AIM: To retrospectively compare previous-day vs splitdose preparation in terms of bowel cleanliness and polyp detection in patients referred for polypectomy. METHODS: Fifty patients underwent two colonoscopies: one di...AIM: To retrospectively compare previous-day vs splitdose preparation in terms of bowel cleanliness and polyp detection in patients referred for polypectomy. METHODS: Fifty patients underwent two colonoscopies: one diagnostic in a private clinic and a second for polypectomy in a University Hospital. The latter procedures were performed within 12 wk of the index ones. Examinations were accomplished by two experienced endoscopists, different in each facility. Twenty-seven patients underwent screening/surveillance colonoscopy, while the rest were symptomatic. Previous day bowel preparation was utilized initially and splitdose for polypectomy. Colon cleansing was evaluated using the Aronchick scale. We measured the number of detected polyps, and the polyp miss rates per-polyp.RESULTS: Excellent/good preparation was reported in 38 cases with previous-day preparation(76%) vs 46 with split-dose(92%), respectively(P = 0.03). One hundred and twenty-six polyps were detected initially and 169 subsequently(P < 0.0001); 88 vs 126 polyps were diminutive(P < 0.0001), 25 vs 29 small(P = 0.048) and 13 vs 14 equal or larger than 10 mm. The miss rates for total, diminutive, small and large polyps were 25.4%, 30.1%, 13.7% and 6.6%, respectively. Multivariate analysis revealed that split-dose preparation was significantly associated(OR, P) with increased number of polyps detected overall(0.869, P < 0.001), in the right(0.418, P = 0.008) and in the left colon(0.452, P = 0.02). CONCLUSION: Split-dose preparation improved colon cleansing, enhanced polyp detection and unmasked significant polyp miss rates.展开更多
BACKGROUND Artificial intelligence in colonoscopy is an emerging field,and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas.Several deep learning-bas...BACKGROUND Artificial intelligence in colonoscopy is an emerging field,and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas.Several deep learning-based computer-assisted detection(CADe)techniques were established from small single-center datasets,and unrepresentative learning materials might confine their application and generalization in wide practice.Although CADes have been reported to identify polyps in colonoscopic images and videos in real time,their diagnostic performance deserves to be further validated in clinical practice.AIM To train and test a CADe based on multicenter high-quality images of polyps and preliminarily validate it in clinical colonoscopies.METHODS With high-quality screening and labeling from 55 qualified colonoscopists,a dataset consisting of over 71000 images from 20 centers was used to train and test a deep learning-based CADe.In addition,the real-time diagnostic performance of CADe was tested frame by frame in 47 unaltered full-ranged videos that contained 86 histologically confirmed polyps.Finally,we conducted a selfcontrolled observational study to validate the diagnostic performance of CADe in real-world colonoscopy with the main outcome measure of polyps per colonoscopy in Changhai Hospital.RESULTS The CADe was able to identify polyps in the test dataset with 95.0%sensitivity and 99.1%specificity.For colonoscopy videos,all 86 polyps were detected with 92.2%sensitivity and 93.6%specificity in frame-by-frame analysis.In the prospective validation,the sensitivity of CAD in identifying polyps was 98.4%(185/188).Folds,reflections of light and fecal fluid were the main causes of false positives in both the test dataset and clinical colonoscopies.Colonoscopists can detect more polyps(0.90 vs 0.82,P<0.001)and adenomas(0.32 vs 0.30,P=0.045)with the aid of CADe,particularly polyps<5 mm and flat polyps(0.65 vs 0.57,P<0.001;0.74 vs 0.67,P=0.001,respectively).However,high efficacy is not realized in colonoscopies with inadequate bowel preparation and withdrawal time(P=0.32;P=0.16,respectively).CONCLUSION CADe is feasible in the clinical setting and might help endoscopists detect more polyps and adenomas,and further confirmation is warranted.展开更多
AIM To assess the interendoscopist variability in the detection of colorectal polyps according to their location and histological type.METHODS This study was a retrospective analysis of prospectively collected data fr...AIM To assess the interendoscopist variability in the detection of colorectal polyps according to their location and histological type.METHODS This study was a retrospective analysis of prospectively collected data from a regional colorectal cancer(CRC) screening program; 2979 complete colonoscopies from 18 endoscopists were included. Variability in performance between endoscopists for detection of at least one adenoma(A), one proximal adenoma(PA), one distal adenoma(DA), and one proximal serrated polyp(PSP) was assessed by using multilevel logistic regression models.RESULTS The observed detection rates among the 18 endoscopists ranged from 24.6% to 47.6%(mean = 35.7%) for A, from 19.1% to 39.0%(mean = 29.4%) for DA, from 6.0% to 22.9%(mean = 12.4%) for PA, and from 1.3% to 19.3%(mean = 6.9%) for PSP.After adjusting for patient-level variables(sex, age), the interendoscopist detection rates variability achieved a significant level for A, PA, and PSP but not for DA(P = 0.03, P = 0.02, P = 0.02 and P = 0.08, respectively). This heterogeneity, as measured by the variance partition coefficient, was approximately threefold higher for PA(6.6%) compared with A(2.1%), and twofold higher for PSP(12.3%) compared with PA.CONCLUSION These results demonstrate significant interendoscopist variability for proximal polyp particularly for serrated p o l y p s, b u t n o t f o r d i s t a l a d e n o m a d e t e c t i o n. These findings contribute to explain the decreased effectiveness of complete colonoscopies at preventing proximal CRCs and the need to carefully assess the proximal colon during scope procedure.展开更多
AIMTo identify the prevalence, and clinical and pathologic characteristic of colonic polyps among Iranian patients undergoing a comprehensive colonoscopy, and determine the polyp detection rate (PDR) and adenoma detec...AIMTo identify the prevalence, and clinical and pathologic characteristic of colonic polyps among Iranian patients undergoing a comprehensive colonoscopy, and determine the polyp detection rate (PDR) and adenoma detection rate (ADR). METHODSIn this cross-sectional study, demographics and epidemiologic characteristics of 531 persons who underwent colonoscopies between 2014 and 2015 at Mehrad gastrointestinal clinic were determined. Demographics, indication for colonoscopy, colonoscopy findings, number of polyps, and histopathological characteristics of the polyps were examined for each person. RESULTSOur sample included 295 (55.6%) women and 236 (44.4%) men, with a mean age of 50.25 ± 14.89 years. Overall PDR was 23.5% (125/531). ADR and colorectal cancer detection rate in this study were 12.8% and 1.5%, respectively. Polyps were detected more significantly frequently in men than in women (52.8% vs 47.2%, P vs 56.4 years, P CONCLUSIONThe prevalence of polyps and adenomas in this study is less than that reported in the Western populations. In our patients, distal colon is more susceptible to developing polyps and cancer than proximal colon.展开更多
AIM: To evaluate the new Retro View^(TM) colonoscope and compare its ability to detect simulated polyps "hidden" behind colonic folds with that of a conventional colonoscope, utilizing anatomic colon models....AIM: To evaluate the new Retro View^(TM) colonoscope and compare its ability to detect simulated polyps "hidden" behind colonic folds with that of a conventional colonoscope, utilizing anatomic colon models.METHODS: Three anatomic colon models were prepared,with twelve simulated polyps "hidden" behind haustral folds and five placed in easily viewed locations in each model. Five blinded endoscopists examined two colon models in random order with the conventional or Retro View^(TM) colonoscope, utilizing standard withdrawal technique. The third colon model was then examined with the Retro View^(TM) colonoscope withdrawn initially in retroflexion and then in standard withdrawal. Polyp detection rates during standard and retroflexed withdrawal of the conventional and Retro View^(TM) colonoscopes were determined. Polyp detection rates for combined standard and retroflexed withdrawal(combination withdrawal) with the Retro View^(TM) colonoscope were also determined.RESULTS: For hidden polyps, retroflexed withdrawal using the Retro View^(TM) colonoscope detected more polyps than the conventional colonoscope in standard withdrawal(85% vs 12%, P = 0.0001). For hidden polyps, combination withdrawal with the Retro View^(TM) colonoscope detected more polyps than the conventional colonoscope in standard withdrawal(93% vs 12%, P ≤ 0.0001). The Retro View^(TM) colonoscope in "combination withdrawal" was superior to other methods in detecting all(hidden + easily visible) polyps, with successful detection of 80 of 85 polyps(94%) compared to 28(32%) polyps detected by the conventional colonoscope in standard withdrawal(P < 0.0001) and 67(79%) polyps detected by the Retro View^(TM) colonoscope in retroflexed withdrawal alone(P < 0.01). Continuous withdrawal of the colonoscope through the colon model while retroflexed was achieved by all endoscopists. In a post-test survey, four out of five colonoscopists reported that manipulation of the colonoscope was easy or very easy.CONCLUSION: In simulated testing, the Retro View^(TM) colonoscope increased detection of hidden polyps. Combining standard withdrawal with retroflexed withdrawal may become the new paradigm for "complete screening colonoscopy".展开更多
AIM: To investigate the benefits of hyoscine butylbromide in polyp detection during colonoscopy by a meta-analysis of available randomized controlled trials (RCTs).
AIM: To compare high resolution colonoscopy (Olympus Lucera) with a megapixel high resolution system (Pentax HiLine) as an in-service evaluation. METHODS: Polyp detection rates and measures of performance were c...AIM: To compare high resolution colonoscopy (Olympus Lucera) with a megapixel high resolution system (Pentax HiLine) as an in-service evaluation. METHODS: Polyp detection rates and measures of performance were collected for 269 colonoscopy procedures. Five colonoscopists conducted the study over a three month period, as part of the United Kingdom bowel cancer screening program. RESULTS:There were no differences in procedure duration (x^2 p = 0.98), caecal intubation rates (x^2 P = 0.67), or depth of sedation (x^2 P = 0.64). Mild discomfort was more common in the Pentax group (x^2 p = 0.036). Adenoma detection rate was significantly higher in the Pentax group (x^2 test for trend P = 0.01). Most of the extra polyps detected were flat or sessile adenomas. CONCLUSION: Megapixel definition colonoscopes improve adenoma detection without compromising other measures of endoscope performance. Increased polyp detection rates may improve future outcomes in bowel cancer screening programs.展开更多
AIM To investigate changes in polyp detection throughout fellowship training, and estimate colonoscopy volume required to achieve the adenoma detection rate(ADRs) and polyp detection rate(PDRs) of attending gastroente...AIM To investigate changes in polyp detection throughout fellowship training, and estimate colonoscopy volume required to achieve the adenoma detection rate(ADRs) and polyp detection rate(PDRs) of attending gastroenterologists.METHODS We reviewed colonoscopies from July 1, 2009 to June 30, 2014. Fellows' procedural logs were used to retrieve colonoscopy procedural volumes, and these were treated as the time variable. Findings from screening colonoscopies were used to calculate colonoscopy outcomes for each fellow for the prior 50 colonoscopies at each time point. ADR and PDR were plotted against colonoscopy procedural volumes to produce individual longitudinal graphs. Repeated measures linear mixed effects models were used to study the change of ADR and PDR with increasing procedural volume.RESULTS During the study period, 12 fellows completed full three years of training and were included in the analysis. The average ADR and PDR were, respectively, 31.5% and 41.9% for all fellows, and 28.9% and 38.2% for attendings alone. There was a statistically significant increase in ADR with increasing procedural volume(1.8%/100 colonoscopies, P = 0.002). Similarly, PDR increased 2.8%/100 colonoscopies(P = 0.0001), while there was no significant change in advanced ADR(0.04%/100 colonoscopies, P = 0.92). The ADR increase was limited to the right side of the colon, while the PDR increased in both the right and left colon. The adenoma per colon and polyp per colon also increased throughout training. Fellows reached the attendings' ADR and PDR after 265 and 292 colonoscopies, respectively.CONCLUSION We found that the ADR and PDR increase with increasing colonoscopy volume throughout fellowship. Our findings support recent recommendations of ≥ 275 colonoscopies for colonoscopy credentialing.展开更多
The incidence of colorectal cancer(CRC)in China has increased in recent years.The mortality rate of CRC has become one of the highest among all cancers;CRC increasingly affects the health and quality of people’s live...The incidence of colorectal cancer(CRC)in China has increased in recent years.The mortality rate of CRC has become one of the highest among all cancers;CRC increasingly affects the health and quality of people’s lives.However,due to the insufficiency of medical resources in China,the workload on medical doctors has further increased.In the past few decades,the adult CRC mortality and morbidity rate dropped sharply,mainly because of CRC screening and removal of adenomatous polyps.However,due to the differences in polyp itself and the skills of endoscopists,the detection rate of polyps varies greatly.In this paper,we adopt an anchor-free mechanism and introduce a better method to factorize the process of bounding box regression.Firstly,we regress the shape of object by the variant of Faster RCNN.Secondly,we re-define the target function of the location of object.The experimental result shows that our method achieves a mAP of 55.8%,which outperforms other state-of-the-art methods by at least 11.9%.This will greatly help to reduce the missed diagnosis of clinicians during endoscopy and treatment,and provide effective help for early diagnosis,early treatment and prevention of CRC.展开更多
AIM: To present a simple colonoscopy reporting system that can be checked easily the detection rate of colon polyps.METHODS: A simple colonoscopy reporting system Kosin Gastroenterology(KG quality reporting system) wa...AIM: To present a simple colonoscopy reporting system that can be checked easily the detection rate of colon polyps.METHODS: A simple colonoscopy reporting system Kosin Gastroenterology(KG quality reporting system) was developed. The polyp detection rate(PDR),adenoma detection rate(ADR),serrated polyp detection rate(SDR),and advanced adenoma detection rate(AADR) are easily calculated to use this system.RESULTS: In our gastroenterology center,the PDR,ADR,SDR,and AADR test results from each gastroenterologist were updated,every month. Between June 2014,when the program was started,and December 2014,the overall PDR and ADR in our center were 62.5% and 41.4%,respectively. And the overall SDR and AADR were 7.5% and 12.1%,respectively.CONCLUSION: We envision that KG quality reporting system can be applied to develop a comprehensive system to check colon polyp detection rates in other gastroenterology centers.展开更多
AIM: To assess the role of hyoscine for polyp detectionduring colonoscopy.METHODS: Studies(randomized controlled trials orRCTs) that compared the use of hyoscine vs no hyo-scine or placebo for polyp detection during c...AIM: To assess the role of hyoscine for polyp detectionduring colonoscopy.METHODS: Studies(randomized controlled trials orRCTs) that compared the use of hyoscine vs no hyo-scine or placebo for polyp detection during colonoscopywere included in our analysis. A search on multiple da-tabases was performed in September 2013 with searchterms being "hyoscine and colonoscopy", "hyoscineand polyp", "hyoscine and adenoma", "antispasmoticand colonoscopy", "antispasmotic and adenoma", and"antispasmotic and polyp". Jadad scoring was used toassess the quality of studies. The efficacy of hyoscinewas analyzed using Mantel-Haenszel model for polypand adenoma detection with odds ratio(OR). The I2measure of inconsistency was used to assess hetero-geneity(P < 0.05 or I2 > 50%). Statistical analysis was performed by RevMan 5.1. Funnel plots was used to assess publication bias.RESULTS: The search of the electronic databases identified 283 articles. Of these articles, eight published RCTs performed at various locations in Europe, Asia, and Australia were included in our meta-analysis, seven published as manuscripts and one published as an ab-stract(n = 2307). All the studies included patients with a hyoscine and a no hyoscine/placebo group and were of adequate quality(Jadad score ≥ 2). Eight RCTs as-sessed the polyp detection rate(PDR)(n = 2307). The use of hyoscine demonstrated no statistically significant difference as compared to no hyoscine or placebo for PDR(OR = 1.06; 95%CI: 0.89-1.25; P = 0.51). Five RCTs assessed the adenoma detection rate(ADR)(n = 2015). The use of hyoscine demonstrated no statisti-cally significant difference as compared to no hyoscine or placebo for ADR(OR = 1.12; 95%CI: 0.92-1.37; P = 0.25). Furthermore, the timing of hyoscine admin-istration(given at cecal intubation or pre-procedure) demonstrated no differences in PDR compared to no hyoscine or placebo. Publication bias or heterogeneity was not observed for any of the outcomes.CONCLUSION: Hyoscine use in patients undergoing colonoscopy does not appear to significantly increase the detection of polyps or adenomas.展开更多
To investigate whether adenoma and polyp detection rates (ADR and PDR, respectively) in screening colonoscopies performed in the presence of fellows differ from those performed by attending physicians alone. METHODSWe...To investigate whether adenoma and polyp detection rates (ADR and PDR, respectively) in screening colonoscopies performed in the presence of fellows differ from those performed by attending physicians alone. METHODSWe performed a retrospective review of all patients who underwent a screening colonoscopy at Grady Memorial Hospital between July 1, 2009 and June 30, 2015. Patients with a history of colon polyps or cancer and those with poor colon preparation or failed cecal intubation were excluded from the analysis. Associations of fellowship training level with the ADR and PDR relative to attendings alone were assessed using unconditional multivariable logistic regression. Models were adjusted for sex, age, race, and colon preparation quality. RESULTSA total of 7503 colonoscopies met the inclusion criteria and were included in the analysis. The mean age of the study patients was 58.2 years; 63.1% were women and 88.2% were African American. The ADR was higher in the fellow participation group overall compared to that in the attending group: 34.5% vs 30.7% (P = 0.001), and for third year fellows it was 35.4% vs 30.7% (aOR = 1.23, 95%CI: 1.09-1.39). The higher ADR in the fellow participation group was evident for both the right and left side of the colon. For the PDR the corresponding figures were 44.5% vs 40.1% (P = 0.0003) and 45.7% vs 40.1% (aOR = 1.25, 95%CI: 1.12-1.41). The ADR and PDR increased with increasing fellow training level (P for trend < 0.05). CONCLUSIONThere is a stepwise increase in ADR and PDR across the years of gastroenterology training. Fellow participation is associated with higher adenoma and polyp detection.展开更多
The goal of artificial intelligence in colonoscopy is to improve adenoma detection rate and reduce interval colorectal cancer.Artificial intelligence in polyp detection during colonoscopy has evolved tremendously over...The goal of artificial intelligence in colonoscopy is to improve adenoma detection rate and reduce interval colorectal cancer.Artificial intelligence in polyp detection during colonoscopy has evolved tremendously over the last decade mainly due to the implementation of neural networks.Computer aided detection(CADe)utilizing neural networks allows real time detection of polyps and adenomas.Current CADe systems are built in single centers by multidisciplinary teams and have only been utilized in limited clinical research studies.We review the most recent prospective randomized controlled trials here.These randomized control trials,both non-blinded and blinded,demonstrated increase in adenoma and polyp detection rates when endoscopists used CADe systems vs standard high definition colonoscopes.Increase of polyps and adenomas detected were mainly small and sessile in nature.CADe systems were found to be safe with little added time to the overall procedure.Results are promising as more CADe have shown to have ability to increase accuracy and improve quality of colonoscopy.Overall limitations included selection bias as all trials built and utilized different CADe developed at their own institutions,non-blinded arms,and question of external validity.展开更多
Up to a quarter of polyps and adenomas are missed during colonoscopy due to poor visualization behind folds and the inner curves of flexures, and the presence of flat lesions that are difficult to detect. These number...Up to a quarter of polyps and adenomas are missed during colonoscopy due to poor visualization behind folds and the inner curves of flexures, and the presence of flat lesions that are difficult to detect. These numbers may however be conservative because they mainly come from back-to-back studies performed with standard colonoscopes, which are unable to visualize the entire mucosal surface. In the past several years, new endoscopic techniques have been introduced to improve the detection of polyps and adenomas. The introduction of high definition colonoscopes and visual image enhancement technologies have been suggested to lead to better recognition of flat and small lesions, but the absolute increase in diagnostic yield seems limited. Cap assisted colonoscopy and water-exchange colonoscopy are methods to facilitate cecal intubation and increase patients comfort, but show only a marginal or no benefit on polyp and adenoma detection. Retroflexion is routinely used in the rectum for the inspection of the dentate line, but withdrawal in retroflexion in the colon is in general not recommended due to the risk of perforation. In contrast, colonoscopy with the Third-Eye Retroscope<sup>®</sup> may result in considerable lower miss rates compared to standard colonoscopy, but this technique is not practical in case of polypectomy and is more time consuming. The recently introduced Full Spectrum Endoscopy™ colonoscopes maintains the technical capabilities of standard colonoscopes and provides a much wider view of 330 degrees compared to the 170 degrees with standard colonoscopes. Remarkable lower adenoma miss rates with this new technique were recently demonstrated in the first randomized study. Nonetheless, more studies are required to determine the exact additional diagnostic yield in clinical practice. Optimizing the efficacy of colorectal cancer screening and surveillance requires high definition colonoscopes with improved virtual chromoendoscopy technology that visualize the whole colon mucosa while maintaining optimal washing, suction and therapeutic capabilities, and keeping the procedural time as low and patient discomfort as optimal as possible.展开更多
AIM: To determine the diagnostic yield of the “third eye retroscope”, on adenoma detection rate during screening colonoscopy.METHODS: The “third eye retroscope” when used with standard colonoscopy provides an ad...AIM: To determine the diagnostic yield of the “third eye retroscope”, on adenoma detection rate during screening colonoscopy.METHODS: The “third eye retroscope” when used with standard colonoscopy provides an additional retro-grade view to visualize lesions on the proximal aspects of folds and fexures. We searched MEDLINE (PubMed and Ovid), SCOPUS (including MEDLINE and EMBASE databases), Cochrane Database of Systemic Reviews, Google Scholar, and CINAHL Plus databases to identify studies that evaluated diagnostic yield of “third eye retroscope” during screening colonoscopy. DerSimonian Laird random effects model was used to generate the overall effect for each outcome. We evaluated statistical heterogeneity among the studies by using the Cochran Q statistic and quantifed by I2 statistics.RESULTS: Four distinct studies with a total of 920 pa-tients, mean age 59.83 (95%CI: 56.77-62.83) years, were included in the review. The additional adenoma detection rate (AADR) defined as the number of ad-ditional adenomas identified due to “third eye retro-scope” device in comparison to standard colonoscopy alone was 19.9% (95%CI: 7.3-43.9). AADR for right and left colon were 13.9% (95%CI: 9.4-20) and 10.7 (95%CI: 1.9-42), respectively. AADR for polyps ≥ 6 mm and ≥ 10 mm were 24.6% (95%CI: 16.6-34.9) and 24.2% (95%CI: 12.9-40.8), respectively. The ad-ditional polyp detection rate defined as the number of additional polyps identifed due to “third eye retro-scope” device in comparison to standard colonoscopyalone was 19.8% (95%CI: 7.9-41.8). There were no complications reported with use of “third eye retro-scope” device.CONCLUSION: The “third eye retroscope” device when used with standard colonoscopy is safe and de-tects 19.9% additional adenomas, compared to stan-dard colonoscopy alone.展开更多
文摘AIM: To retrospectively compare previous-day vs splitdose preparation in terms of bowel cleanliness and polyp detection in patients referred for polypectomy. METHODS: Fifty patients underwent two colonoscopies: one diagnostic in a private clinic and a second for polypectomy in a University Hospital. The latter procedures were performed within 12 wk of the index ones. Examinations were accomplished by two experienced endoscopists, different in each facility. Twenty-seven patients underwent screening/surveillance colonoscopy, while the rest were symptomatic. Previous day bowel preparation was utilized initially and splitdose for polypectomy. Colon cleansing was evaluated using the Aronchick scale. We measured the number of detected polyps, and the polyp miss rates per-polyp.RESULTS: Excellent/good preparation was reported in 38 cases with previous-day preparation(76%) vs 46 with split-dose(92%), respectively(P = 0.03). One hundred and twenty-six polyps were detected initially and 169 subsequently(P < 0.0001); 88 vs 126 polyps were diminutive(P < 0.0001), 25 vs 29 small(P = 0.048) and 13 vs 14 equal or larger than 10 mm. The miss rates for total, diminutive, small and large polyps were 25.4%, 30.1%, 13.7% and 6.6%, respectively. Multivariate analysis revealed that split-dose preparation was significantly associated(OR, P) with increased number of polyps detected overall(0.869, P < 0.001), in the right(0.418, P = 0.008) and in the left colon(0.452, P = 0.02). CONCLUSION: Split-dose preparation improved colon cleansing, enhanced polyp detection and unmasked significant polyp miss rates.
基金the National Key R&D Program of China,No.2018YFC1313103the National Natural Science Foundation of China,No.81670473 and No.81873546+1 种基金the“Shu Guang”Project of Shanghai Municipal Education Commission and Shanghai Education Development Foundation,No.19SG30the Key Area Research and Development Program of Guangdong Province,China,No.2018B010111001.
文摘BACKGROUND Artificial intelligence in colonoscopy is an emerging field,and its application may help colonoscopists improve inspection quality and reduce the rate of missed polyps and adenomas.Several deep learning-based computer-assisted detection(CADe)techniques were established from small single-center datasets,and unrepresentative learning materials might confine their application and generalization in wide practice.Although CADes have been reported to identify polyps in colonoscopic images and videos in real time,their diagnostic performance deserves to be further validated in clinical practice.AIM To train and test a CADe based on multicenter high-quality images of polyps and preliminarily validate it in clinical colonoscopies.METHODS With high-quality screening and labeling from 55 qualified colonoscopists,a dataset consisting of over 71000 images from 20 centers was used to train and test a deep learning-based CADe.In addition,the real-time diagnostic performance of CADe was tested frame by frame in 47 unaltered full-ranged videos that contained 86 histologically confirmed polyps.Finally,we conducted a selfcontrolled observational study to validate the diagnostic performance of CADe in real-world colonoscopy with the main outcome measure of polyps per colonoscopy in Changhai Hospital.RESULTS The CADe was able to identify polyps in the test dataset with 95.0%sensitivity and 99.1%specificity.For colonoscopy videos,all 86 polyps were detected with 92.2%sensitivity and 93.6%specificity in frame-by-frame analysis.In the prospective validation,the sensitivity of CAD in identifying polyps was 98.4%(185/188).Folds,reflections of light and fecal fluid were the main causes of false positives in both the test dataset and clinical colonoscopies.Colonoscopists can detect more polyps(0.90 vs 0.82,P<0.001)and adenomas(0.32 vs 0.30,P=0.045)with the aid of CADe,particularly polyps<5 mm and flat polyps(0.65 vs 0.57,P<0.001;0.74 vs 0.67,P=0.001,respectively).However,high efficacy is not realized in colonoscopies with inadequate bowel preparation and withdrawal time(P=0.32;P=0.16,respectively).CONCLUSION CADe is feasible in the clinical setting and might help endoscopists detect more polyps and adenomas,and further confirmation is warranted.
文摘AIM To assess the interendoscopist variability in the detection of colorectal polyps according to their location and histological type.METHODS This study was a retrospective analysis of prospectively collected data from a regional colorectal cancer(CRC) screening program; 2979 complete colonoscopies from 18 endoscopists were included. Variability in performance between endoscopists for detection of at least one adenoma(A), one proximal adenoma(PA), one distal adenoma(DA), and one proximal serrated polyp(PSP) was assessed by using multilevel logistic regression models.RESULTS The observed detection rates among the 18 endoscopists ranged from 24.6% to 47.6%(mean = 35.7%) for A, from 19.1% to 39.0%(mean = 29.4%) for DA, from 6.0% to 22.9%(mean = 12.4%) for PA, and from 1.3% to 19.3%(mean = 6.9%) for PSP.After adjusting for patient-level variables(sex, age), the interendoscopist detection rates variability achieved a significant level for A, PA, and PSP but not for DA(P = 0.03, P = 0.02, P = 0.02 and P = 0.08, respectively). This heterogeneity, as measured by the variance partition coefficient, was approximately threefold higher for PA(6.6%) compared with A(2.1%), and twofold higher for PSP(12.3%) compared with PA.CONCLUSION These results demonstrate significant interendoscopist variability for proximal polyp particularly for serrated p o l y p s, b u t n o t f o r d i s t a l a d e n o m a d e t e c t i o n. These findings contribute to explain the decreased effectiveness of complete colonoscopies at preventing proximal CRCs and the need to carefully assess the proximal colon during scope procedure.
基金Supported by Gastroenterology and Liver Diseases Research Center,Research Institute for Gastroenterology and Liver Diseases,Shahid Beheshti University of Medical Sciences,Tehran,Iran
文摘AIMTo identify the prevalence, and clinical and pathologic characteristic of colonic polyps among Iranian patients undergoing a comprehensive colonoscopy, and determine the polyp detection rate (PDR) and adenoma detection rate (ADR). METHODSIn this cross-sectional study, demographics and epidemiologic characteristics of 531 persons who underwent colonoscopies between 2014 and 2015 at Mehrad gastrointestinal clinic were determined. Demographics, indication for colonoscopy, colonoscopy findings, number of polyps, and histopathological characteristics of the polyps were examined for each person. RESULTSOur sample included 295 (55.6%) women and 236 (44.4%) men, with a mean age of 50.25 ± 14.89 years. Overall PDR was 23.5% (125/531). ADR and colorectal cancer detection rate in this study were 12.8% and 1.5%, respectively. Polyps were detected more significantly frequently in men than in women (52.8% vs 47.2%, P vs 56.4 years, P CONCLUSIONThe prevalence of polyps and adenomas in this study is less than that reported in the Western populations. In our patients, distal colon is more susceptible to developing polyps and cancer than proximal colon.
文摘AIM: To evaluate the new Retro View^(TM) colonoscope and compare its ability to detect simulated polyps "hidden" behind colonic folds with that of a conventional colonoscope, utilizing anatomic colon models.METHODS: Three anatomic colon models were prepared,with twelve simulated polyps "hidden" behind haustral folds and five placed in easily viewed locations in each model. Five blinded endoscopists examined two colon models in random order with the conventional or Retro View^(TM) colonoscope, utilizing standard withdrawal technique. The third colon model was then examined with the Retro View^(TM) colonoscope withdrawn initially in retroflexion and then in standard withdrawal. Polyp detection rates during standard and retroflexed withdrawal of the conventional and Retro View^(TM) colonoscopes were determined. Polyp detection rates for combined standard and retroflexed withdrawal(combination withdrawal) with the Retro View^(TM) colonoscope were also determined.RESULTS: For hidden polyps, retroflexed withdrawal using the Retro View^(TM) colonoscope detected more polyps than the conventional colonoscope in standard withdrawal(85% vs 12%, P = 0.0001). For hidden polyps, combination withdrawal with the Retro View^(TM) colonoscope detected more polyps than the conventional colonoscope in standard withdrawal(93% vs 12%, P ≤ 0.0001). The Retro View^(TM) colonoscope in "combination withdrawal" was superior to other methods in detecting all(hidden + easily visible) polyps, with successful detection of 80 of 85 polyps(94%) compared to 28(32%) polyps detected by the conventional colonoscope in standard withdrawal(P < 0.0001) and 67(79%) polyps detected by the Retro View^(TM) colonoscope in retroflexed withdrawal alone(P < 0.01). Continuous withdrawal of the colonoscope through the colon model while retroflexed was achieved by all endoscopists. In a post-test survey, four out of five colonoscopists reported that manipulation of the colonoscope was easy or very easy.CONCLUSION: In simulated testing, the Retro View^(TM) colonoscope increased detection of hidden polyps. Combining standard withdrawal with retroflexed withdrawal may become the new paradigm for "complete screening colonoscopy".
文摘AIM: To investigate the benefits of hyoscine butylbromide in polyp detection during colonoscopy by a meta-analysis of available randomized controlled trials (RCTs).
基金Supported by Proportion of UCLH/UCL funding from the Department of Health’s NIHR Biomedical Research Centres funding schemeA grant from the UCL experimental cancer medicine centreUnrestricted educational grant support from Pentax United Kingdom (Lovat LB)
文摘AIM: To compare high resolution colonoscopy (Olympus Lucera) with a megapixel high resolution system (Pentax HiLine) as an in-service evaluation. METHODS: Polyp detection rates and measures of performance were collected for 269 colonoscopy procedures. Five colonoscopists conducted the study over a three month period, as part of the United Kingdom bowel cancer screening program. RESULTS:There were no differences in procedure duration (x^2 p = 0.98), caecal intubation rates (x^2 P = 0.67), or depth of sedation (x^2 P = 0.64). Mild discomfort was more common in the Pentax group (x^2 p = 0.036). Adenoma detection rate was significantly higher in the Pentax group (x^2 test for trend P = 0.01). Most of the extra polyps detected were flat or sessile adenomas. CONCLUSION: Megapixel definition colonoscopes improve adenoma detection without compromising other measures of endoscope performance. Increased polyp detection rates may improve future outcomes in bowel cancer screening programs.
基金Supported by(in part) National Center for Advancing Translational Sciences of the National Institutes of Health,No.UL1TR000454
文摘AIM To investigate changes in polyp detection throughout fellowship training, and estimate colonoscopy volume required to achieve the adenoma detection rate(ADRs) and polyp detection rate(PDRs) of attending gastroenterologists.METHODS We reviewed colonoscopies from July 1, 2009 to June 30, 2014. Fellows' procedural logs were used to retrieve colonoscopy procedural volumes, and these were treated as the time variable. Findings from screening colonoscopies were used to calculate colonoscopy outcomes for each fellow for the prior 50 colonoscopies at each time point. ADR and PDR were plotted against colonoscopy procedural volumes to produce individual longitudinal graphs. Repeated measures linear mixed effects models were used to study the change of ADR and PDR with increasing procedural volume.RESULTS During the study period, 12 fellows completed full three years of training and were included in the analysis. The average ADR and PDR were, respectively, 31.5% and 41.9% for all fellows, and 28.9% and 38.2% for attendings alone. There was a statistically significant increase in ADR with increasing procedural volume(1.8%/100 colonoscopies, P = 0.002). Similarly, PDR increased 2.8%/100 colonoscopies(P = 0.0001), while there was no significant change in advanced ADR(0.04%/100 colonoscopies, P = 0.92). The ADR increase was limited to the right side of the colon, while the PDR increased in both the right and left colon. The adenoma per colon and polyp per colon also increased throughout training. Fellows reached the attendings' ADR and PDR after 265 and 292 colonoscopies, respectively.CONCLUSION We found that the ADR and PDR increase with increasing colonoscopy volume throughout fellowship. Our findings support recent recommendations of ≥ 275 colonoscopies for colonoscopy credentialing.
基金This research was supported in part by the National Natural Science Foundation of China under grants No.61602202 and 61603146the Natural Science Foundation of Jiangsu Province under contracts BK20160428 and BK20160427+2 种基金the Six talent peaks project in Jiangsu Province under contract XYDXX-034the Natural Science Foundation of Huaian under contract HAB201934the project in Jiangsu Association for science and technology.
文摘The incidence of colorectal cancer(CRC)in China has increased in recent years.The mortality rate of CRC has become one of the highest among all cancers;CRC increasingly affects the health and quality of people’s lives.However,due to the insufficiency of medical resources in China,the workload on medical doctors has further increased.In the past few decades,the adult CRC mortality and morbidity rate dropped sharply,mainly because of CRC screening and removal of adenomatous polyps.However,due to the differences in polyp itself and the skills of endoscopists,the detection rate of polyps varies greatly.In this paper,we adopt an anchor-free mechanism and introduce a better method to factorize the process of bounding box regression.Firstly,we regress the shape of object by the variant of Faster RCNN.Secondly,we re-define the target function of the location of object.The experimental result shows that our method achieves a mAP of 55.8%,which outperforms other state-of-the-art methods by at least 11.9%.This will greatly help to reduce the missed diagnosis of clinicians during endoscopy and treatment,and provide effective help for early diagnosis,early treatment and prevention of CRC.
文摘AIM: To present a simple colonoscopy reporting system that can be checked easily the detection rate of colon polyps.METHODS: A simple colonoscopy reporting system Kosin Gastroenterology(KG quality reporting system) was developed. The polyp detection rate(PDR),adenoma detection rate(ADR),serrated polyp detection rate(SDR),and advanced adenoma detection rate(AADR) are easily calculated to use this system.RESULTS: In our gastroenterology center,the PDR,ADR,SDR,and AADR test results from each gastroenterologist were updated,every month. Between June 2014,when the program was started,and December 2014,the overall PDR and ADR in our center were 62.5% and 41.4%,respectively. And the overall SDR and AADR were 7.5% and 12.1%,respectively.CONCLUSION: We envision that KG quality reporting system can be applied to develop a comprehensive system to check colon polyp detection rates in other gastroenterology centers.
文摘AIM: To assess the role of hyoscine for polyp detectionduring colonoscopy.METHODS: Studies(randomized controlled trials orRCTs) that compared the use of hyoscine vs no hyo-scine or placebo for polyp detection during colonoscopywere included in our analysis. A search on multiple da-tabases was performed in September 2013 with searchterms being "hyoscine and colonoscopy", "hyoscineand polyp", "hyoscine and adenoma", "antispasmoticand colonoscopy", "antispasmotic and adenoma", and"antispasmotic and polyp". Jadad scoring was used toassess the quality of studies. The efficacy of hyoscinewas analyzed using Mantel-Haenszel model for polypand adenoma detection with odds ratio(OR). The I2measure of inconsistency was used to assess hetero-geneity(P < 0.05 or I2 > 50%). Statistical analysis was performed by RevMan 5.1. Funnel plots was used to assess publication bias.RESULTS: The search of the electronic databases identified 283 articles. Of these articles, eight published RCTs performed at various locations in Europe, Asia, and Australia were included in our meta-analysis, seven published as manuscripts and one published as an ab-stract(n = 2307). All the studies included patients with a hyoscine and a no hyoscine/placebo group and were of adequate quality(Jadad score ≥ 2). Eight RCTs as-sessed the polyp detection rate(PDR)(n = 2307). The use of hyoscine demonstrated no statistically significant difference as compared to no hyoscine or placebo for PDR(OR = 1.06; 95%CI: 0.89-1.25; P = 0.51). Five RCTs assessed the adenoma detection rate(ADR)(n = 2015). The use of hyoscine demonstrated no statisti-cally significant difference as compared to no hyoscine or placebo for ADR(OR = 1.12; 95%CI: 0.92-1.37; P = 0.25). Furthermore, the timing of hyoscine admin-istration(given at cecal intubation or pre-procedure) demonstrated no differences in PDR compared to no hyoscine or placebo. Publication bias or heterogeneity was not observed for any of the outcomes.CONCLUSION: Hyoscine use in patients undergoing colonoscopy does not appear to significantly increase the detection of polyps or adenomas.
文摘To investigate whether adenoma and polyp detection rates (ADR and PDR, respectively) in screening colonoscopies performed in the presence of fellows differ from those performed by attending physicians alone. METHODSWe performed a retrospective review of all patients who underwent a screening colonoscopy at Grady Memorial Hospital between July 1, 2009 and June 30, 2015. Patients with a history of colon polyps or cancer and those with poor colon preparation or failed cecal intubation were excluded from the analysis. Associations of fellowship training level with the ADR and PDR relative to attendings alone were assessed using unconditional multivariable logistic regression. Models were adjusted for sex, age, race, and colon preparation quality. RESULTSA total of 7503 colonoscopies met the inclusion criteria and were included in the analysis. The mean age of the study patients was 58.2 years; 63.1% were women and 88.2% were African American. The ADR was higher in the fellow participation group overall compared to that in the attending group: 34.5% vs 30.7% (P = 0.001), and for third year fellows it was 35.4% vs 30.7% (aOR = 1.23, 95%CI: 1.09-1.39). The higher ADR in the fellow participation group was evident for both the right and left side of the colon. For the PDR the corresponding figures were 44.5% vs 40.1% (P = 0.0003) and 45.7% vs 40.1% (aOR = 1.25, 95%CI: 1.12-1.41). The ADR and PDR increased with increasing fellow training level (P for trend < 0.05). CONCLUSIONThere is a stepwise increase in ADR and PDR across the years of gastroenterology training. Fellow participation is associated with higher adenoma and polyp detection.
文摘The goal of artificial intelligence in colonoscopy is to improve adenoma detection rate and reduce interval colorectal cancer.Artificial intelligence in polyp detection during colonoscopy has evolved tremendously over the last decade mainly due to the implementation of neural networks.Computer aided detection(CADe)utilizing neural networks allows real time detection of polyps and adenomas.Current CADe systems are built in single centers by multidisciplinary teams and have only been utilized in limited clinical research studies.We review the most recent prospective randomized controlled trials here.These randomized control trials,both non-blinded and blinded,demonstrated increase in adenoma and polyp detection rates when endoscopists used CADe systems vs standard high definition colonoscopes.Increase of polyps and adenomas detected were mainly small and sessile in nature.CADe systems were found to be safe with little added time to the overall procedure.Results are promising as more CADe have shown to have ability to increase accuracy and improve quality of colonoscopy.Overall limitations included selection bias as all trials built and utilized different CADe developed at their own institutions,non-blinded arms,and question of external validity.
文摘Up to a quarter of polyps and adenomas are missed during colonoscopy due to poor visualization behind folds and the inner curves of flexures, and the presence of flat lesions that are difficult to detect. These numbers may however be conservative because they mainly come from back-to-back studies performed with standard colonoscopes, which are unable to visualize the entire mucosal surface. In the past several years, new endoscopic techniques have been introduced to improve the detection of polyps and adenomas. The introduction of high definition colonoscopes and visual image enhancement technologies have been suggested to lead to better recognition of flat and small lesions, but the absolute increase in diagnostic yield seems limited. Cap assisted colonoscopy and water-exchange colonoscopy are methods to facilitate cecal intubation and increase patients comfort, but show only a marginal or no benefit on polyp and adenoma detection. Retroflexion is routinely used in the rectum for the inspection of the dentate line, but withdrawal in retroflexion in the colon is in general not recommended due to the risk of perforation. In contrast, colonoscopy with the Third-Eye Retroscope<sup>®</sup> may result in considerable lower miss rates compared to standard colonoscopy, but this technique is not practical in case of polypectomy and is more time consuming. The recently introduced Full Spectrum Endoscopy™ colonoscopes maintains the technical capabilities of standard colonoscopes and provides a much wider view of 330 degrees compared to the 170 degrees with standard colonoscopes. Remarkable lower adenoma miss rates with this new technique were recently demonstrated in the first randomized study. Nonetheless, more studies are required to determine the exact additional diagnostic yield in clinical practice. Optimizing the efficacy of colorectal cancer screening and surveillance requires high definition colonoscopes with improved virtual chromoendoscopy technology that visualize the whole colon mucosa while maintaining optimal washing, suction and therapeutic capabilities, and keeping the procedural time as low and patient discomfort as optimal as possible.
文摘AIM: To determine the diagnostic yield of the “third eye retroscope”, on adenoma detection rate during screening colonoscopy.METHODS: The “third eye retroscope” when used with standard colonoscopy provides an additional retro-grade view to visualize lesions on the proximal aspects of folds and fexures. We searched MEDLINE (PubMed and Ovid), SCOPUS (including MEDLINE and EMBASE databases), Cochrane Database of Systemic Reviews, Google Scholar, and CINAHL Plus databases to identify studies that evaluated diagnostic yield of “third eye retroscope” during screening colonoscopy. DerSimonian Laird random effects model was used to generate the overall effect for each outcome. We evaluated statistical heterogeneity among the studies by using the Cochran Q statistic and quantifed by I2 statistics.RESULTS: Four distinct studies with a total of 920 pa-tients, mean age 59.83 (95%CI: 56.77-62.83) years, were included in the review. The additional adenoma detection rate (AADR) defined as the number of ad-ditional adenomas identified due to “third eye retro-scope” device in comparison to standard colonoscopy alone was 19.9% (95%CI: 7.3-43.9). AADR for right and left colon were 13.9% (95%CI: 9.4-20) and 10.7 (95%CI: 1.9-42), respectively. AADR for polyps ≥ 6 mm and ≥ 10 mm were 24.6% (95%CI: 16.6-34.9) and 24.2% (95%CI: 12.9-40.8), respectively. The ad-ditional polyp detection rate defined as the number of additional polyps identifed due to “third eye retro-scope” device in comparison to standard colonoscopyalone was 19.8% (95%CI: 7.9-41.8). There were no complications reported with use of “third eye retro-scope” device.CONCLUSION: The “third eye retroscope” device when used with standard colonoscopy is safe and de-tects 19.9% additional adenomas, compared to stan-dard colonoscopy alone.