A quantitative assessment of the risks and cost savings of forgoing histologic examination of diminutive polyps

Use of artificial intelligence to measure colorectal polyp size without a reference object

Background and study aims

Polyp size is crucial for determining colonoscopy surveillance intervals. We present an artificial intelligence (AI) model for colorectal polyp size measurement without a reference object.

Methods

The regression model for polyp size estimation was developed using outputs from two SegFormer models, segmentation and depth estimation. Initially built on colonoscopic images of polyp phantoms, the model underwent transfer learning with 1,304 real-world images. Testing was conducted on 178 images from 52 polyps, independent of the training set, using a snare as the ground truth for size comparison with the AI-based model. Polyps were classified into three size groups: ≤ 5 mm, 5-10 mm, and ≥ 10 mm. Error rates were calculated to evaluate discrepancies in actual size values between the AI model and the snare method. Precision indicated the positive predictive value per size group and recall and Bland-Altman were also conducted.

Results

The Bland-Altman analysis showed a mean bias of -0.03 mm between methods, with limits of agreement from -1.654 mm to 1.596 mm. AI model error rates for actual size discrepancies were 10.74%, 12.36%, and 9.89% for the ≤ 5 mm, 5-10 mm, and ≥ 10 mm groups, respectively, averaging 11.47%. Precision values were 0.870, 0.911, and 0.857, with overall recall of 0.846.

Conclusions

Our study shows that colorectal polyp size measurement by AI model is practical and clinically useful, exhibiting low error rates and high precision. AI shows promise as an accurate tool for measurement without the need for a reference object during screening colonoscopy.

Optical Polyp Diagnosis in the Era or Artificial Intelligence

The development of new image enhancement modalities and improved endoscopic imaging quality has not led to increased adoption of resect-and-discard in routine practice. Studies have shown that endoscopists have the capacity to achieve quality thresholds to perform optical diagnosis; however, this has not led to acceptance of optical diagnosis as a replacement for pathology for diminutive (1-5 mm) polyps. In recent years, artificial intelligence (AI)-based computer-assisted characterization of diminutive polyps has recently emerged as a strategy that could potentially represent a breakthrough technology to enable widespread adoption of resect-and-discard. Recent evidence suggests that pathology-based diagnosis is suboptimal, as polyp nonretrieval, fragmentation, sectioning errors, incorrect diagnosis as "normal mucosa," and interpathologist variability limit the efficacy of pathology for the diagnosis of 1-5 mm polyps. New paradigms in performing polyp diagnosis with or without AI have emerged to compete with pathology in terms of efficacy. Strategies, such as autonomous AI, AI-assisted human diagnosis, AI-unassisted human diagnosis, and combined strategies have been proposed as potential paradigms for resect-and-discard, although further research is still required to determine the optimal strategy. Implementation studies with high patient acceptance, where polyps are truly being discarded without histologic diagnosis, are paving the way toward normalizing resect-and-discard in routine clinical practice. Ultimately the largest challenges for computer-assisted characterization remain liability perceptions from endoscopists. The potential benefits of AI-based resect-and-discard are many, with very little potential harm. Real-world implementation studies are therefore required to pave the way for the acceptability of such strategies in routine practice.

Artificial Intelligence in Coloproctology: A Review of Emerging Technologies and Clinical Applications

Artificial intelligence (AI) has emerged as a transformative tool across several specialties, namely gastroenterology, where it has the potential to optimize both diagnosis and treatment as well as enhance patient care. Coloproctology, due to its highly prevalent pathologies and tremendous potential to cause significant mortality and morbidity, has drawn a lot of attention regarding AI applications. In fact, its application has yielded impressive outcomes in various domains, colonoscopy being one prominent example, where it aids in the detection of polyps and early signs of colorectal cancer with high accuracy and efficiency. With a less explored path but equivalent promise, AI-powered capsule endoscopy ensures accurate and time-efficient video readings, already detecting a wide spectrum of anomalies. High-resolution anoscopy is an area that has been growing in interest in recent years, with efforts being made to integrate AI. There are other areas, such as functional studies, that are currently in the early stages, but evidence is expected to emerge soon. According to the current state of research, AI is anticipated to empower gastroenterologists in the decision-making process, paving the way for a more precise approach to diagnosing and treating patients. This review aims to provide the state-of-the-art use of AI in coloproctology while also reflecting on future directions and perspectives.

Computer-Aided Diagnosis for Leaving Colorectal Polyps In Situ : A Systematic Review and Meta-analysis

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).

Evaluating the Efficacy of Resect-and-Discard and Resect-and-Retrieve Strategies for Diminutive Colonic Polyps

BACKGROUND AND OBJECTIVES

Diminutive polyps present a unique challenge in colorectal cancer (CRC) prevention strategies. This study aims to assess the characteristics and variables of diminutive polyps in a Romanian cohort, intending to develop a combined resect-and-retrieve or resect-and-discard strategy that reduces the need for an optical diagnosis.

MATERIALS AND METHODS

A prospective cohort study was conducted at two endoscopy centers in Romania from July to December 2021. Adult patients undergoing colonoscopies where polyps were identified and resected were included. Endoscopic procedures employed advanced diagnostic features, including blue-light imaging (BLI) and narrow-band imaging (NBI). Logistic regression analysis was utilized to determine factors impacting the probability of adenomatous polyps with high-grade dysplasia (HGD).

RESULTS

A total of 427 patients were included, with a mean age of 59.42 years (±11.19), predominantly male (60.2%). The most common indication for a colonoscopy was lower gastrointestinal symptoms (42.6%), followed by screening (28.8%). Adequate bowel preparation was achieved in 87.8% of cases. The logistic regression analysis revealed significant predictors of HGD in adenomatous polyps: age (OR = 1.05, 95% CI: 1.01-1.08, p = 0.01) and polyp size (>5 mm vs. ≤5 mm, OR = 4.4, 95% CI: 1.94-10.06, p < 0.001). Polyps classified as Paris IIa, Ip, and Isp were significantly more likely to harbor HGD compared to the reference group (Is), with odds ratios of 6.05, 3.68, and 2.7, respectively.

CONCLUSIONS

The study elucidates significant associations between the presence of HGD in adenomatous polyps and factors such as age, polyp size, and Paris classification. These findings support the feasibility of a tailored approach in the resect-and-discard and resect-and-retrieve strategies for diminutive polyps, potentially optimizing CRC prevention and intervention practices. Further research is warranted to validate these strategies in broader clinical settings.

A real-time deep learning-based system for colorectal polyp size estimation by white-light endoscopy: development and multicenter prospective validation

BACKGROUND

The choice of polypectomy device and surveillance intervals for colorectal polyps are primarily decided by polyp size. We developed a deep learning-based system (ENDOANGEL-CPS) to estimate colorectal polyp size in real time.

METHODS

ENDOANGEL-CPS calculates polyp size by estimating the distance from the endoscope lens to the polyp using the parameters of the lens. The depth estimator network was developed on 7297 images from five virtually produced colon videos and tested on 730 images from seven virtual colon videos. The performance of the system was first evaluated in nine videos of a simulated colon with polyps attached, then tested in 157 real-world prospective videos from three hospitals, with the outcomes compared with that of nine endoscopists over 69 videos. Inappropriate surveillance recommendations caused by incorrect estimation of polyp size were also analyzed.

RESULTS

The relative error of depth estimation was 11.3% (SD 6.0%) in successive virtual colon images. The concordance correlation coefficients (CCCs) between system estimation and ground truth were 0.89 and 0.93 in images of a simulated colon and multicenter videos of 157 polyps. The mean CCC of ENDOANGEL-CPS surpassed all endoscopists (0.89 vs. 0.41 [SD 0.29]; P<0.001). The relative accuracy of ENDOANGEL-CPS was significantly higher than that of endoscopists (89.9% vs. 54.7%; P<0.001). Regarding inappropriate surveillance recommendations, the system's error rate is also lower than that of endoscopists (1.5% vs. 16.6%; P<0.001).

CONCLUSIONS

ENDOANGEL-CPS could potentially improve the accuracy of colorectal polyp size measurements and size-based surveillance intervals.

Third Eye? The Assistance of Artificial Intelligence (AI) in the Endoscopy of Gastrointestinal Neoplasms

Gastrointestinal cancers are characterized by high incidence and mortality. However, there are well-established methods of screening. The endoscopy exam provides the macroscopical image and enables harvesting the tissue samples for further histopathological diagnosis. The efficiency of endoscopies relies not only on proper patient preparation, but also on the skills of the personnel conducting the exam. In recent years, a number of reports concerning the application of artificial intelligence (AI) in medicine have arisen. Numerous studies aimed to assess the utility of deep learning/ neural network systems supporting endoscopies. In this review, we summarized the most recent reports and randomized clinical trials regarding the application of AI in screening and surveillance of gastrointestinal cancers among patients suffering from esophageal, gastric, and colorectal cancer, along with the advantages, limitations, and controversies of those novel solutions.

The Utility of Narrow-Band Imaging International Colorectal Endoscopic Classification in Predicting the Histologies of Diminutive Colorectal Polyps Using I-Scan Optical Enhancement: A Prospective Study

(1) Background: This study aimed to evaluate the accuracy of predicting the histology of diminutive colonic polyps (DCPs) (≤5 mm) using i-scan optical enhancement (OE) based on the narrow-band imaging international colorectal endoscopic (NICE) classification. The study compared the diagnostic accuracy between experts who were already familiar with the NICE classification and trainees who were not, both before and after receiving brief training on the NICE classification. (2) Method: This prospective, single-center clinical trial was conducted at the Dong-A University Hospital from March 2020 to August 2020 and involved two groups of participants. The first group comprised two experienced endoscopists who were proficient in using i-scan OE and had received formal training in optical diagnosis and dye-less chromoendoscopy (DLC) techniques. The second group consisted of three endoscopists in the process of training in internal medicine at the Dong-A University Hospital. Each endoscopist examined the polyps and evaluated them using the NICE classification through i-scan OE. The results were not among the participants. Trained endoscopists were divided into pre- and post-training groups. (3) Results: During the study, a total of 259 DCPs were assessed using i-scan OE by the two expert endoscopists. They made real-time histological predictions according to the NICE classification criteria. For the trainee group, before training, the area under the receiver operating characteristic curves (AUROCs) for predicting histopathological results using i-scan OE were 0.791, 0.775, and 0.818. However, after receiving training, the AUROCs improved to 0.935, 0.949, and 0.963, which were not significantly different from the results achieved by the expert endoscopists. (4) Conclusions: This study highlights the potential of i-scan OE, along with the NICE classification, in predicting the histopathological results of DCPs during colonoscopy. In addition, this study suggests that even an endoscopist without experience in DLC can effectively use i-scan OE to improve diagnostic performance with only brief training.

Economic impact of implementing optical diagnosis with a "resect and discard" strategy within the English Bowel Cancer Screening Programme: findings from the DISCARD3 study

BACKGROUND AND AIMS

Advances in endoscopic technology, such as narrow-band imaging and high-definition colonoscopes, offer the potential for optical diagnosis (OD) with a "resect and discard" (RD) strategy for diminutive (≤5 mm) and small (6-9 mm) colorectal polyps. This could help alleviate the huge cost and time burden required for histopathology. The aim of this study was to conduct an economic analysis of an RD strategy within the English Bowel Cancer Screening Programme (BCSP).

METHODS

A decision tree was designed to compare an RD strategy with standard histopathology for patients included in the DISCARD3 study (Detect InSpect ChAracterise Resect and Discard 3) and was extrapolated to a national BCSP patient cohort.

RESULTS

Of the 525 patients in the DISCARD3 study, 354 were assessed for surveillance intervals (after excluding cases with colorectal cancer and at least 1 polyp >10 mm). Of 354 patients, 269 had polyps, of which 182 had only diminutive polyps, 77 had both small and diminutive polyps, and 10 had only small polyps. Surveillance interval concordance was 97.9% in patients with at least 1 diminutive polyp and 98.7% in patients with at least 1 diminutive or small polyp. In DISCARD3, an RD approach was found to reduce overall direct healthcare costs by $44,285.63 (-72.3%) for patients with diminutive polyps or by $66,129.13 (-75.0%) for patients with diminutive or small polyps. When extrapolated to the entire English BCSP, the annual savings were almost $3 million for patients with diminutive polyps or $4.3 million for patients with diminutive or small polyps, after adjusting for the costs of an OD quality assurance process.

CONCLUSIONS

OD with an RD strategy for diminutive and small polyps during BCSP colonoscopy would offer substantial cost savings without adversely affecting surveillance interval concordance.

Lipidomic Profiling of Colorectal Lesions for Real-Time Tissue Recognition and Risk-Stratification Using Rapid Evaporative Ionization Mass Spectrometry

OBJECTIVE

Rapid evaporative ionization mass spectrometry (REIMS) is a metabolomic technique analyzing tissue metabolites, which can be applied intraoperatively in real-time. The objective of this study was to profile the lipid composition of colorectal tissues using REIMS, assessing its accuracy for real-time tissue recognition and risk-stratification.

SUMMARY BACKGROUND DATA

Metabolic dysregulation is a hallmark feature of carcinogenesis; however, it remains unknown if this can be leveraged for real-time clinical applications in colorectal disease.

METHODS

Patients undergoing colorectal resection were included, with carcinoma, adenoma and paired-normal mucosa sampled. Ex vivo analysis with REIMS was conducted using monopolar diathermy, with the aerosol aspirated into a Xevo G2S QToF mass spectrometer. Negatively charged ions over 600 to 1000 m/z were used for univariate and multivariate functions including linear discriminant analysis.

RESULTS

A total of 161 patients were included, generating 1013 spectra. Unique lipidomic profiles exist for each tissue type, with REIMS differentiating samples of carcinoma, adenoma, and normal mucosa with 93.1% accuracy and 96.1% negative predictive value for carcinoma. Neoplasia (carcinoma or adenoma) could be predicted with 96.0% accuracy and 91.8% negative predictive value. Adenomas can be risk-stratified by grade of dysplasia with 93.5% accuracy, but not histological subtype. The structure of 61 lipid metabolites was identified, revealing that during colorectal carcinogenesis there is progressive increase in relative abundance of phosphatidylglycerols, sphingomyelins, and mono-unsaturated fatty acid-containing phospholipids.

CONCLUSIONS

The colorectal lipidome can be sampled by REIMS and leveraged for accurate real-time tissue recognition, in addition to riskstratification of colorectal adenomas. Unique lipidomic features associated with carcinogenesis are described.

Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice: the Artificial intelligence BLI Characterization (ABC) study

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 (≤ 5 mm) rectosigmoid polyps (DRSPs).

METHODS

Consecutive colonoscopy outpatients with ≥ 1 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 ≥ 90 % 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 (≥ 90 %; 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 92.3 %. The NPV of AI-assisted optical diagnosis for DRSPs (PIVI-1) was 91.0 % (95 %CI 87.1 %-93.9 %). The PIVI-2 threshold was met with 97.4 % (95 %CI 95.7 %-98.9 %) and 92.6 % (95 %CI 90.0 %-95.2 %) of patients according to ESGE and USMSTF, respectively. AI-assisted optical diagnosis accuracy was significantly lower for nonexperts (82.3 %, 95 %CI 76.4 %-87.3 %) than for experts (91.9 %, 95 %CI 88.5 %-94.5 %); 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.

What size cutoff level should be used to implement optical polyp diagnosis?

BACKGROUND : The risk of advanced pathology increases with polyp size, as does the potential for mismanagement when optical diagnosis is used. This study aimed to evaluate the proportion of patients who would be assigned inadequate surveillance intervals when different size cutoffs are adopted for use of optical diagnosis. METHODS : In a post hoc analysis of three prospective studies, the use of optical diagnosis was evaluated for three polyp size groups: 1-3, 1-5, and 1-10 mm. The primary outcome was the proportion of patients in whom advanced adenomas were found and optical diagnosis resulted in delayed surveillance. Secondary outcomes included agreements between surveillance intervals based on high confidence optical diagnosis and pathology outcomes, reduction in histopathological examinations, and proportion of patients who could receive an immediate surveillance recommendation. RESULTS : We included 3374 patients (7291 polyps ≤ 10 mm) undergoing complete colonoscopies (median age 66.0 years, 75.2 % male, 29.6 % for screening). The percentage of patients with advanced adenomas and either 2- or 7-year delayed surveillance intervals (n = 79) was 3.8 %, 15.2 %, and 25.3 % for size cutoffs of 1-3, 1-5, and 1-10 mm polyps, respectively (P < 0.001). Surveillance interval agreements between pathology and optical diagnosis for the three groups were 97.2 %, 95.5 %, and 94.2 %, respectively. Total reductions in pathology examinations for the three groups were 33.5 %, 62.3 %, and 78.2 %, respectively. CONCLUSION : A 3-mm cutoff for clinical implementation of optical diagnosis resulted in a very low risk of delayed management of advanced neoplasia while showing high surveillance interval agreement with pathology and a one-third reduction in overall requirement for pathology examinations.

The role of artificial intelligence based systems for cost optimization in colorectal cancer prevention programs

Colorectal Cancer (CRC) has seen a dramatic increase in incidence globally. In 2019, colorectal cancer accounted for 1.15 million deaths and 24.28 million disability-adjusted life-years (DALYs) worldwide. In India, the annual incidence rates (AARs) for colon cancer was 4.4 per 100,000. There has been a steady rise in the prevalence of CRC in India which may be attributed to urbanization, mass migration of population, westernization of diet and lifestyle practices and a rise of obesity and metabolic risk factors that place the population at a higher risk of CRC. Moreoever, CRC in India differs from that described in the Western countries, with a higher proportion of young patients and more patients presenting with an advanced stage. This may be due to poor access to specialized healthcare and socio-economic factors. Early identification of adenomatous colonic polyps, which are well-recognized pre-cancerous lesions, at the time of screening colonoscopy has been shown to be the most effective measure used for CRC prevention. However, colonic polyps are frequently missed during colonoscopy and moreover, these screening programs necessitate man-power, time and resources for processing resected polyps, that may hamper penetration and efficacy in mid- to low-income countries. In the last decade, there has been significant progress made in the automatic detection of colonic polyps by multiple AI-based systems. With the advent of better AI methodology, the focus has shifted from mere detection to accurate discrimination and diagnosis of colonic polyps. These systems, once validated, could usher in a new era in Colorectal Cancer (CRC) prevention programs which would center around "Leave in-situ" and "Resect and discard" strategies. These new strategies hinge around the specificity and accuracy of AI based systems in correctly identifying the pathological diagnosis of the polyps, thereby providing the endoscopist with real-time information in order to make a clinical decision of either leaving the lesion in-situ (mucosal polyps) or resecting and discarding the polyp (hyperplastic polyps). The major advantage of employing these strategies would be in cost optimization of CRC prevention programs while ensuring good clinical outcomes. The adoption of these AI-based systems in the national cancer prevention program of India in accordance with the mandate to increase technology integration could prove to be cost-effective and enable implementation of CRC prevention programs at the population level. This level of penetration could potentially reduce the incidence of CRC and improve patient survival by enabling early diagnosis and treatment. In this review, we will highlight key advancements made in the field of AI in the identification of polyps during colonoscopy and explore the role of AI based systems in cost optimization during the universal implementation of CRC prevention programs in the context of mid-income countries like India.

Comparison of blue laser imaging and narrow band imaging for the differentiation of diminutive colorectal polyps: A randomized controlled trial

BACKGROUND

To compare the diagnostic efficacy of blue laser imaging (BLI)- bright and narrow band imaging (NBI) modes of image enhanced endoscopy (IEE) in differentiating neoplastic and non-neoplastic lesions of diminutive colorectal polyps.

METHODS

We conducted a prospective randomized controlled trial from September 2015 to July 2016. The participants were randomly assigned (1:1) for colonoscopy with polyp classification under NBI or BLI-bright mode without magnification. Histopathologic diagnosis was used as the gold standard.

RESULTS

Three hundred and twenty-four diminutive polyps in 164 patients were included for analysis (BLI: 162 polyps in 73 patients, NBI: 162 polyps in 91 patients). These polyps were located at colon proximal to sigmoid (61.1 and 58.0%) and rectosigmoid colon (38.9 and 42.0%) in the BLI and NBI groups, respectively. Most polyps (71.9%) were adenomatous with one malignant polyp (0.3%). BLI achieved 86.4% accuracy, 98.3% sensitivity, 55.6% specificity, 85.2% positive predictive value (PPV), and 92.6% negative predictive value (NPV), similar to NBI which exhibited 90.1% accuracy, 99.1% sensitivity, 67.4% specificity, 88.5% PPV, and 96.9% NPV in the diagnosis of adenomatous polyps. Based on the location of the polyp, both modes of IEE provided ≥ 95% NPV for diagnosis of adenomatous polyps at the rectosigmoid colon.

CONCLUSIONS

BLI-bright and NBI modes of IEE have similar accuracy in differentiation between neoplastic and non-neoplastic lesions of diminutive polyps. Both modes provided ≥ 90% NPV which allows for the adaptation of the American Society of Gastrointestinal Endoscopy "diagnose-and-leave" recommended strategy for diminutive polyps at the rectosigmoid colon.

Factors influencing endoscopic estimation of colon polyp size in a colon model

BACKGROUND/AIMS

Colorectal polyps are removed to prevent progression to colorectal cancer. Polyp size is an important factor for risk stratification of malignant transformation. Endoscopic size estimation correlates poorly with pathological reports and several factors have been suggested to influence size estimation. We aimed to gain insight into the factors influencing endoscopic polyp size estimation.

METHODS

Images of polyps in an artificial model were obtained at 1, 3, and 5 cm from the colonoscope's tip. Participants were asked to estimate the diameter and volume of each polyp.

RESULTS

Fifteen endoscopists from three large-volume centers participated in this study. With an intraclass correlation coefficient of 0.66 (95% confidence interval [CI], 0.62-0.71) for diameter and 0.56 (95% CI, 0.50-0.62) for volume. Polyp size estimated at 3 cm from the colonoscope's tip yielded the best results. A lower distance between the tip and the polyp was associated with a larger estimated polyp size.

CONCLUSION

Correct endoscopic estimation of polyp size remains challenging. This finding can affect size estimation skills and future training programs for endoscopists.

CC-CLEAR (Colon Capsule Cleansing Assessment and Report): the novel scale to evaluate the clinical impact of bowel preparation in capsule colonoscopy - a multicentric validation study

BACKGROUND

Colon Capsule Cleansing Assessment and Report (CC-CLEAR) is a novel quantitative bowel preparation scale for colon capsule.

AIM

The aim of this study is to validate the association between CC-CLEAR's classification and major CC outcomes: lesion detection rate, surveillance recommendations and post-CC endoscopic treatment.

METHODS

Multicentric cohort of consecutive CCs. An expert's panel decided post-CC recommendations. Data included CC-CLEAR and Leighton-REX scales. Major CC outcomes were associated with the different cleansing grades.

RESULTS

From 168 CC's included, findings were reported in 123 (73.2%), 67 (54.4%) of those being colorectal polyps. CC-CLEAR influenced CC's lesion detection (OR 1.25 95% IC [1.07-1.46], p-value .004) and polyp detection rate (OR 1.22 95% IC [1.04-1.43], p-value.014). Thirty-two (19%) post-CC colonoscopies were recommended, including 22 (68.75%) with at least one polypectomy. CC-CLEAR was associated with post-CC colonoscopy treatment (OR 1.40 95% IC [1.07-1.84], p-value .015). Regarding surveillance, CC-CLEAR influenced the decision for immediate CC repetition (OR 0.21 95% IC [0.12-0.36], p-value < .001) and the recommendation for CC in 3-5 years' time (OR 1.47 95% IC [1.50-1.86], p-value < .002). The Leighton-Rex scale was not correlated with major CC outcomes.

CONCLUSION

CC-CLEAR impacts major CC outcomes: lesion detection, surveillance recommendations and post-CC endoscopic treatment.

Evaluation of the polyp-based resect and discard strategy: a retrospective study

BACKGROUND

Standard colonoscopy practice requires removal and histological characterization of almost all detected small (< 10 mm) and diminutive (≤ 5 mm) colorectal polyps. This study aimed to test a simplified polyp-based resect and discard (PBRD) strategy that assigns surveillance intervals based only on size and number of small/diminutive polyps, without the need for pathology examination.

METHODS

A post hoc analysis was performed on patients enrolled in a prospective study. The primary outcome was surveillance interval agreement of the PBRD strategy with pathology-based management according to 2020 US Multi-Society Task Force guidelines. Chart analysis also evaluated clinician adherence to pathology-based recommendations. One-sided testing was performed with a null-hypothesis of 90 % agreement with pathology-based surveillance intervals and a two-sided 96.7 % confidence interval (CI) using correction for multiple testing.

RESULTS

452 patients were included in the study. Surveillance intervals assigned using the PBRD strategy were correct in 97.8 % (96.7 %CI 96.3-99.3 %) of patients compared with pathology-based management. The PBRD strategy reduced pathology examinations by 58.7 % while providing 87.8 % of patients with immediate surveillance interval recommendations on the day of colonoscopy, compared with 47.1 % when using pathology-based management. Chart analysis of surveillance interval assignments showed 63.3 % adherence to pathology-based guidelines.

CONCLUSION

The PBRD strategy surpassed the 90 % agreement with the pathology-based standard for determining surveillance interval, reduced the need for pathology examinations, and increased the proportion of patients receiving immediate surveillance interval recommendations. The PBRD strategy does not require expertise in optical diagnosis and may replace histological characterization of small and diminutive colorectal polyps.

Artificial Intelligence-Based Assessment of Colorectal Polyp Histology by Elastic-Scattering Spectroscopy

BACKGROUND

Colonoscopic screening and surveillance for colorectal cancer could be made safer and more efficient if endoscopists could predict histology without the need to biopsy and perform histopathology on every polyp. Elastic-scattering spectroscopy (ESS), using fiberoptic probes integrated into standard biopsy tools, can assess, both in vivo and in real time, the scattering and absorption properties of tissue related to its underlying pathology.

AIMS

The objective of this study was to evaluate prospectively the potential of ESS to predict polyp pathology accurately.

METHODS

We obtained ESS measurements from patients undergoing screening/surveillance colonoscopy using an ESS fiberoptic probe integrated into biopsy forceps. The integrated forceps were used for tissue acquisition, following current standards of care, and optical measurement. All measurements were correlated to the index pathology. A machine learning model was then applied to measurements from 367 polyps in 169 patients to prospectively evaluate its predictive performance.

RESULTS

The model achieved sensitivity of 0.92, specificity of 0.87, negative predictive value (NPV) of 0.87, and high-confidence rate (HCR) of 0.84 for distinguishing 220 neoplastic polyps from 147 non-neoplastic polyps of all sizes. Among 138 neoplastic and 131 non-neoplastic polyps ≤ 5 mm, the model achieved sensitivity of 0.91, specificity of 0.88, NPV of 0.89, and HCR of 0.83.

CONCLUSIONS

Results show that ESS is a viable endoscopic platform for real-time polyp histology, particularly for polyps ≤ 5 mm. ESS is a simple, low-cost, clinically friendly, optical biopsy modality that, when interfaced with minimally obtrusive endoscopic tools, offers an attractive platform for in situ polyp assessment.

Pit pattern analysis of colorectal polyps using Storz professional image enhancement system (SPIES) endoscopy: A pilot study

Background:

Aim:

Materials and Methods:

Result:

Conclusion:

Definition of competence standards for optical diagnosis of diminutive colorectal polyps: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

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

Weakly Supervised Attention Map Training for Histological Localization of Colonoscopy Images

We consider the problem of training a convolutional neural network for histological localization of colorectal lesions from imperfectly annotated datasets. Given that we have a colonoscopic image dataset for 4-class histology classification and another dataset originally dedicated to polyp segmentation, we propose a weakly supervised learning approach to histological localization by training with the two different types of datasets. With the classification dataset, we first train a convolutional neural network to classify colonoscopic images into 4 different histology categories. By interpreting the trained classifier, we can extract an attention map corresponding to the predicted class for each colonoscopy image. We further improve the localization accuracy of attention maps by training the model to focus on lesions under the guidance of the polyp segmentation dataset. The experimental results show that the proposed approach simultaneously improves histology classification and lesion localization accuracy.

Guidance for setting easy-to-adopt competence criteria for optical diagnosis of diminutive colorectal polyps: a simulation approach

BACKGROUND AND AIMS

One reason the optical diagnosis strategy for diminutive colorectal polyps has not yet been implemented is that the current competence criteria (Preservation and Incorporation of Valuable Endoscopic Innovation [PIVI] initiative) are difficult to use in daily practice. To provide guidance for setting alternative easy-to-adopt competence criteria, we determined the lowest proportion of diminutive polyps that should have a correct optical diagnosis to meet the PIVI.

METHODS

For this simulation study, we used datasets from 2 prospectively collected cohorts of patients who underwent colonoscopy in either a primary colonoscopy or fecal immunochemical test (FIT) screening setting. In the simulation approach, virtual endoscopists or computer-aided diagnosis systems performed optical diagnosis of diminutive polyps with a fixed diagnostic performance level (strategy) on all individuals in the cohort who had ≥1 diminutive polyp. Strategies were defined by systematically varying the proportion of correct optical diagnoses for each polyp subtype (ie, adenomas, hyperplastic polyps, sessile serrated lesions). For each strategy, we determined whether PIVI-1 (≥90% agreement with U.S. or European Society for Gastrointestinal Endoscopy [ESGE] surveillance guidelines) and PIVI-2 (≥90% negative predictive value [NPV] for neoplastic lesions in the rectosigmoid) were met using Monte Carlo sampling with 1000 repetitions, with histology as reference.

RESULTS

The level of overall diagnostic accuracy to achieve the PIVI differed significantly depending on the clinical setting and guidelines used. In the colonoscopy screening setting, all diagnostic strategies in which 92% of all diminutive polyps (regardless of histology) were diagnosed correctly led to 90% or more agreement with U.S. surveillance intervals (ie, PIVI-1). For all diagnostic strategies in which ≥89% of all diminutive polyps were correctly diagnosed, at least 90% NPV was achieved (ie, PIVI-2). For the FIT screening setting, values were respectively ≥77% and ≥94%. When using ESGE guidelines, PIVI-1 was in both settings already met when 40% of all diminutive polyps were diagnosed correctly.

CONCLUSIONS

In contrast to the fixed PIVI criteria, our simulation study shows that different thresholds for the proportion of correctly diagnosed diminutive polyps lead to different clinical consequences depending on guidelines and clinical setting. However, this target proportion of diminutive colorectal polyps correctly diagnosed with optical diagnosis represents easier-to-adopt competence criteria.

Colorectal Polyp Image Detection and Classification through Grayscale Images and Deep Learning

Colonoscopy screening and colonoscopic polypectomy can decrease the incidence and mortality rate of colorectal cancer (CRC). The adenoma detection rate and accuracy of diagnosis of colorectal polyp which vary in different experienced endoscopists have impact on the colonoscopy protection effect of CRC. The work proposed a colorectal polyp image detection and classification system through grayscale images and deep learning. The system collected the data of CVC-Clinic and 1000 colorectal polyp images of Linkou Chang Gung Medical Hospital. The red-green-blue (RGB) images were transformed to 0 to 255 grayscale images. Polyp detection and classification were performed by convolutional neural network (CNN) model. Data for polyp detection was divided into five groups and tested by 5-fold validation. The accuracy of polyp detection was 95.1% for grayscale images which is higher than 94.1% for RGB and narrow-band images. The diagnostic accuracy, precision and recall rates were 82.8%, 82.5% and 95.2% for narrow-band images, respectively. The experimental results show that grayscale images achieve an equivalent or even higher accuracy of polyp detection than RGB images for lightweight computation. It is also found that the accuracy of polyp detection and classification is dramatically decrease when the size of polyp images small than 1600 pixels. It is recommended that clinicians could adjust the distance between the lens and polyps appropriately to enhance the system performance when conducting computer-assisted colorectal polyp analysis.

Optical diagnosis of colorectal polyps: a randomized controlled trial comparing endoscopic image-enhancing modalities

BACKGROUND AND AIMS

Optical polyp diagnosis using image-enhanced endoscopy (IEE) allows for real-time histology prediction of colorectal polyps. The aim of this study was to evaluate a recently introduced IEE modality (Optivista [OV]; Pentax Medical, Tokyo, Japan) in a randomized controlled trial.

METHODS

In a prospective cohort of subjects (ages 45-80 years) undergoing elective screening, surveillance, or diagnostic colonoscopy, all colorectal polyps between 1 and 5 mm underwent IEE assessment. Study subjects were randomized before their colonoscopy procedure to undergo optical polyp diagnosis using either OV IEE or iScan (IS) IEE. A validated IEE scale (NBI International Colorectal Endoscopic classification) was used for optical polyp diagnosis. The primary outcome was the agreement of surveillance intervals determined when using OV IEE compared with IS IEE in reference with pathology-based surveillance intervals. Secondary outcomes were the percentage of surveillance intervals that could be given on the same day as the procedure, percentage of pathology tests avoided, diagnostic performance, and negative predictive value (NPV) of optical diagnosis for rectosigmoid adenomas.

RESULTS

Four hundred ten patients were enrolled in the trial. The polyp detection rate was 58.6%, and the adenoma detection rate was 38.8%. The proportion of correct surveillance interval assignment when using OV or IS IEE was 96.5% versus 96.0% (P = .75). A total of 65.1% of patients could be given same-day surveillance intervals when using OV IEE versus 73.1% for IS IEE (P = .07). The NPV for rectosigmoid adenomas (including sessile serrated adenomas) was 97.5% when using OV IEE and 88.2% when using IS IEE. Using high-confidence optical diagnosis instead of pathology would have resulted in a 44.3% elimination of required pathology examinations for OV IEE versus 52.8% for IS IEE (P = .34).

CONCLUSIONS

Optical diagnosis using OV and IS IEE both surpassed the 90% benchmark of surveillance interval assignment, and no significant difference with regard to correct surveillance interval assignment was found. OV IEE surpassed the ≥90% NPV for rectosigmoid adenomas, whereas IS IEE did not. (Clinical trial registration number: NCT03515343.).

Real-time artificial intelligence-based histologic classification of colorectal polyps with augmented visualization

BACKGROUND AND AIMS

Artificial intelligence (AI)-based computer-aided diagnostic (CADx) algorithms are a promising approach for real-time histology (RTH) of colonic polyps. Our aim is to present a novel in situ CADx approach that seeks to increase transparency and interpretability of results by generating an intuitive augmented visualization of the model's predicted histology over the polyp surface.

METHODS

We developed a deep learning model using semantic segmentation to delineate polyp boundaries and a deep learning model to classify subregions within the segmented polyp. These subregions were classified independently and were subsequently aggregated to generate a histology map of the polyp's surface. We used 740 high-magnification narrow-band images from 607 polyps in 286 patients and over 65,000 subregions to train and validate the model.

RESULTS

The model achieved a sensitivity of .96, specificity of .84, negative predictive value (NPV) of .91, and high-confidence rate (HCR) of .88, distinguishing 171 neoplastic polyps from 83 non-neoplastic polyps of all sizes. Among 93 neoplastic and 75 non-neoplastic polyps ≤5 mm, the model achieved a sensitivity of .95, specificity of .84, NPV of .91, and HCR of .86.

CONCLUSIONS

The CADx model is capable of accurately distinguishing neoplastic from non-neoplastic polyps and provides a histology map of the spatial distribution of localized histologic predictions along the delineated polyp surface. This capability may improve interpretability and transparency of AI-based RTH and offer intuitive, accurate, and user-friendly guidance in real time for the clinical management and documentation of optical histology results.

Colorectal polyp characterization with standard endoscopy: Will Artificial Intelligence succeed where human eyes failed?

The American Society for Gastrointestinal Endoscopy (ASGE) has proposed the "resect-and-discard" and "diagnose-and-leave" strategies for diminutive colorectal polyps to reduce the costs of unnecessary polyp resection and pathology evaluation. However, the diagnostic thresholds set by these guidelines are not always met in community practice. To overcome this sub-optimal performance, artificial intelligence (AI) has been applied to the field of endoscopy. The incorporation of deep learning algorithms with AI models resulted in highly accurate systems that match the expert endoscopists' optical biopsy and exceed the ASGE recommended thresholds. Recent studies have demonstrated that the integration of AI in clinical practice results in significant improvement in endoscopists' diagnostic accuracy while reducing the time to make a diagnosis. Yet, several points need to be addressed before AI models can be successfully implemented in clinical practice. In this review, we summarize the recent literature on the application of AI for characterization of colorectal polyps, and review the current limitation and future directions for this field.

Correlation between ADR of screening and all colonoscopies

BACKGROUND AND AIMS

Colonoscopy with polypectomy are associated with a reduction in the incidence of colorectal cancer (CRC), as well as mortality, secondary to CRC. Because of the variation in physicians' performance and the risk of interval CRC after a colonoscopy, several quality indicators have been established. ADR (adenoma detection rate) is a generally accepted quality indicator. But it is also a target of possible gaming and achieving an adequate number of colonoscopies only from screening may be a problem for some practices. The aim of this study was to compare ADR for colonoscopies done for various indications and to look for correlations between the ADR of screening and all examinations.

METHODS

We retrospectively assessed the quality indicators of all colonoscopies performed in a nonuniversity hospital, Frydek-Mistek, from January 2013 to December 2017. We calculated the ADR for all colonoscopies in patients over 50 years of age (subdivided into screening, surveillance, diagnostic) and separately only for screening colonoscopies. Correlations were made using the Pearson's correlation coeficient.

RESULTS

The sample was composed of 6925 patients over 50 years of age (3620 men, 3305 women, mean age 66.2 years). The ADRs for screening and surveillance were higher than for diagnostic colonoscopies for all of the endoscopists, and the ADRs for all colonoscopies were lower than for screening, but sufficiently over 25%. There was a positive correlation between the ADR of screening and all colonoscopies (r=0.906, P<0.005).

CONCLUSIONS

The calculation of ADR for all colonoscopies was possible in our endoscopic department, and there was a positive correlation with ADR for screening colonoscopies. ADR for all colonoscopies is a good tool for calculating real ADR from large sample sizes without gaming.

TRIAL REGISTRATION

ClinicalTrials.gov (NCT03730441).

Curriculum for optical diagnosis training in Europe: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

This manuscript represents an official Position Statement of the European Society of Gastrointestinal Endoscopy (ESGE) aiming to guide general gastroenterologists to develop and maintain skills in optical diagnosis during endoscopy. In general, this requires additional training beyond the core curriculum currently provided in each country. In this context, ESGE have developed a European core curriculum for optical diagnosis practice across Europe for high quality optical diagnosis training. 1:  ESGE suggests that every endoscopist should have achieved general competence in upper and/or lower gastrointestinal (UGI/LGI) endoscopy before commencing training in optical diagnosis of the UGI/LGI tract, meaning personal experience of at least 300 UGI and/or 300 LGI endoscopies and meeting the ESGE quality measures for UGI/LGI endoscopy. ESGE suggests that every endoscopist should be able and competent to perform UGI/LGI endoscopy with high definition white light combined with virtual and/or dye-based chromoendoscopy before commencing training in optical diagnosis. 2:  ESGE suggests competency in optical diagnosis can be learned by attending a validated optical diagnosis training course based on a validated classification, and self-learning with a minimum number of lesions. If no validated training course is available, optical diagnosis can only be learned by attending a non-validated onsite training course and self-learning with a minimum number of lesions. 3:  ESGE suggests endoscopists are competent in optical diagnosis after meeting the pre-adoption and learning criteria, and meeting competence thresholds by assessing a minimum number of lesions prospectively during real-time endoscopy. ESGE suggests ongoing in vivo practice by endoscopists to maintain competence in optical diagnosis. If a competent endoscopist does not perform in vivo optical diagnosis on a regular basis, ESGE suggests repeating the learning and competence phases to maintain competence.Key areas of interest were optical diagnosis training in Barrett's esophagus, esophageal squamous cell carcinoma, early gastric cancer, diminutive colorectal lesions, early colorectal cancer, and neoplasia in inflammatory bowel disease. Condition-specific recommendations are provided in the main document.

Cost savings in colonoscopy with artificial intelligence-aided polyp diagnosis: an add-on analysis of a clinical trial (with video)

BACKGROUND AND AIMS

Artificial intelligence (AI) is being implemented in colonoscopy practice, but no study has investigated whether AI is cost saving. We aimed to quantify the cost reduction using AI as an aid in the optical diagnosis of colorectal polyps.

METHODS

This study is an add-on analysis of a clinical trial that investigated the performance of AI for differentiating colorectal polyps (ie, neoplastic versus non-neoplastic). We included all patients with diminutive (≤5 mm) rectosigmoid polyps in the analyses. The average colonoscopy cost was compared for 2 scenarios: (1) a diagnose-and-leave strategy supported by the AI prediction (ie, diminutive rectosigmoid polyps were not removed when predicted as non-neoplastic), and (2) a resect-all-polyps strategy. Gross annual costs for colonoscopies were also calculated based on the number and reimbursement of colonoscopies conducted under public health insurances in 4 countries.

RESULTS

Overall, 207 patients with 250 diminutive rectosigmoid polyps (104 neoplastic, 144 non-neoplastic, and 2 indeterminate) were included. AI correctly differentiated neoplastic polyps with 93.3% sensitivity, 95.2% specificity, and 95.2% negative predictive value. Thus, 105 polyps were removed and 145 were left under the diagnose-and-leave strategy, which was estimated to reduce the average colonoscopy cost and the gross annual reimbursement for colonoscopies by 18.9% and US$149.2 million in Japan, 6.9% and US$12.3 million in England, 7.6% and US$1.1 million in Norway, and 10.9% and US$85.2 million in the United States, respectively, compared with the resect-all-polyps strategy.

CONCLUSIONS

The use of AI to enable the diagnose-and-leave strategy results in substantial cost reductions for colonoscopy.

Uptake and barriers for implementation of the resect and discard strategy: an international survey

Background and study aims  Optical real-time diagnosis (= resect-and-discard strategy) is an alternative to histopathology for diminutive colorectal polyps. However, clinical adoption of this approach seems sparse. We were interested in evaluating potential clinical uptake and barriers for implementation of this approach. Methods  We conducted an international survey using the "Google forms" platform. Nine endoscopy societies distributed the survey. Survey questions measured current clinical uptake and barriers for implementing the resect-and-discard strategy , perceived cancer risk associated with diminutive polyps and potential concerns with using CT-colonography as follow-up, as well as non-resection of diminutive polyps. Results  Eight hundred and eight endoscopists participated in the survey. 84.2 % (95 % CI 81.6 %-86.7 %) of endoscopists are currently not using the resect-and-discard strategy and 59.9 % (95 % CI 56.5 %-63.2 %) do not believe that the resect-and-discard strategy is feasible for implementation in its current form. European (38.5 %) and Asian (45 %) endoscopists had the highest rates of resect-and-discard practice, while Canadian (13.8 %) and American (5.1 %) endoscopists had some of the lowest implementation rates. 80.3 % (95 % CI 77.5 %-83.0 %) of endoscopists believe that using the resect-and-discard strategy for diminutive polyps will not increase cancer risk. 48.4 % (95 % CI 45.0 %-51.9 %) of endoscopists believe that leaving diminutive polyps in place is associated with increased cancer risk. This proportion was slightly higher (54.7 %; 95 % CI 53.6 %-60.4 %) when asked if current CT-colonography screening practice might increase cancer risks. Conclusion  Clinical uptake of resect-and-discard is very low. Most endoscopists believe that resect-and-discard is not feasible for clinical implementation in its current form. The most important barriers for implementation are fear of making an incorrect diagnosis, assigning incorrect surveillance intervals and medico-legal consequences.

Feasibility of using narrow band imaging international colorectal endoscopic classification for diagnosing colorectal neoplasia in China: A multicenter pilot observational study

OBJECTIVE

We aimed to investigate whether Chinese endoscopists without narrow-band imaging (NBI) experiences could achieve high accuracy in the real-time diagnosis of colorectal polyps using NBI International Colorectal Endoscopic (NICE) classification after web-based training.

METHODS

Altogether 15 endoscopists from five centers with no NBI experiences followed a short, web-based training program on the NICE classification and took web-based test. Their performances were compared with 15 matched experienced endoscopists with no NBI experience who received no NBI training. These 15 trained endoscopists then made real-time diagnoses of colorectal neoplasia. A logistic regression was used to assess potential predictors of diagnostic performance.

RESULTS

Compared with those who received no training, trained endoscopists achieved comparable overall accuracy (85.3% vs 83.1%, P = 0.408) and accuracy at a high-confidence level (87.0% vs 86.0%, P = 0.670), but had a higher confidence rate (86.1% vs 83.7%, P = 0.004) for the diagnosis of neoplasia. Real-time diagnostic accuracy, sensitivity and specificity were 94.3% (95% confidence interval [CI] 91.5%-96.2%), 96.2% (95% CI 93.4%-97.9%) and 85.3% (95% CI 74.8%-92.1%) at high-confidence level. The high-confidence level was the strongest predictor of real-time diagnostic accuracy (odds ratio 12.66, P < 0.001).

CONCLUSIONS

Web-based training can improve the confidence level of endoscopists in accurately diagnosing colorectal polyps using the NICE classification. Chinese endoscopists can achieve high accuracy in diagnosing colorectal neoplasia at a high confidence level (ClinicalTrials ID: NCT02033980).

Advanced Endoscopic Imaging in Colonic Neoplasia

BACKGROUND

Endoscopic imaging is a rapidly evolving field with a constant influx of new concepts and technologies. Since the introduction of video endoscopy and subsequently high-definition imaging as the first revolutions in gastrointestinal endoscopy, several technologies of virtual chromoendoscopy have been developed and brought to the market in the past decade, which have shaped and revolutionized for a second time our approach to endoscopic imaging. In parallel to these developments, microscopic imaging technologies, such as endomicroscopy and endocytoscopy, allow us to examine single cells within the mucosa in real time, thereby enabling histological diagnoses during ongoing endoscopy.

SUMMARY

In this review, we provide an overview on the technical background of different technologies of advanced endoscopic imaging, and then review and discuss their role and applications for the diagnosis and management of colorectal neoplasms as well as limitations and challenges that exist despite all technological improvements.

KEY MESSAGES

Technologies of advanced endoscopic imaging have profound impact not only on our imaging capabilities, they are also about to fundamentally change our approach to managing lesions in the gastrointestinal tract: not every lesion found during colonoscopy has to be excised or sent for histopathologic evaluation. However, before this becomes widespread reality, major obstacles such as patient acceptance, adoption by less trained endoscopists, and also legal aspects need to carefully addressed. The development of computer-aided diagnosis and artificial intelligence algorithms hold the potential to overcome the obstacles associated with the concept of optical biopsy and will most likely fundamentally facilitate, shape, and change decision making in the management of colorectal lesions.

Artificial Intelligence for the Determination of a Management Strategy for Diminutive Colorectal Polyps: Hype, Hope, or Help

Most colorectal polyps are diminutive, and malignant potential for these polyps is uncommon, especially for those in the rectosigmoid. However, many diminutive polyps are still being resected to determine whether these are adenomas or serrated/hyperplastic polyps. Resecting all the diminutive polyps is not cost-effective. Therefore, gastroenterologists have proposed optical diagnosis using image-enhanced endoscopy for polyp characterization. These technologies have achieved favorable outcomes, but are not widely available. Artificial intelligence has been used in clinical medicine to classify lesions. Here, artificial intelligence technology for the characterization of colorectal polyps is discussed in a decision-making context regarding diminutive colorectal polyps.

Improved Real-Time Optical Diagnosis of Colorectal Polyps Following a Comprehensive Training Program

BACKGROUND & AIMS

The optimal training method for endoscopic characterization of colorectal polyps using narrow-band imaging is uncertain, and sessile serrated lesions (SSLs) optical diagnosis data are lacking. We aimed to evaluate a comprehensive training program for real-time optical diagnosis of colorectal polyps, including SSLs.

METHODS

We performed a single-institution prospective study of 15 endoscopists trained with the Workgroup Serrated Polyps and Polyposis classification system. After the first phase of in vivo optical diagnosis, their performances were evaluated. After re-education for insufficient competency, they began the second phase. The learning curves and performance on 2 preservation and incorporation of valuable endoscopic innovations benchmarks were assessed.

RESULTS

A total of 7294 polyps, including 486 SSLs, were diagnosed in real-time. The overall accuracy improved from 73.5% in the first phase to 77.1% in the second. The accuracy with high confidence was 79.4% and 85.1% in the first and second phases, respectively. In the first and second phases, the negative predictive values for diminutive neoplastic polyps were 82.1% and 92.5%, respectively, and concordances of the surveillance intervals were 80.7% and 89.7%, respectively. Eight endoscopists achieved the preservation and incorporation of valuable endoscopic innovations benchmarks after the second phase compared with none after the first. In contrast, the high confidence rate decreased from 74.6% to 70.2% as training progressed.

CONCLUSION

A comprehensive training program for real-time optical diagnosis significantly improved performance and reduced individual variability in less-experienced endoscopists. ClinicalTrials.gov no: NCT02516748.

An Integrated Approach for Efficient Multi-Omics Joint Analysis

The challenges associated with multi-omics analysis, e.g. DNA-seq, RNA-seq, metabolomics, methylomics and microbiomics domains, include: (1) increased high-dimensionality, as all -omics domains include ten thousands to hundreds of thousands of variables each; (2) increased complexity in analyzing domain-domain interactions, quadratic for pairwise correlation, and exponential for higher-order interactions; (3) variable heterogeneity, with highly skewed distributions in different units and scales for methylation and microbiome. Here, we developed an efficient strategy for joint-domain analysis, applying it to an analysis of correlations between colon epithelium methylomics and fecal microbiomics data with colorectal cancer risk as estimated by colorectal polyp prevalence. First, we applied domain-specific standard pipelines for quality assessment, cleaning, batch-effect removal, et cetera. Second, we performed variable homogenization for both the methylation and microbiome data sets, using domain-specific normalization and dimension reduction, obtaining scale-free variables that could be compared across the two domains. Finally, we implemented a joint-domain network analysis to identify relevant microbial-methylation island patterns. The network analysis considered all possible species-island pairs, thus being quadratic in its complexity. However, we were able to pre-select the unpaired variables by performing a preliminary association analysis on the outcome polyp prevalence. All results from association and interaction analyses were adjusted for multiple comparisons. Although the limited sample size did not provide good power (80% to detect medium to large effect sizes with 5% alpha error), a number of potentially significant association (dozens in the uncorrected analysis, reducing to just a few in the corrected one) were identified As a last step, we linked the network patterns identified by our approach to the KEGG functional ontology, showing that the method can generate new mechanistic hypotheses for the biological causes of polyp development.

Best Practices for Resection of Diminutive and Small Polyps in the Colorectum

Diminutive colorectal lesions are polyps and flat lesions 1 to 5 mm in size, and small are 6 to 9 mm in size. The best resection method is the cold snare. Cold forceps are acceptable for 1- to 3-mm lesions, but should not be used to piecemeal polyps. Cold snaring has few complications and is more effective than cold forceps for 4- to 5-mm polyps and as effective and more efficient than hot snaring for 6- to 9-mm polyps.

Contrast of nuclei in stratified squamous epithelium in optical coherence tomography images at 800 nm

Imaging nuclei of keratinocytes in the stratified squamous epithelium has been a subject of intense research since nucleus associated cellular atypia is the key criteria for the screening and diagnosis of epithelial cancers and their precursors. However, keratinocyte nuclei have been reported to be either low scattering or high scattering, so that these inconsistent reports might have led to misinterpretations of optical images, and more importantly, hindered the establishment of optical diagnostic criteria. We disclose that they are generally low scattering in the core using Micro-optical coherence tomography (μOCT) of 1.28-μm axial resolution in vivo; those previously reported "high scattering" or "bright" signals from nuclei are likely from the nucleocytoplasmic boundary, and the low-scattering nuclear cores were missed possibly due to insufficient axial resolutions (~4μm). It is further demonstrated that the high scattering signals may be associated with flattening of nuclei and cytoplasmic glycogen accumulation, which are valuable cytologic hallmarks of cell maturation.

Optical Technologies for Endoscopic Real-Time Histologic Assessment of Colorectal Polyps: A Meta-Analysis

OBJECTIVES

Accurate, real-time, endoscopic risk stratification of colorectal polyps would improve decision-making and optimize clinical efficiency. Technologies to manipulate endoscopic optical outputs can be used to predict polyp histology in vivo; however, it remains unclear how accuracy has progressed and whether it is sufficient for routine clinical implementation.

METHODS

A meta-analysis was conducted by searching MEDLINE, Embase, and the Cochrane Library. Studies were included if they prospectively deployed an endoscopic optical technology for real-time in vivo prediction of adenomatous colorectal polyps. Polyposis and inflammatory bowel diseases were excluded. Bayesian bivariate meta-analysis was performed, presenting 95% confidence intervals (CI).

RESULTS

One hundred two studies using optical technologies on 33,123 colorectal polyps were included. Digital chromoendoscopy differentiated neoplasia (adenoma and adenocarcinoma) from benign polyps with sensitivity of 92.2% (90.6%-93.9% CI) and specificity of 84.0% (81.5%-86.3% CI), with no difference between constituent technologies (narrow-band imaging, Fuji intelligent Chromo Endoscopy, iSCAN) or with only diminutive polyps. Dye chromoendoscopy had sensitivity of 92.7% (90.1%-94.9% CI) and specificity of 86.6% (82.9%-89.9% CI), similarly unchanged for diminutive polyps. Spectral analysis of autofluorescence had sensitivity of 94.4% (84.0%-99.1% CI) and specificity of 50.9% (13.2%-88.8% CI). Endomicroscopy had sensitivity of 93.6% (85.3%-98.3% CI) and specificity of 92.5% (81.8%-98.1% CI). Computer-aided diagnosis had sensitivity of 88.9% (74.2%-96.7% CI) and specificity of 80.4% (52.6%-95.7% CI). Prediction confidence and endoscopist experience alone did not significantly improve any technology. The only subgroup to demonstrate a negative predictive value for adenoma above 90% was digital chromoendoscopy, making high confidence predictions of diminutive recto-sigmoid polyps. Chronologic meta-analyses show a falling negative predictive value over time. A significant publication bias exists.

DISCUSSION

This novel approach to meta-analysis demonstrates that existing optical technologies are increasingly unlikely to allow safe "resect and discard" strategies and that step-change innovation may be required. A "diagnose and leave" strategy may be supported for diminutive recto-sigmoid polyps diagnosed with high confidence; however, limitations exist in the evidence base for this cohort.

Establishing funding rates for colonoscopy and gastroscopy procedures in Ontario

Introduction

This paper describes the funding rates established in Ontario to reflect best practices in hospital-based care delivery for these endoscopic procedures: colonoscopy, colonoscopy biopsy, gastroscopy, gastroscopy biopsy, and colonoscopy combined with gastroscopy.

Methods

The funding rates are based on direct costs and were established using a micro-costing approach after receipt of inputs from 3 working groups and a review of the administrative data and literature, where applicable. The first group advised on nursing activities, time, and staffing ratios along the patient pathway for each of the procedures. The second group provided recommendations about the duration for each procedure, and the third group provided information about supplies and equipment, their use, and costs.

Results

The resulting funding rates are $161.18 for colonoscopy and $151.08 for gastroscopy (without accompanying interventions), $16.06 for colonoscopy biopsy and $8.22 for gastroscopy biopsy (added to the respective procedures), and $207.26 for combined colonoscopy and gastroscopy. Detailed costs for each component embedded in the rates are also provided.

Conclusions

The rates came into effect in April 2018. The process and outcomes described here allowed for a transparent pricing mechanism in which funding follows the patient, clinical expert consensus is the basis for practice, and providers and payers both understand the components.

Optical Diagnosis of Colorectal Polyps: Recent Developments

PURPOSE OF REVIEW

Optical diagnosis of diminutive colorectal polyps has been recently proposed as an alternative to histopathologic diagnosis. Recent developments in imaging techniques, new classification systems, and the use of artificial intelligence have allowed for increased viability of optical diagnosis. This review provides an up-to-date overview of optical diagnosis recommendations, classifications, outcomes, and recent developments.

RECENT FINDINGS

There are currently seven major classification systems and three major society recommendations for quality benchmarks for optical diagnosis of diminutive polyps. The NICE classification has been extensively studied and meets quality benchmarks for most imaging techniques but does not allow for the diagnosis of sessile serrated polyps (SSPs). The SIMPLE classification has met quality benchmarks for NBI and i-Scan and allows for the diagnosis of SSPs. Other classification systems need to be further studied to validate effectiveness. Computer-assisted diagnosis of colorectal polyps is a very promising recent development with first studies showing that society-recommended quality benchmarks for real-time colonoscopies on patients are being met. Limitations include a non-negligible percentage of failure to diagnose, low specificity, and low number of real-time diagnostic studies. More research needs to be performed to further understand the value of artificial intelligence for optical polyp diagnosis. Optical diagnosis of diminutive colorectal polyps is currently a viable strategy for experienced endoscopists using validated classifications and imaging-enhanced endoscopy. Artificial intelligence-based diagnosis could make optical diagnosis widely applicable but is currently in its early developmental stage.

Diminutive Polyps With Advanced Histologic Features Do Not Increase Risk for Metachronous Advanced Colon Neoplasia

BACKGROUND & AIMS

With advances in endoscopic imaging, it is possible to differentiate adenomatous from hyperplastic diminutive (1-5 mm) polyps during endoscopy. With the optical Resect-and-Discard strategy, these polyps are then removed and discarded without histopathology assessment. However, failure to recognize adenomas (vs hyperplastic polyps), or discarding a polyp with advanced histologic features, could result in a patient being considered at low risk for metachronous advanced neoplasia, resulting in an inappropriately long surveillance interval. We collected data from international cohorts of patients undergoing colonoscopy to determine what proportion of patients are high risk because of diminutive polyps advanced histologic features and their risk for metachronous advanced neoplasia.

METHODS

We collected data from 12 cohorts (in the United States or Europe) of patients undergoing colonoscopy after a positive result from a fecal immunochemical test (FIT cohort, n = 34,221) or undergoing colonoscopies for screening, surveillance, or evaluation of symptoms (colonoscopy cohort, n = 30,123). Patients at high risk for metachronous advanced neoplasia were defined as patients with polyps that had advanced histologic features (cancer, high-grade dysplasia, ≥25% villous features), 3 or more diminutive or small (6-9 mm) nonadvanced adenomas, or an adenoma or sessile serrated lesion ≥10 mm. Using an inverse variance random effects model, we calculated the proportion of diminutive polyps with advanced histologic features; the proportion of patients classified as high risk because their diminutive polyps had advanced histologic features; and the risk of these patients for metachronous advanced neoplasia.

RESULTS

In 51,510 diminutive polyps, advanced histologic features were observed in 7.1% of polyps from the FIT cohort and 1.5% polyps from the colonoscopy cohort (P = .044); however, this difference in prevalence did not produce a significant difference in the proportions of patients assigned to high-risk status (0.8% of patients in the FIT cohort and 0.4% of patients in the colonoscopy cohort) (P = .25). The proportions of high-risk patients because of diminutive polyps with advanced histologic features who were found to have metachronous advanced neoplasia (17.6%) did not differ significantly from the proportion of low-risk patients with metachronous advanced neoplasia (14.6%) (relative risk for high-risk categorization, 1.13; 95% confidence interval 0.79-1.61).

CONCLUSION

In a pooled analysis of data from 12 international cohorts of patients undergoing colonoscopy for screening, surveillance, or evaluation of symptoms, we found that diminutive polyps with advanced histologic features do not increase risk for metachronous advanced neoplasia.

Should We Resect and Discard Low Risk Diminutive Colon Polyps

Diminutive colorectal polyps <5 mm are very common and almost universally benign. The current strategy of resection with histological confirmation of all colorectal polyps is costly and may increase the risk of colonoscopy. Accurate, optical diagnosis without histology can be achieved with currently available endoscopic technologies. The American Society of Gastrointestinal Endoscopy Preservation and Incorporation of Valuable endoscopic Innovations supports strategies for optical diagnosis of small non neoplastic polyps as long as two criteria are met. For hyperplastic appearing polyps <5 mm in recto-sigmoid colon, the negative predictive value should be at least 90%. For diminutive low grade adenomatous appearing polyps, a resect and discard strategy should be sufficiently accurate such that post-polypectomy surveillance recommendations based on the optical diagnosis, agree with a histologically diagnosis at least 90% of the time. Although the resect and discard as well as diagnose and leave behind approach has major benefits with regard to both safety and cost, it has yet to be used widely in practice. To fully implement such as strategy, there is a need for better-quality training, quality assurance, and patient acceptance. In the article, we will review the current state of the science on optical diagnose of colorectal polyps and its implications for colonoscopy practice.

Investigation of the Local Recurrence Rate after Colorectal Endoscopic Mucosal Resection: Is Incomplete Polyp Resection Really a Clinically Important Problem? Analysis of the Rationale for the "Resect and Discard" Strategy

BACKGROUND/AIMS

The "Resect and Discard" strategy is a potentially useful strategy. At present, only the lesion size and accuracy of diagnosis are cited as considerations for clinical adoption of this strategy. On the other hand, histopathology of the resected specimens after Endoscopic Mucosal Resection (EMR) reveals often an unclear or positive-margin status, implying Incomplete Polyp Resection (IPR). If IPR indeed increased the risk of local recurrence, histopathological evaluation of the margin would be indispensable and clinical adoption of this strategy is difficult. The aim of this study is to verify the association between IPR and the risk of local recurrence.

METHODS

The 1872 polyps and 603 EMR cases in 597 patients who had EMR between May 2013 and May 2014 were enrolled. The local recurrence rate until 3 years after the EMR in cases with the target lesions of the "Resect and Discard" strategy was determined in the negative-margin and IPR groups.

RESULTS

The final analysis was performed using the data of 1092 polyps, and 222 were categorized into the IPR group. There were no cases of recurrence in either of the groups.

CONCLUSION

This is the world's first report conducted to examine the correlation of IPR and the local recurrence rate for clinical practice of "Resect and Discard" strategy. There is the possibility that pathological evaluation of the margins after EMR in patients with small polyps can be skipped.

Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model

BACKGROUND

In general, academic but not community endoscopists have demonstrated adequate endoscopic differentiation accuracy to make the 'resect and discard' paradigm for diminutive colorectal polyps workable. Computer analysis of video could potentially eliminate the obstacle of interobserver variability in endoscopic polyp interpretation and enable widespread acceptance of 'resect and discard'.

STUDY DESIGN AND METHODS

We developed an artificial intelligence (AI) model for real-time assessment of endoscopic video images of colorectal polyps. A deep convolutional neural network model was used. Only narrow band imaging video frames were used, split equally between relevant multiclasses. Unaltered videos from routine exams not specifically designed or adapted for AI classification were used to train and validate the model. The model was tested on a separate series of 125 videos of consecutively encountered diminutive polyps that were proven to be adenomas or hyperplastic polyps.

RESULTS

The AI model works with a confidence mechanism and did not generate sufficient confidence to predict the histology of 19 polyps in the test set, representing 15% of the polyps. For the remaining 106 diminutive polyps, the accuracy of the model was 94% (95% CI 86% to 97%), the sensitivity for identification of adenomas was 98% (95% CI 92% to 100%), specificity was 83% (95% CI 67% to 93%), negative predictive value 97% and positive predictive value 90%.

CONCLUSIONS

An AI model trained on endoscopic video can differentiate diminutive adenomas from hyperplastic polyps with high accuracy. Additional study of this programme in a live patient clinical trial setting to address resect and discard is planned.

Raman spectroscopy for cancer detection and cancer surgery guidance: translation to the clinics

Oncological applications of Raman spectroscopy have been contemplated, pursued, and developed at academic level for at least 25 years. Published studies aim to detect pre-malignant lesions, detect cancer in less invasive stages, reduce the number of unnecessary biopsies and guide surgery towards the complete removal of the tumour with adequate tumour resection margins. This review summarizes actual clinical needs in oncology that can be addressed by spontaneous Raman spectroscopy and it provides an overview over the results that have been published between 2007 and 2017. An analysis is made of the current status of translation of these results into clinical practice. Despite many promising results, most of the applications addressed in scientific studies are still far from clinical adoption and commercialization. The main hurdles are identified, which need to be overcome to ensure that in the near future we will see the first Raman spectroscopy-based solutions being used in routine oncologic diagnostic and surgical procedures.