopy (APC) and withdrawal time. Relative risks (RRs) adjusted for age, sex, and colonoscopy indication were calculated. RESULTS: We enrolled 747 patients (mean age 62.3 [SD 9.5] years, 50.2â% male). ADR was significantly higher with TXI (221/375, 58.9â%) vs. WLI (159/372, 42.7â%; adjusted RR 1.38 [95â%CI 1.20-1.59]). This was significant for ≤â5âmm (RR 1.42 [1.16-1.73]) and 6-9âmm (RR 1.36 [1.01-1.83]) adenomas. A higher proportion of polypoid (151/375 [40.3â%] vs. 104/372 [28.0â%]; RR 1.43 [1.17-1.75]) and nonpolypoid (136/375 [36.3â%] vs. 102/372 [27.4â%]; RR 1.30 [1.05-1.61]) adenomas, and proximal (143/375 [38.1â%] vs. 111/372 [29.8â%]; RR 1.28 [1.05-1.57]) and distal (144/375 [38.4â%] vs. 98/372 [26.3â%]; RR 1.46 [1.18-1.80]) lesions were found with TXI. APC was higher with TXI (1.36 [SD 1.79] vs. 0.89 [SD 1.35]; incident rate ratio 1.53 [1.25-1.88]). CONCLUSIONS: TXI increased ADR and APC among patients undergoing colonoscopy for various indications. TXI increased detection of polyps <â10âmm, both in the proximal and distal colon, and may help to improve colonoscopy quality indicators.
Assuntos
Adenoma , Pólipos do Colo , Neoplasias Colorretais , Pólipos , Humanos , Masculino , Pessoa de Meia-Idade , Feminino , Neoplasias Colorretais/diagnóstico por imagem , Neoplasias Colorretais/patologia , Colonoscopia/métodos , Pólipos/diagnóstico , Adenoma/diagnóstico por imagem , Adenoma/patologia , Pólipos do Colo/diagnóstico por imagem , Pólipos do Colo/patologiaRESUMO
BACKGROUND AND AIMS: The optimal endoscopic resection method of challenging colorectal lesions (ie, adenomatous recurrences, nongranular laterally spreading tumors [LST-NGs], lesions without lifting sign <30 mm) is still under debate. The aim of this study was to directly compare endoscopic submucosal dissection (ESD) and endoscopic full-thickness resection (EFTR) for the resection of challenging colorectal lesions in a randomized trial. METHODS: A multicenter, prospective, randomized study was performed in 4 Italian referral centers. Consecutive patients referred for endoscopic resection of challenging lesions were randomly assigned to undergo EFTR or ESD. Primary outcomes were complete (R0) resection and en bloc resection of lesions. Technical success, procedure time, procedure speed, area of the resected specimen, adverse event rate, and local recurrence rate at 6 months were also compared. RESULTS: Overall, 90 patients were included in the study, equally representing the 3 challenging lesion types. Age and sex were comparable in the 2 groups. En bloc resection was obtained in 95.5% of the EFTR group and in 93.3% of the ESD group. R0 resection rate was comparable in the 2 groups (EFTR vs ESD, 42 [93.3%] vs 36 [80%]; P = .06). The EFTR group exhibited a significantly shorter total procedure time (25.6 ± 10.6 minutes vs 76.7 ± 26.4 minutes, P ≤ .01), as well as overall procedure speed (16.8 ± 11.8 mm2/min vs 11.9 ± 9.2 mm2/min, P = .03). The EFTR group had a significantly smaller mean lesion size (21.6 ± 8.3 mm vs 28.7 ± 7.7 mm, P ≤ .01). Adverse events were reported less frequently in patients in the EFTR group (4.44% vs 15.5%, P = .04). CONCLUSIONS: EFTR is comparable to ESD in the treatment of challenging colorectal lesions in terms of safety and efficacy. EFTR is considerably faster than ESD in the treatment of nonlifting lesions and adenoma recurrences. (Clinical trial registration number: NCT05502276.).
Assuntos
Adenoma , Neoplasias Colorretais , Ressecção Endoscópica de Mucosa , Humanos , Colonoscopia/métodos , Neoplasias Colorretais/patologia , Ressecção Endoscópica de Mucosa/métodos , Estudos Prospectivos , Estudos Retrospectivos , Adenoma/patologia , Resultado do TratamentoRESUMO
The aim of this study was to assess the morpho-functional involvement of the retinal ganglion cells (RGCs) and of the visual pathways in patients with superficial (ODD-S) or deep (ODD-D) optic disc drusen. This study enrolled 17 patients with ODD (mean age of 59.10 ± 12.68 years) providing 19 eyes and 20 control subjects (mean age 58.62 ± 8.77 years) providing 20 eyes. We evaluated the following: best-corrected visual acuity, visual field mean deviation (MD), the amplitude (A) of Pattern Electroretinogram (PERG), the implicit time (IT) and A of Visual Evoked Potentials (VEPs), retinal nerve fiber layer thickness (RNFL-T) and ganglion cell thickness (GC-T). In ODD-S eyes, the drusen visible height was measured. ODD-D and ODD-S were detected in 26.3% and 73.7% of ODD eyes, respectively. Significantly (p < 0.01) reduced MD, PERG A, VEP amplitude, RNFL-T and GC-T values and significantly (p < 0.01) increased VEP IT values were found in the ODD Group as compared to the Control one. In the ODD Group, no significant correlation (p > 0.01) between PERG As and VEP ITs was found. In ODD-S, the visible height was significantly correlated (p < 0.01) with reduced MD, PERG As and RNFL-T and with increased PSD and VEP IT values. Our findings suggest that ODD might induce morpho-functional changes in RGCs and their fibers and an unrelated visual pathway dysfunction leading or not leading to visual field defects. The observed morpho-functional impairment should be ascribed to an alteration in retrograde (from the axons to the RGCs) and anterograde (from the RGCs up to the visual cortex) axoplasmic transport. In ODD-S eyes, a minimum visible height of 300 microns represented the threshold for the abnormalities, suggesting that "the higher the ODD, the worse the impairment".
RESUMO
BACKGROUND & AIMS: Both computer-aided detection (CADe)-assisted and Endocuff-assisted colonoscopy have been found to increase adenoma detection. We investigated the performance of the combination of the 2 tools compared with CADe-assisted colonoscopy alone to detect colorectal neoplasias during colonoscopy in a multicenter randomized trial. METHODS: Men and women undergoing colonoscopy for colorectal cancer screening, polyp surveillance, or clincial indications at 6 centers in Italy and Switzerland were enrolled. Patients were assigned (1:1) to colonoscopy with the combinations of CADe (GI-Genius; Medtronic) and a mucosal exposure device (Endocuff Vision [ECV]; Olympus) or to CADe-assisted colonoscopy alone (control group). All detected lesions were removed and sent to histopathology for diagnosis. The primary outcome was adenoma detection rate (percentage of patients with at least 1 histologically proven adenoma or carcinoma). Secondary outcomes were adenomas detected per colonoscopy, advanced adenomas and serrated lesions detection rate, the rate of unnecessary polypectomies (polyp resection without histologically proven adenomas), and withdrawal time. RESULTS: From July 1, 2021 to May 31, 2022, there were 1316 subjects randomized and eligible for analysis; 660 to the ECV group, 656 to the control group). The adenoma detection rate was significantly higher in the ECV group (49.6%) than in the control group (44.0%) (relative risk, 1.12; 95% CI, 1.00-1.26; P = .04). Adenomas detected per colonoscopy were significantly higher in the ECV group (mean ± SD, 0.94 ± 0.54) than in the control group (0.74 ± 0.21) (incidence rate ratio, 1.26; 95% CI, 1.04-1.54; P = .02). The 2 groups did not differ in term of detection of advanced adenomas and serrated lesions. There was no significant difference between groups in mean ± SD withdrawal time (9.01 ± 2.48 seconds for the ECV group vs 8.96 ± 2.24 seconds for controls; P = .69) or proportion of subjects undergoing unnecessary polypectomies (relative risk, 0.89; 95% CI, 0.69-1.14; P = .38). CONCLUSIONS: The combination of CADe and ECV during colonoscopy increases adenoma detection rate and adenomas detected per colonoscopy without increasing withdrawal time compared with CADe alone. CLINICALTRIALS: gov, Number: NCT04676308.
Assuntos
Adenoma , Neoplasias Colorretais , Masculino , Humanos , Feminino , Colonoscopia , Adenoma/diagnóstico por imagem , Adenoma/patologia , Neoplasias Colorretais/diagnóstico , Neoplasias Colorretais/patologia , Mucosa , ComputadoresRESUMO
Gastrointestinal endoscopy has proved to be a perfect context for the development of artificial intelligence (AI) systems that can aid endoscopists in many tasks of their daily activities. Lesion detection (computer-aided detection, CADe) and lesion characterization (computer-aided characterization, CADx) during colonoscopy are the clinical applications of AI in gastroenterology for which by far the most evidence has been published. Indeed, they are the only applications for which more than one system has been developed by different companies, is currently available on the market, and may be used in clinical practice. Both CADe and CADx, alongside hopes and hypes, come with potential drawbacks, limitations and dangers that must be known, studied and researched as much as the optimal uses of these machines, aiming to stay one step ahead of the possible misuse of what will always be an aid to the clinician and never a substitute. An AI revolution in colonoscopy is on the way, but the potential uses are infinite and only a fraction of them have currently been studied. Future applications can be designed to ensure all aspects of colonoscopy quality parameters and truly deliver a standardization of practice, regardless of the setting in which the procedure is performed. In this review, we cover the available clinical evidence on AI applications in colonoscopy and offer an overview of future directions.
RESUMO
BACKGROUND: Colorectal cancer (CRC) screening programs based on fecal immunochemical tests (FITs) represent the standard of care for population-based interventions. Their benefit depends on the identification of neoplasia at colonoscopy after FIT positivity. Colonoscopy quality measured by adenoma detection rate (ADR) may affect screening program effectiveness. OBJECTIVE: To examine the association between ADR and postcolonoscopy CRC (PCCRC) risk in a FIT-based screening program. DESIGN: Retrospective population-based cohort study. SETTING: Fecal immunochemical test-based CRC screening program between 2003 and 2021 in northeastern Italy. PATIENTS: All patients with a positive FIT result who had a colonoscopy were included. MEASUREMENTS: The regional cancer registry supplied information on any PCCRC diagnosed between 6 months and 10 years after colonoscopy. Endoscopists' ADR was categorized into 5 groups (20% to 39.9%, 40% to 44.9%, 45% to 49.9%, 50% to 54.9%, and 55% to 70%). To examine the association of ADR with PCCRC incidence risk, Cox regression models were fitted to estimate hazard ratios (HRs) and 95% CIs. RESULTS: Of the 110 109 initial colonoscopies, 49 626 colonoscopies done by 113 endoscopists between 2012 and 2017 were included. After 328 778 person-years follow-up, 277 cases of PCCRC were diagnosed. Mean ADR was 48.3% (range, 23% and 70%). Incidence rates of PCCRC from lowest to highest ADR group were 13.13, 10.61, 7.60, 6.01, and 5.78 per 10 000 person-years. There was a significant inverse association between ADR and PCCRC incidence risk, with a 2.35-fold risk increase (95% CI, 1.63 to 3.38) in the lowest group compared with the highest. The adjusted HR for PCCRC associated with 1% increase in ADR was 0.96 (CI, 0.95 to 0.98). LIMITATION: Adenoma detection rate is partly determined by FIT positivity cutoff; exact values may vary in different settings. CONCLUSION: In a FIT-based screening program, ADR is inversely associated with PCCRC incidence risk, mandating appropriate colonoscopy quality monitoring in this setting. Increasing endoscopists' ADR may significantly reduce PCCRC risk. PRIMARY FUNDING SOURCE: None.
Assuntos
Adenoma , Neoplasias Colorretais , Humanos , Estudos de Coortes , Estudos Retrospectivos , Detecção Precoce de Câncer , Neoplasias Colorretais/diagnóstico , Neoplasias Colorretais/epidemiologia , Colonoscopia , Adenoma/diagnóstico , Adenoma/epidemiologia , Convulsões , Programas de RastreamentoRESUMO
BACKGROUND: Optical diagnosis of colonic polyps is poorly reproducible outside of high volume referral centers. The present study aimed to assess whether real-time artificial intelligence (AI)-assisted optical diagnosis is accurate enough to implement the leave-in-situ strategy for diminutive (≤â5âmm) rectosigmoid polyps (DRSPs). METHODS: Consecutive colonoscopy outpatients with ≥â1 DRSP were included. DRSPs were categorized as adenomas or nonadenomas by the endoscopists, who had differing expertise in optical diagnosis, with the assistance of a real-time AI system (CAD-EYE). The primary end point was ≥â90â% negative predictive value (NPV) for adenomatous histology in high confidence AI-assisted optical diagnosis of DRSPs (Preservation and Incorporation of Valuable endoscopic Innovations [PIVI-1] threshold), with histopathology as the reference standard. The agreement between optical- and histology-based post-polypectomy surveillance intervals (≥â90â%; PIVI-2 threshold) was also calculated according to European Society of Gastrointestinal Endoscopy (ESGE) and United States Multi-Society Task Force (USMSTF) guidelines. RESULTS: Overall 596 DRSPs were retrieved for histology in 389 patients; an AI-assisted high confidence optical diagnosis was made in 92.3â%. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0â% (95â%CI 87.1â%-93.9â%). The PIVI-2 threshold was met with 97.4â% (95â%CI 95.7â%-98.9â%) and 92.6â% (95â%CI 90.0â%-95.2â%) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3â%, 95â%CI 76.4â%-87.3â%) than for experts (91.9â%, 95â%CI 88.5â%-94.5â%); however, nonexperts quickly approached the performance levels of experts over time. CONCLUSION: AI-assisted optical diagnosis matches the required PIVI thresholds. This does not however offset the need for endoscopists' high level confidence and expertise. The AI system seems to be useful, especially for nonexperts.