Diagnosis Of Colorectal Polyps Research Articles

Longer Interval Between First Colonoscopy With Negative Findings for Colorectal Cancer and Repeat Colonoscopy

For individuals without a family history of colorectal cancer (CRC), colonoscopy screening every 10 years is recommended to reduce CRC incidence and mortality. However, debate exists about whether and for how long this 10-year interval could be safely expanded. To assess how many years after a first colonoscopy with findings negative for CRC a second colonoscopy can be performed. This cohort study leveraged Swedish nationwide register-based data to examine CRC diagnoses and CRC-specific mortality among individuals without a family history of CRC. The exposed group included individuals who had a first colonoscopy with findings negative for CRC at age 45 to 69 years between 1990 and 2016. The control group included individuals matched by sex, birth year, and baseline age (ie, the age of their matched exposed individual when the exposed individual's first colonoscopy with findings negative for CRC was performed). Individuals in the control group either did not have a colonoscopy during the follow-up or underwent colonoscopy that resulted in a CRC diagnosis. Up to 18 controls were matched with each exposed individual. Individuals were followed up from 1990 to 2018, and data were analyzed from November 2022 to November 2023. A first colonoscopy with findings negative for CRC, defined as a first colonoscopy without a diagnosis of colorectal polyp, adenoma, carcinoma in situ, or CRC before or within 6 months after screening. The primary outcomes were CRC diagnosis and CRC-specific death. The 10-year standardized incidence ratio and standardized mortality ratio were calculated to compare risks of CRC and CRC-specific death in the exposed and control groups based on different follow-up screening intervals. The sample included 110 074 individuals (65 147 females [59.2%]) in the exposed group and 1 981 332 (1 172 646 females [59.2%]) in the control group. The median (IQR) age for individuals in both groups was 59 (52-64) years. During up to 29 years of follow-up of individuals with a first colonoscopy with findings negative for CRC, 484 incident CRCs and 112 CRC-specific deaths occurred. After a first colonoscopy with findings negative for CRC, the risks of CRC and CRC-specific death in the exposed group were significantly lower than those in their matched controls for 15 years. At 15 years after a first colonoscopy with findings negative for CRC, the 10-year standardized incidence ratio was 0.72 (95% CI, 0.54-0.94) and the 10-year standardized mortality ratio was 0.55 (95% CI, 0.29-0.94). In other words, the 10-year cumulative risk of CRC in year 15 in the exposed group was 72% that of the 10-year cumulative risk of CRC in the control group. Extending the colonoscopy screening interval from 10 to 15 years in individuals with a first colonoscopy with findings negative for CRC could miss the early detection of only 2 CRC cases and the prevention of 1 CRC-specific death per 1000 individuals, while potentially avoiding 1000 colonoscopies. This cohort study found that for the population without a family history of CRC, the 10-year interval between colonoscopy screenings for individuals with a first colonoscopy with findings negative for CRC could potentially be extended to 15 years. A longer interval between colonoscopy screenings could be beneficial in avoiding unnecessary invasive examinations.

Computer-aided diagnosis system for optical diagnosis of colorectal polyps under white light imaging

ObjectivesThis study presents a novel computer-aided diagnosis (CADx) designed for optically diagnosing colorectal polyps using white light imaging (WLI).We aimed to evaluate the effectiveness of the CADx and its auxiliary role among endoscopists with different levels of expertise. MethodsWe collected 2,324 neoplastic and 3,735 nonneoplastic polyp WLI images for model training, and 838 colorectal polyp images from 740 patients for model validation. We compared the diagnostic accuracy of the CADx with that of 15 endoscopists under WLI and narrow band imaging (NBI). The auxiliary benefits of CADx for endoscopists of different experience levels and for identifying different types of colorectal polyps was also evaluated. ResultsThe CADx demonstrated an optical diagnostic accuracy of 84.49%, showing considerable superiority over all endoscopists, irrespective of whether WLI or NBI was used (P < 0.001). Assistance from the CADx significantly improved the diagnostic accuracy of the endoscopists from 68.84% to 77.49% (P = 0.001), with the most significant impact observed among novice endoscopists. Notably, novices using CADx-assisted WLI outperform junior and expert endoscopists without such assistance. ConclusionsThe CADx demonstrated a crucial role in substantially enhancing the precision of optical diagnosis for colorectal polyps under WLI and showed the greatest auxiliary benefits for novice endoscopists.

EfficientPolypSeg: Efficient Polyp Segmentation in colonoscopy images using EfficientNet-B5 with dilated blocks and attention mechanisms

Background:Colorectal cancer ranks as the second leading cause of cancer-related death worldwide, prompting the need for effective strategies to combat this disease. The urgent need for effective strategies to combat this disease has led to the exploration of innovative approaches in medical imaging and diagnosis. Automatic segmentation and detection of colorectal polyps in colonoscopy images have emerged as a promising approach, enabling timely identification and diagnosis of colorectal diseases. Methods:This paper introduces EfficientPolypSeg, an advanced segmentation architecture that leverages the capabilities of EfficientNet-B5 as the encoder, enhanced by two dilated blocks, a Channel Attention Block (CAB), a Spatial Attention Block (SAB), and a Feature Fusion Block (FFB). Notably, our model exhibits superior performance compared to state-of-the-art methods, achieving exceptional accuracy and segmentation quality. Results:To validate the effectiveness of EfficientPolypSeg, extensive experiments were conducted on four publicly available datasets. The results demonstrate the remarkable performance of our model, showcasing its ability to outperform existing approaches in terms of accuracy and segmentation quality. Our model achieved an impressive mean Dice score of 0.92 and a mean Intersection over Union (IoU) of 0.86 on these datasets. These findings highlight the potential impact of EfficientPolypSeg in improving the detection and diagnosis of colorectal polyps. Conclusion:EfficientPolypSeg, the segmentation architecture proposed in this study, exhibits remarkable capabilities in the automatic detection and segmentation of colorectal polyps. The model’s superior performance, as evidenced by extensive experimentation on diverse datasets, emphasizes its potential impact on improving the detection and diagnosis of colorectal diseases.

Artificial intelligence for characterization of diminutive colorectal polyps: A feasibility study comparing two computer-aided diagnosis systems

BACKGROUND Artificial intelligence (AI) has potential in the optical diagnosis of colorectal polyps. AIM To evaluate the feasibility of the real-time use of the computer-aided diagnosis system (CADx) AI for ColoRectal Polyps (AI4CRP) for the optical diagnosis of diminutive colorectal polyps and to compare the performance with CAD EYETM (Fujifilm, Tokyo, Japan). CADx influence on the optical diagnosis of an expert endoscopist was also investigated. METHODS AI4CRP was developed in-house and CAD EYE was proprietary software provided by Fujifilm. Both CADx-systems exploit convolutional neural networks. Colorectal polyps were characterized as benign or premalignant and histopathology was used as gold standard. AI4CRP provided an objective assessment of its characterization by presenting a calibrated confidence characterization value (range 0.0-1.0). A predefined cut-off value of 0.6 was set with values &lt; 0.6 indicating benign and values ≥ 0.6 indicating premalignant colorectal polyps. Low confidence characterizations were defined as values 40% around the cut-off value of 0.6 (&lt; 0.36 and &gt; 0.76). Self-critical AI4CRP’s diagnostic performances excluded low confidence characterizations. RESULTS AI4CRP use was feasible and performed on 30 patients with 51 colorectal polyps. Self-critical AI4CRP, excluding 14 low confidence characterizations [27.5% (14/51)], had a diagnostic accuracy of 89.2%, sensitivity of 89.7%, and specificity of 87.5%, which was higher compared to AI4CRP. CAD EYE had a 83.7% diagnostic accuracy, 74.2% sensitivity, and 100.0% specificity. Diagnostic performances of the endoscopist alone (before AI) increased non-significantly after reviewing the CADx characterizations of both AI4CRP and CAD EYE (AI-assisted endoscopist ). Diagnostic performances of the AI-assisted endoscopist were higher compared to both CADx-systems, except for specificity for which CAD EYE performed best. CONCLUSION Real-time use of AI4CRP was feasible. Objective confidence values provided by a CADx is novel and self-critical AI4CRP showed higher diagnostic performances compared to AI4CRP.

A17 COMPARING ENDOSCOPIST DIAGNOSIS OF COLORECTAL POLYPS ASSISTED BY ARTIFICIAL INTELLIGENCE (CADX) VS CADX WITHOUT ENDOSCOPIST INPUT: A RANDOMIZED CONTROLLED TRIAL

Abstract Background Artificial intelligence-based optical diagnosis systems (CADx) have been developped to assist in eliminating the need for histologic diagnosis of diminutive colorectal polyps (resect-and-discard and diagnose-and-leave strategies). However, these systems have not yet been implemented in routine clinical practice. Aims We were interested in evaluating the performance of CADx without human input to diagnoses performed by endoscopists assisted by CADx. Methods We performed a randomized clinical trial of patients undergoing elective colonoscopies at the CHUM. Patients were randomized into two arms: 1) optical diagnosis of colorectal polyps using CADx without human input; 2) endoscopists performed optical diagnosis after consulting a real-time CADx diagnosis (Human in the Loop [HiL]). Primary outcome was accuracy in optical diagnosis for both arms. Results 467 patients were randomized (229 in the CADx group, 238 in the HiL group). Overall accuracy for optical diagnosis was 76.3% in the CADx group and 70.5% in the HiL group (p=0.19). Sensitivity, specificity, PPV and NPV for adenoma diagnosis were 89.7%, 58.4%, 82.2%, and 72.5% respectively in the CADx group vs 85.3%, 69.6%, 81.8%, and 74.8% in the HiL group. Sensitivity, specificity, PPV and NPV did not differ significantly between the two groups. Conclusions Optical diagnosis of colorectal polyps had similar accuracy when using CADx without human input compared to endoscopist-based diagnosis assisted by CADx. Resect and discard and diagnose and leave strategies can therefore potentially be implemented without need for endoscopist optical diagnosis. Funding Agencies CAGFujifilm

Effectiveness of Dual-Focus Magnification on Confidence Levels in Optical Diagnosis of Small Colorectal Polyps.

Background and objectives Achieving accurate real-time optical diagnoses of colorectal polyps with high-confidence predictions is crucial for appropriate decision-making in daily practice. The dual-focus (DF) magnification mode helps endoscopists scrutinize subtle features of polyp surfaces and vessel patterns. This prospective study aimed to evaluate the impact of DF imaging on enhancing the rate of high-confidence narrow-band imaging (NBI)-based optical diagnosis. Methods Consecutive adult patients who underwent colonoscopy and had small colorectal polyps (<10 mm) were enrolled between September 2022 and May 2023. The optical diagnosis of each polyp was evaluated during colonoscopy in two stages by the same endoscopist, utilizing NBI with DF magnification (NDB-DF). A confidence level was assigned to each prediction. High confidence was indicated by clinical judgment when a polyp exhibited distinctive features associated solely with one histological subtype and lacked characteristics of any other subtype. All procedures were carried out with a prototype 190 series Exera III NBI system (Olympus Corporation, Tokyo, Japan) with DFmagnification. Results The study included 413 patients with 623 polyps, comprising 483 ≤ 5 mm and 140 measuring 6-9 mm. The majority were low-grade adenomas (343 lesions), with 17 identified as high-grade adenomas, and none characterized as deep submucosal invasive carcinomas. NBI-DF significantly improved the rate of high-confidence optical diagnoses compared to NBI for both ≤ 5 mm polyps (93.1% vs. 87.5%, p < 0.0001) and 6-9 mm polyps (97.9% vs. 94.2%, p = 0.03). Furthermore, DF significantly facilitated the assessment of microvessel and surface pattern criteria (p < 0.01). Conclusion DF magnification markedly enhanced the rate of high-confidence NBI-based optical predictions for small colorectal polyps. This technique demonstrates the potential for improving the diagnostic yield in real-time optical diagnosis of colorectal polyps in the Vietnamese setting.

Two-stage deep-learning-based colonoscopy polyp detection incorporating fisheye and reflection correction.

Colonoscopy is a useful method for the diagnosis and management of colorectal diseases. Many computer-aided systems have been developed to assist clinicians in detecting colorectal lesions by analyzing colonoscopy images. However, fisheye-lens distortion and light reflection in colonoscopy images can substantially affect the clarity of these images and their utility in detecting polyps. This study proposed a two-stage deep-learning model to correct distortion and reflections in colonoscopy images and thus facilitate polyp detection. Images were collected from the PolypSet dataset, the Kvasir-SEG dataset, and one medical center's patient archiving and communication system. The training, validation, and testing datasets comprised 808, 202, and 1100 images, respectively. The first stage involved the correction of fisheye-related distortion in colonoscopy images and polyp detection, which was performed using a convolutional neural network. The second stage involved the use of generative and adversarial networks for correcting reflective colonoscopy images before the convolutional neural network was used for polyp detection. The model had higher accuracy when it was validated using corrected images than when it was validated using uncorrected images (96.8% vs 90.8%, P<0.001). The model's accuracy in detecting polyps in the Kvasir-SEG dataset reached 96%, and the area under the receiver operating characteristic curve was 0.94. The proposed model can facilitate the clinical diagnosis of colorectal polyps and improve the quality of colonoscopy.

Classification and endoscopic diagnosis of colorectal polyps

Background: Colorectal cancer is a common malignancy and a major health concern in Korea. The increased use of screening colonoscopies has led to improved survival of patients with colorectal cancer despite its high prevalence; this highlights the importance of early detection and removal of neoplastic polyps such as adenoma and sessile serrated lesions. Therefore, optical diagnosis of colorectal polyps is crucial in deciding whether the lesion requires removal and if endoscopic procedures can be used for its removal.Current Concepts: Several image-enhanced endoscopy (IEE) techniques and classifications can be used to improve the optical diagnosis of different polyps that match the histopathologic findings. Kudo’s pit pattern classification is based on features of pit patterns observed from different types of polyps via chromoendoscopy. The Narrow-Band Imaging (NBI) International Colorectal Endoscopic (NICE) classification is an international classification based on patterns observed from NBI findings. The Japan NBI Expert Team (JNET) classification identifies different patterns observed from magnified images with NBI. The Workgroup serrAted polypS and Polyposis (WASP) classification helps to differentiate hyperplastic polyps from sessile serrated lesions. Endoscopy manufacturers have also developed IEE techniques such as I-scan, flexible spectral imaging color enhancement, and blue laser imaging/linked color imaging to highlight, delineate, and differentiate various polyps.Discussion and Conclusion: Optical diagnosis of colorectal polyps using IEE such as NBI with different classifications such as NICE, JNET, and WASP is important for differentiating neoplastic polyps and removing them with an appropriate method.

AI-powered medical devices for practical clinicians including the diagnosis of colorectal polyps

Background: The integration of medical devices with artificial intelligence (AI) software is rapidly advancing as technology progresses. AI machine learning can be used in commercial medical services to generate practical data; there is evidence that it can be integrated into newly developed devices. However, such devices must undergo approval, regulation, and supervision. The Food and Drug Administration approves regulations for numerous machine-learning medical devices and shares open lists with the public. In this article, we examine recent medical AI devices in different fields, including the diagnosis of colorectal polyps.Current Concepts: Currently, in the field of gastroenterology, there has been a significant amount of research aimed at enhancing adenoma detection rates using tools powered by AI, such as the EndoScreener and GI Genius. Various such devices have also been developed for other fields; examples include the 23andMe Personal Genome Service for DNA detection, Spectral MD’s DeepView platform for wound imaging in surgery, Gili Pro BioSensor for monitoring vital signs, DreaMed Advisor Pro for diabetes, Minuteful for urinary analysis, BrainScope TBI for cerebral diagnosis, Compumedics Sleep Monitoring System for sleep disorders, Idx-DR v2.3 for ophthalmology, and EarliPoint system for pediatrics.Discussion and Conclusion: By the time this article is published, it is likely that even more AI medical devices will have been approved and commercialized. The development of such devices should be strongly encouraged. Additionally, we anticipate greater involvement from practitioners in the development and validation of diverse medical AI devices in Korea.

A Systematic Review and Meta-analysis of Convolutional Neural Network in the Diagnosis of Colorectal Polyps and Cancer.

Convolutional neural networks are a class of deep neural networks used for different clinical purposes, including improving the detection rate of colorectal lesions. This systematic review and meta-analysis aimed to assess the performance of convolutional neural network-based models in the detection or classification of colorectal polyps and colorectal cancer. A systematic search was performed in MEDLINE, SCOPUS, Web of Science, and other related databases. The performance measures of the convolutional neural network models in the detection of colorectal polyps and colorectal cancer were calculated in the 2 scenarios of the best and worst accuracy. Stata and R software were used for conducting the meta-analysis. From 3368 searched records, 24 primary studies were included. The sensitivity and specificity of convolutional neural network models in predicting colorectal polyps in worst and best scenarios ranged from 84.7% to 91.6% and from 86.0% to 93.8%, respectively. These values in predicting colorectal cancer varied between 93.2% and 94.1% and between 94.6% and 97.7%. The positive and negative likelihood ratios varied between 6.2 and 14.5 and 0.09 and 0.17 in these scenarios, respectively, in predicting colorectal polyps, and 17.1-41.2 and 0.07-0.06 in predicting colorectal polyps. The diagnostic odds ratio and accuracy measures of convolutional neural network models in predicting colorectal polyps in worst and best scenarios ranged between 36% and 162% and between 80.5% and 88.6%, respectively. These values in predicting colorectal cancer in the worst and the best scenarios varied between 239.63% and 677.47% and between 88.2% and 96.4%. The area under the receiver operating characteristic varied between 0.92 and 0.97 in the worst and the best scenarios in colorectal polyps, respectively, and between 0.98 and 0.99 in colorectal polyps prediction. Convolutional neural network-based models showed an acceptable accuracy in detecting colorectal polyps and colorectal cancer.

Advances in artificial intelligence and computer science for computer-aided diagnosis of colorectal polyps: current status.

Advances in artificial intelligence and computer science for computer-aided diagnosis of colorectal polyps: current status.

Target trial emulation of aspirin after diagnosis of colorectal polyps

Backgound and AimsPrevious research on the potential chemoprotective effect of aspirin for colorectal cancer (CRC) shows conflicting results. We aimed to emulate a trial of aspirin intiation in individuals with incident polyps.MethodsWe identified individuals registered with their first colorectal polyp in the nationwide gastrointestinal ESPRESSO histopathology cohort in Sweden. Individuals aged 45–79 years diagnosed with colorectal polyps 2006–2016 in Sweden without CRC or contraindications for preventive aspirin (cerebrovascular disease, heart failure, aortic aneurysms, pulmonary emboli, myocardial infarction, gastric ulcer, dementia, liver cirrhosis, or any other metastatic cancer) registered until the month of first polyp detection were eligible. Using duplication and inverse probability weighting, we emulated a target trial of aspirin initiation within 2 years of initial polyp detection. The main outcome measures were incident CRC, CRC mortality and all-cause mortality registered until 2019.ResultsOf 31,633 individuals meeting our inclusion criteria, 1716 (5%) initiated aspirin within 2 years of colon polyp diagnosis. Median follow-up was 8.07 years. The 10-year cumulative incidence in initiators versus non-initiators was 6% versus 8% for CRC incidence, 1% versus 1% for CRC mortality and 21% versus 18% for all-cause mortality. The corresponding hazard ratios were 0.88 (95% confidence interval, 95%CI = 0.86–0.90), 0.90 (95%CI = 0.75–1.06) and 1.18 (95%CI = 1.12–1.24).ConclusionAspirin initiation in individuals with polyp removal was linked to 2% lower cumulative incidence of CRC after 10 years but did not alter CRC mortality. We also observed a 4% increased risk difference of all-cause mortality at 10 years after the initiation of aspirin.

Cover Image

Digestive EndoscopyVolume 35, Issue 4 p. i-i Cover ImageFree Access Cover Image First published: 11 May 2023 https://doi.org/10.1111/den.14360AboutPDF ToolsRequest permissionExport citationAdd to favoritesTrack citation ShareShare Give accessShare full text accessShare full-text accessPlease review our Terms and Conditions of Use and check box below to share full-text version of article.I have read and accept the Wiley Online Library Terms and Conditions of UseShareable LinkUse the link below to share a full-text version of this article with your friends and colleagues. Learn more.Copy URL Graphical Abstract Cover image: (Top left) Computer-aided detection for colorectal polyps (EndoBRAIN; Olympus Corp., Tokyo, Japan); (top right) computer-aided diagnosis for colorectal polyps (GI GENIUS CADx; Medtronic Corp., Dublin, Ireland). (Bottom) Possible cost increase and reduction introduced by artificial intelligence (AI) in colonoscopy. ADR, adenoma detection rate. (See Mori et al. pp. 423 & 425). Volume35, Issue4May 2023Pages i-i RelatedInformation

FeDNet: Feature Decoupled Network for polyp segmentation from endoscopy images

Early detection and diagnosis of colorectal polyps are critical to the diagnosis and treatment of colorectal cancer. When it comes to polyp segmentation, previous methods have limited benefit whether starting with the global contextual information to maintain the consistency of the information within the polyp or starting with the edge information to refine the prediction results. Therefore, a comprehensive way to obtain good polyp segmentation performance is to optimize both simultaneously. Depending on the above analysis, we explore in this paper how to improve the performance of polyp segmentation by optimizing the body and edge simultaneously. Inspired by the feature decoupled method in Laplacian pyramid, we decouple the input feature into the body and edge feature explicitly in an effective and reasonable way, and subsequently perform targeted optimization by introducing a novel Feature Decoupled Module (FDM). Furthermore, combined with FDM (with only 0.08 m network parameters), our approach can significantly outperform previous state-of-the-art methods, attaining a further improvement over the baseline. Especially, we achieve 92.4% mean Dice on the large-scale Kvasir dataset. Not only that, it also demonstrates strong generalization ability. It obtains the top performance on three datasets, where it achieves 82.3% and 81.0% mean Dice on CVC-ColonDB and ETIS, respectively, far exceeding the competitors. Code will be released.11https://github.com/suyanzhou626/FeDNet-BSPC.

Diagnostic Value of Adding Magnifying Chromoendoscopy to Magnifying Narrow-Band Imaging Endoscopy for Colorectal Polyps

This study examined the additional value of magnifying chromoendoscopy (MCE) on magnifying narrow-band imaging endoscopy (M-NBI) in the optical diagnosis of colorectal polyps. A multicenter prospective study was conducted at 9 facilities in Japan and Germany. Patients with colorectal polyps scheduled for resection were included. Optical diagnosis was performed by M-NBI first, followed by MCE. Both diagnoses were made in real time. MCE was performed on all type 2B lesions classified according to the Japan NBI Expert Team classification and other lesions at the discretion of endoscopists. The diagnostic accuracy and confidence of M-NBI and MCE for colorectal cancer (CRC) with deep invasion (≥T1b) were compared on the basis of histologic findings after resection. In total, 1173 lesions were included between February 2018 and December 2020, with 654 (5 hyperplastic polyp/sessile serrated lesion, 162 low-grade dysplasia, 403 high-grade dysplasia, 97 T1 CRCs, and 32 ≥T2 CRCs) examined using MCE after M-NBI. In the diagnostic accuracy for predicting CRC with deep invasion, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy for M-NBI were 63.1%, 94.2%, 61.6%, 94.5%, and 90.2%, respectively, and for MCE they were 77.4%, 93.2%, 62.5%, 96.5%, and 91.1%, respectively. The sensitivity was significantly higher in MCE (P < .001). However, these additional values were limited to lesions with low confidence in M-NBI or the ones diagnosed as ≥T1b CRC by M-NBI. In this multicenter prospective study, we demonstrated the additional value of MCE on M-NBI. We suggest that additional MCE be recommended for lesions with low confidence or the ones diagnosed as ≥T1b CRC. Trials registry number: UMIN000031129.

Updates in narrow-band imaging for colorectal polyps: Narrow-band imaging generations, detection, diagnosis, and artificial intelligence.

Narrow-band imaging (NBI) is an optical digital enhancement method that allows the observation of vascular and surface structures of colorectal lesions. Its usefulness in the detection and diagnosis of colorectal polyps has been demonstrated in several clinical trials and the diagnostic algorithms have been simplified after the establishment of endoscopic classifications such as the Japan NBI Expert Team classification. However, there were issues including lack of brightness in the earlier models, poor visibility under insufficient bowel preparation, and the incompatibility of magnifying endoscopes in certain endoscopic platforms, which had impeded NBI from becoming standardized globally. Nonetheless, NBI continued its evolution and the newest endoscopic platform launched in 2020 offers significantly brighter and detailed images. Enhanced visualization is expected to improve the detection of polyps while universal compatibility across all scopes including magnifying endoscopy will promote the global standardization of magnifying diagnosis. Therefore, knowledge related to magnifying colonoscopy will become essential as magnification becomes standardly equipped in future models, although the advent of computer-aided diagnosis and detection may greatly assist endoscopists to ensure quality of practice. Given that most endoscopic departments will be using both old and new models, it is important to understand how each generation of endoscopic platforms differ from each other. We reviewed the advances in the endoscopic platforms, artificial intelligence, and evidence related to NBI essential for the next generation of endoscopic practice.

Multi-Classification of Polyps in Colonoscopy Images Based on an Improved Deep Convolutional Neural Network

Achieving accurate classification of colorectal polyps during colonoscopy can avoid unnecessary endoscopic biopsy or resection. This study aimed to develop a deep learning model that can automatically classify colorectal polyps histologically on white-light and narrow-band imaging (NBI) colonoscopy images based on World Health Organization (WHO) and Workgroup serrAted polypS and Polyposis (WASP) classification criteria for colorectal polyps. White-light and NBI colonoscopy images of colorectal polyps exhibiting pathological results were firstly collected and classified into four categories: conventional adenoma, hyperplastic polyp, sessile serrated adenoma/polyp (SSAP) and normal, among which conventional adenoma could be further divided into three sub-categories of tubular adenoma, villous adenoma and villioustublar adenoma, subsequently the images were re-classified into six categories. In this paper, we proposed a novel convolutional neural network termed Polyp-DedNet for the four- and six-category classification tasks of colorectal polyps. Based on the existing classification network ResNet50, Polyp-DedNet adopted dilated convolution to retain more high-dimensional spatial information and an Efficient Channel Attention (ECA) module to improve the classification performance further. To eliminate gridding artifacts caused by dilated convolutions, traditional convolutional layers were used instead of the max pooling layer, and two convolutional layers with progressively decreasing dilation were added at the end of the network. Due to the inevitable imbalance of medical image data, a regularization method DropBlock and a Class-Balanced (CB) Loss were performed to prevent network overfitting. Furthermore, the 5-fold cross-validation was adopted to estimate the performance of Polyp-DedNet for the multi-classification task of colorectal polyps. Mean accuracies of the proposed Polyp-DedNet for the four- and six-category classifications of colorectal polyps were 89.91% ± 0.92% and 85.13% ± 1.10%, respectively. The metrics of precision, recall and F1-score were also improved by 1%~2% compared to the baseline ResNet50. The proposed Polyp-DedNet presented state-of-the-art performance for colorectal polyp classifying on white-light and NBI colonoscopy images, highlighting its considerable potential as an AI-assistant system for accurate colorectal polyp diagnosis in colonoscopy.

Real-World Experience of AI-Assisted Endocytoscopy Using EndoBRAIN—An Observational Study from a Tertiary Care Center

Abstract Background and Aims Precise optical diagnosis of colorectal polyps could improve the cost-effectiveness of colonoscopy and reduce polypectomy-related complications. We conducted this study to estimate the diagnostic performance of visual inspection alone (WLI + NBI) and of EndoBRAIN (endocytoscopy-computer-aided diagnosis [EC-CAD]) in identifying a lesion as neoplastic or nonneoplastic using EC in real-world scenario. Methods In this observational, prospective, pilot study, a total of 55 polyps were studied in the patients aged more than or equal to 18 years. EndoBRAIN is an artificial intelligence (AI)-based system that analyzes cell nuclei, crypt structure, and vessel pattern in differentiating neoplastic and nonneoplastic lesion in real-time. Endoscopist assessed polyps using white light imaging (WLI), narrow band imaging (NBI) initially followed by assessment using EC with NBI and EC with methylene blue staining. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of endoscopist and EndoBRAIN in identifying the neoplastic from nonneoplastic polyp was compared using histopathology as gold-standard. Results A total of 55 polyps were studied, in which most of them were diminutive (36/55) and located in rectum (21/55). The image acquisition rate was 78% (43/55) and histopathology of the majority was identified to be hyperplastic (20/43) and low-grade adenoma (16/43). EndoBRAIN identified colonic polyps with 100% sensitivity, 81.82% specificity (95% confidence interval [CI], 59.7–94.8%), 90.7% accuracy (95% CI, 77.86–97.41%), 84% positive predictive value (95% CI, 68.4–92.72%), and 100% negative predictive value. The sensitivity and negative predictive value were significantly greater than visual inspection of endoscopist. The diagnostic accuracy seems to be superior; however, it did not reach statistical significance. Specificity and positive predictive value were similar in both groups. Conclusion Optical diagnosis using EC and EC-CAD has a potential role in predicting the histopathological diagnosis. The diagnostic performance of CAD seems to be better than endoscopist using EC for predicting neoplastic lesions.

Comparison of nice classification for optical diagnosis of colorectal polyps and morphology of removed lesions depending on localisation in colon

Abstract The narrow-band imaging (NBI) International Colorectal Endoscopic (NICE) classification is based on narrow-band pictures of colon polyps viewed through a narrow-band spectrum. The categorisation utilises staining, surface structure, and vascular patterns to differentiate between hyperplastic and adenomatous colon polyps. It is known that accuracy of the NICE classification for colorectal polyps varies depending on the localisation in the colon.The aim of this study was to compare the diagnostic accuracy of the NICE classification and the gold standard — morphological analysis for the determination of the type of colorectal lesions depending on localisation in colon. A prospective study was performed in an outpatient clinic. 1214 colonoscopies were performed by two expert endoscopists and 475 polyps were found in 291 patients. The overall diagnostic accuracy of the NICE classification was 80.3%. Optical verification was better in ascending colon — 93.9%, followed by sigmoid colon — 82.1%. Inferior results were found for the descending colon — 64.0%. The results of this study showed that the NICE classification could be a helpful instrument in daily practice for the ascending and sigmoid colon. For better results, proper training should be considered. The NICE system could have a role in the replacement of morphological analysis if appropriate results of verification could be achieved.

Comparative Performance of Artificial Intelligence Optical Diagnosis Systems for Leaving in Situ Colorectal Polyps

Comparative Performance of Artificial Intelligence Optical Diagnosis Systems for Leaving in Situ Colorectal Polyps