Saudi Journal of Gastroenterology
Home About us Instructions Submission Subscribe Advertise Contact Login    Print this page  Email this page Small font sizeDefault font sizeIncrease font size 
Users Online: 72 


 
Table of Contents   
ORIGINAL ARTICLE  
Year : 2020  |  Volume : 26  |  Issue : 1  |  Page : 13-19
Study on detection rate of polyps and adenomas in artificial-intelligence-aided colonoscopy


Department of Digestive Endoscopy, No. 988 Hospital of Joint Logistic Support Force of PLA, Zhengzhou, China

Click here for correspondence address and email

Date of Web Publication18-Feb-2020
 

   Abstract 


Background/Aim: To study the impact of computer-aided detection (CADe) system on the detection rate of polyps and adenomas in colonoscopy.
Materials and Methods: A total of 1026 patients were prospectively randomly scheduled for colonoscopy with (the CADe group, CADe) or without (the control group, CON) the aid of the CADe system, together with visual notification and voice alarm, so as to compare the detection rate of polyp.
Results: Compared with group CON, the detection rate of adenomas increased in group CADe, the average number of adenomas increased, the number of small adenomas increased, the number of proliferative polyps increased, and the differences were statistically significant (P < 0.001), but the comparison for the number of larger adenomas showed no significant difference between the groups (P> 0.05).
Conclusions: The CADe system is feasible for increasing the detection of polyps and adenomas in colonoscopy.

Keywords: Adenoma, artificial intelligence, colonoscopy, detection rate, polyp

How to cite this article:
Liu WN, Zhang YY, Bian XQ, Wang LJ, Yang Q, Zhang XD, Huang J. Study on detection rate of polyps and adenomas in artificial-intelligence-aided colonoscopy. Saudi J Gastroenterol 2020;26:13-9

How to cite this URL:
Liu WN, Zhang YY, Bian XQ, Wang LJ, Yang Q, Zhang XD, Huang J. Study on detection rate of polyps and adenomas in artificial-intelligence-aided colonoscopy. Saudi J Gastroenterol [serial online] 2020 [cited 2022 Dec 5];26:13-9. Available from: https://www.saudijgastro.com/text.asp?2020/26/1/13/274538

See accompanying editorial on page 1





   Introduction Top


In recent years, the incidence of colorectal cancer (CRC) in China has increased and brought the country to the third place in the world, in terms of incidence of the disease.[1],[2] At present, colonoscopy is considered to be the gold standard for reducing the morbidity and mortality of CRC.[3],[4] It is generally believed that 80%–95% of CRC evolves from colorectal polyps step by step, especially adenomatous polyps. Timely removal of polyps can effectively prevent the occurrence of CRC. Therefore, colonoscopy reduces the incidence of CRC by detecting and excising adenomatous polyps. Nowadays, the workload of colonoscopy in third-class level A hospitals is heavy. Doctors' fatigue state, as well as doctors' lack of experience, may easily lead to mis- and missed diagnosis of diseases, which then directly affects the detection rate and diagnostic accuracy of colonoscopy.[5] The factors affecting the detection rate of intestinal polyps include blind areas and human errors. Blind areas can be solved by wide-angle range or remote connection, and artificial intelligence (AI) can solve human errors and is attracting wide attention.[6],[7],[8],[9],[10],[11] To solve human errors, we obtained a large number of colonoscopic videos and used an automatic image feature extraction and machine-learning-based AI system algorithm to evaluate the performance of computer-aided detection (CADe) system, so that the detection rate of polyps and adenomas can be increased through the CADe system.


   Materials and Methods Top


CADe system of polyp

The CADe system of polyps (Henan Xuanweitang Medical Information Technology Co., LTD., Zhengzhou City, Henan Province, China) (Former name: Henan Tongyu Medical Technology Co., Ltd) was developed on the basis of in-depth learning architecture with the help of endoscopists and modelers. In our study, one endoscopy specialist of Endoscopy Center (had performed >20,000 cases of colonoscopy) retrospectively commented on the presence of polyps in each frame of each video, which was used as the gold standard for the detection of polyps. To use these videos for machine learning and evaluation, we divided these full-length videos into short videos according to the method described in the document and produced 151 polyp-positive videos and 384 polyp-negative videos. These 535 videos were randomly divided into two groups: the study samples (101 polyp-positive cases and 300 polyp-negative cases) and the test samples (46 polyp-positive cases and 88 polyp-negative cases). The study samples were used for machine learning, and the test samples were used to evaluate the performance of our system. Therefore, the test sample set was a completely independent data set that had never been used during machine learning. From the colonoscopy system, the video stream was captured by a high-definition frame capture device. The aperture describing image information in each successively captured frame can be clipped to ignore all unnecessary image data, such as black frames or screen displays. The clipped images were then color transformed, and the information from three color channels was weighted according to their participation degree in the information. Next, the weighted combination of color, structure, texture, and motion information was used to detect the image area where the polyp may be located. Once the image content of the detected area remained constant for at least three consecutive frames, an enhancement mask was provided, which was repeated for each frame of the captured image stream. Therefore, endoscopists were encouraged to pay special attention to each area and check whether such markers matched polyps. The system was designed to highlight potential polypoid structures during real-time colonoscopy.

System algorithms

In this study, we developed a new original algorithm based on convolutional three-dimensional (3D) neural network, which was a kind of deep learning. Deep learning is the latest machine learning method using deep neural network. If a large number of learning samples are available, it can automatically extract specific features from data without human resources. The convolutional 3D network is designed for spatiotemporal data. Therefore, compared with previous deep learning methods, it is more suitable for video data sets.

Prospective comparative study

The prospective study was designed as a randomized controlled trial to study the effect of endoscopist-assisted CAD system on the detection rate of polyps and adenomas. The study was approved by the local ethics committee. Colonoscopy videos in the study were selected from the participants who underwent colonoscopy in Digestive Endoscopy Center of the 988 Hospital of the Joint Logistics Support Force of the Chinese People's Liberation Army from October 2018 to March 2019. All the participants signed the informed consent, and then routine intestinal preparation was performed, followed by oral administration of 3 L of compound polyethylene glycol electrolyte powder. (Beaufour Ipsen Industrie France; Registration No: H20140560; specification: the product is a compound preparation, containing per pouch: 64.000 g of polyethylene glycol 4000, 5.700 g of anhydrous sodium fulfate, 1.460 g of NaCl, 0.750 g of KCl, and 1.680 g of NAHCO3.) Intestinal preparation referred to APP video education of digestive endoscopy. Colonoscopy was performed using one high-definition colonoscopy (Fuji EPX-4450HD) and one high-definition monitor. Exclusion criteria: any participant with inflammatory bowel disease, history of CRC surgery, history of radiotherapy and/or chemotherapy, and biopsy contraindications. Before colonoscopy, nurses recorded the basic information of each participant, including the gender, age, colonoscopy indications, body mass index, history of smoking, constipation, diabetes, stroke, family history of cancer, abdominal surgery, colonoscopy, aspirin, or other nonsteroidal anti-inflammatory drug use. Before colonoscopy, each participant was randomly divided into group CON (routine colonoscopy group) and group CADe. In group CADe, real-time polyp CADe system was used to assist colonoscopy. The CADe system was only opened when colonoscopy exited, especially started from the point the endoscopist identified the opening of the appendix. The system was connected with the endoscope generator and the video stream was collected synchronously. In addition, the system processed each frame and displayed the detected polyps. The CADe system represented the probability of polyps by percentage (0%–100%) in each frame. [Figure 1] shows the probability provided by the CADe system in the upper left corner of the endoscopic image. When the probability exceeded the critical value, the CADe system warned of the possibility of polyps by changing the color of the four corners of the endoscopic image to red. When lesions appeared on the screen, a warning was issued, and when lesions disappeared from the screen, the warning would stop. Endoscopists focused mainly on the main monitor during the examination process, and a voice alarm prompted them to view the system monitor to check the location of each polyp detected by the system. The above operations were done without the assistance of nurses, trainees, or staff. In both groups, nurses needed to record the insertion time, withdrawal time, and Boston Bowel Preparation Scale (BBPS). When polyps were detected, nurses also assisted in biopsy pathological examination. Nurses also recorded the location, size, and morphological characteristics according to the Paris Classification.[12] In group CADe, missed polyps and system error alarms were also recorded. These missed polyps were defined as polyps confirmed by the colonoscopist but not detected by the system. False alarms were defined as lesions detected and continuously tracked but were not identified as polyps by the system.
Figure 1: CADe system provides the probability in the upper left corner of the endoscopic image

Click here to view


Statistical analysis

SPSS 21.0 was used for statistical analysis. The intergroup comparison of the basal clinical and demographic characteristics was performed by the χ2 test of categorical variables and double-sample t-test of continuous variables. Logistic regression analysis was used to analyze the impact of the CADe system on the detection rate of polyps/adenomas in colonoscopy. The response variable was the binary result of whether polyps/adenomas were detected. The covariate was the group variable indicating whether patients belong to group CADe. Regarding the number of polyps and adenomas detected, Poisson's regression was used to evaluate the effectiveness of computer-aided diagnosis of colonoscopy, with P < 0.05 (bilateral) as statistically significant. If any basal clinical and demographic characteristics showed statistical differences between the two groups, an additional covariate was constructed to adjust the logistic/Poisson's regression model to address possible confusion effects by adding these significant features as covariates to the model. The main result was the detection rate of adenoma. The secondary results included were the detection rate of polyp, the average number of polyps detected by colonoscopy in each case, the average number of adenomas detected by colonoscopy in each case, and false-positive and false-negative rates.


   Results Top


Patient enrolment and basal data

A total of 1100 consecutive patients were enrolled. Of these patients, 84 cases (40 in group CON and 44 in group CADe) were excluded because they met the exclusion criteria. A total of 1026 eligible patients were analyzed. They were prospectively divided into group CON (518 cases) and group CADe (508 cases). The basal characteristics are shown in [Table 1]. There was no significant difference in the demographic data and risk factors for adenoma detection between the two groups. No complications were reported. The total withdrawal time of group CON and group CADe was 6.74 and 6.82 min, respectively (P < 0.001). Totally 232 biopsies were performed in group CADe. The withdrawal time of biopsy was 6.11 min in group CON and 6.16 min in group CADe (P > 0.05).
Table 1: Comparison of basal data between the two groups

Click here to view


Polyp characteristics, average number of polyps per patient, and detection rate of polyp

A total of 734 polyps were detected, including 392 cases of adenoma (53.41%) and 31 cases of sessile serrated adenoma (4.22%). In all, 248 polyps were found in group CON (33.79%) and 486 polyps in group CADe (66.21%) [Table 2]. The average number of polyps detected by colonoscopy in group CON and group CADE was 0.57 and 0.87, respectively (P < 0.001). The average number of polyps detected in both groups increased by 1.53 times [95% confidence interval (CI) was 1.652–2.297, P < 0.001] [Table 3]. The detection rates of polyps in group CON and group CADs were 0.28 and 0.44, respectively [odds ratio (OR) =1.57, 95% CI 1.586–2.483, P < 0.001] [Table 3]. There was no significant difference in the basal clinical and demographic variables between the two groups. Therefore, the covariate adjustment model was not considered to solve the potential confusion effect.
Table 2: Characteristics of polyps and adenomas

Click here to view
Table 3: Detection of polyps and adenomas

Click here to view


Adenoma characteristics, average number of adenomas per patient, and detection rate of adenomas

A total of 392 adenomas were detected [Table 2]. The average number of adenomas detected by colonoscopy in group CON and group CADe was 0.34 and 0.52, respectively (P < 0.001). The average number of adenomas detected in both groups increased by 1.51 times (95% CI 1.423–2.016, P < 0.001) [Table 3]. The detection rates of adenomas in group CON and group CADe were 0.23 and 0.39, OR = 1.64, 95% CI 1.201–2.220, respectively, P < 0.001 [Table 3]. The number of polyps detected in group CADe was significantly higher than group CON when considering sessile polyps, polyps ranging from 0 to 1 cm, and polyps in all parts of the colon. The number of adenomas detected in group CADe also increased significantly when considering sessile polyps, polyps less than 0.5 cm, and polyps in all parts of the colon except cecum and ascending colon [Table 3].

Results of good bowel preparation (BBPS <7)

The adenoma detection rate in group CADe was 5.8% higher than group CON when intestinal preparation was good. However, due to the insufficient sample size of subgroup analysis, this study failed to show statistical significance. Other outcomes in group CADe, including the average number of adenomas detected, the average number of polyps detected, and the detection rate of polyps, increased significantly [Table 4].
Table 4: Results of good bowel preparation (BBPS ≥7)

Click here to view


Misreporting of polyp by CADe system

There were 36 false alarms (false-positive) in group CADe, with an average of 0.071 false alarms per colonoscopy [Table 5]. Of all polyps detected in group CADe, no polyps were missed [Table 5].
Table 5: Mis- and missed report of polyps

Click here to view



   Discussion Top


CRC is the third most common malignant tumor in the world and the fourth leading cause of cancer death.[13] Colonoscopy has been demonstrated to be effective in detecting and removing tumors to prevent CRC.[1] However, the diagnostic performance of colonoscopy varies, which leads to the importance of improving quality and reducing operator dependence. Adenoma detection rate is an independent predictor of the risk of interval CRC [14],[15] and even taking patient-related factors into account, this key indicator varies considerably among endoscopists in similar environments.[16],[17] The application of AI in colonoscopy is attracting more and more attention because it may improve the quality of colonoscopy.[6],[18] The main research focused in this field includes automatic paired polyp detection [19],[20] and feature analysis,[8],[10] which may help improve the detection rate of adenomas, respectively. The detection rate of adenomas can also be increased by the shortest withdrawal time, fractional-dose bowel preparation, and right colon inversion.[21],[22],[23],[24] A preliminary study had shown that 94% of test polyps (47 out of 50) were detected by AI system, and the false-positive rate was 60% (51 out of 85).[25] Despite these advances, polyp specificity still produces many false-positives. On the contrary, inadequate sensitivity will not increase the detection rate of polyps. In addition, to improve the efficiency of real-time detection, the analysis time must be fast, and there is should be no obvious delay by endoscopists. Because of these preconditions, most of the current studies on automatic polyp detection are small-scale nonclinical studies. Nonetheless, with the rapid increase in interest in this field and the emergence of in-depth learning, great progress can be expected in the next few years.

However, part of missed detection cases may be due to endoscopists not adequately recognizing the lesions shown on video monitors. It is well-known that the detection rate of polyps in afternoon colonoscopy is lower than that in morning colonoscopy, which may be attributed to the fatigue of endoscopists, consistent with Marcondes et al.[5] CADe polyp detection may be suitable to solve this problem. Computer monitoring of colorectal lesions may be appropriate to prevent the omission of polyps during endoscopy.

Video sequences collected during colonoscopy can be reviewed using CADe retrospectively. The CADe system used in this study has also been successfully tested on video clips recorded in the past.

One reason why colorectal polyps can be detected by colonoscopy may be that frame grabbers are used to capture image signals from the colonoscopy system and process images, which have no (short) delays between final depicting images on the second screen. However, this delay may be reduced by directly accessing the image stream of the colonoscopy system (without using a frame grabber).

In this study, the detection rates of adenoma and the average number of polyps and adenomas by colonoscopy in group CADe were significantly higher than group CON; however, the overall increase in adenoma detection was mainly due to the increase in small adenomas. Most of the small adenomas detected by CADe system were smaller, which also proves that smaller polyps are more easily ignored in the field of vision than larger and more prominent polyps. Smaller adenomas have a lower risk of malignancy than larger adenomas, but higher overall adenoma detection may ultimately help reduce the risk of CRC, consistent with the results by Klare et al.[11] Further research should address the role of CADe system in reducing polyps, which is the main objective of colonoscopy.

The results of this study show that detection of microproliferative polyps increases significantly, which may mean that additional unnecessary polypectomy will increase the workload. The CADe system is expected to be combined with the CADx system to support the detection and diagnosis of lesions, thus avoiding excessive workload.

This system failed to help endoscopists detect more adenomas in the cecum and ascending colon, which may be due to the high instability of colonoscopy in these areas, which reduces vision. In addition, there was no significant difference in the rectum, which may be due to the good visibility and stability of colonoscopy in this segment.

This study is a prospective randomized controlled trial using a deep-learning-based CADe system to help endoscopists detect colon polyps in a large number of patients. The results show that the CADe system can effectively deal with unidentified polyps. However, the remaining polyps in the blind area remains an unsolved problem.

This study has several limitations. First, in this study, we removed the biopsy time from each corresponding withdrawal time as an indirect reminder of attention [Table 1]. The withdrawal time of the two groups was similar (6.11 and 6.16 min, P= 0.16), which may represent similar observation attention. The CADe system had an average of 0.071 false alarms per colonoscopy, while having no prolonged withdrawal time.

In the future, double-blinded studies can be used to study the application of CADe system in improving the detection rate of polyps/adenomas. This study may also help determine whether polyps can be detected simultaneously by endoscopists and systems or those initially missed by endoscopists, which is a problem not designed in current studies.

The detection rate of polyps and adenomas in this study is not as high as reported in the Western countries. It may be affected by a variety of factors, including the differences in genetics, lifestyle, diet and habits, as well as the incidence of colonic polyps/adenomas, between Eastern and Western populations. Therefore, the results of this study may not be extended to the areas with higher detection rate of polyps/adenomas in the world. The application of CADe system in these fields needs further study.

Although the false-positives rate was very low, the system designer did not take some false-positive into account. These false-positive results were caused by feces, fecal residue, local bleeding, inflammation, or wrinkled mucosa, which lead to distraction during examination or operation. This can be corrected by adding enough training samples to the system. This study did not control the fatigue level of endoscopists participating in the examination, which may be an independent factor affecting adverse reactions. The application of CADe system at different fatigue levels needs to be further studied. This study was conducted using Fuji Colonoscopy equipment. Therefore, we should also discuss the application of CADe system in other colonoscope manufacturers.

In conclusion, this study shows that the CADe system based on in-depth learning increases the detection rate of colorectal polyps and adenomas. Therefore, the CADe system is feasible for the detection of polyps and adenomas in colonoscopy.

Financial support and sponsorship

Nil.

Conflicts of interest

There are no conflicts of interest.



 
   References Top

1.
Winawer SJ, Zauber AG, Ho MN, O'Brien MJ, Gottlieb LS, Sternberg SS, et al. Prevention of colorectal cancer by colonoscopic polypectomy. N Engl J Med 1993;329:1977-81.  Back to cited text no. 1
    
2.
Zauber AG, Winawer SJ, O'Brien MJ, Lansdorp-Vogelaar I, van Ballegooijen M, Hankey BF, et al. Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. N Engl J Med 2012;366:687-96.  Back to cited text no. 2
    
3.
Nishihara R, Wu K, Lochhead P, Morikawa T, Liao X, Qian ZR, et al. Long-term colorectal-cancer incidence and mortality after lower endoscopy. N Engl J Med 2013;369:1095-105.  Back to cited text no. 3
    
4.
Rex DK, Boland CR, Dominitz JA, Giardiello FM, Johnson DA, Kaltenbach T, et al. Colorectal cancer screening: Recommendations for physicians and patients from the U.S. multi-society task force on colorectal cancer. Am J Gastroenterol 2017;112:1016-30.  Back to cited text no. 4
    
5.
Marcondes FO, Gourevitch RA, Schoen RE, Crockett SD, Morris M, Mehrotra A. Adenoma detection rate falls at the end of the day in a large multi-site sample. Dig Dis Sci 2018;63:856-9.  Back to cited text no. 5
    
6.
Byrne MF, Shahidi N, Rex DK. Will computer-aided detection and diagnosis revolutionize colonoscopy? Gastroenterology 2017;153:1460-4.e1.  Back to cited text no. 6
    
7.
Misawa M, Kudo SE, Mori Y, Misawa M, Kudo SE, Mori Y, et al. Characterization of colorectal lesions using a computer-aided diagnostic system for narrow-band imaging endocytoscopy. Gastroenterology 2016;150:1531-2.e3.  Back to cited text no. 7
    
8.
Chen PJ, Lin MC, Lai MJ, Lin JC, Lu HH, Tseng VS. Accurate classification of diminutive colorectal polyps using computer-aided analysis. Gastroenterology 2018;154:568-75.  Back to cited text no. 8
    
9.
Mori Y, Kudo SE, Misawa M, Mori K. Simultaneous detection and characterization of diminutive polyps with the use of artificial intelligence during colonoscopy. Video GIE 2019;4:7-10.  Back to cited text no. 9
    
10.
Byrne MF, Chapados N, Soudan F, Oertel C, Linares Pérez M, Kelly R, et al. Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut 2019;68:94-100.  Back to cited text no. 10
    
11.
Klare P, Sander C, Prinzen M, Haller B, Nowack S, Abdelhafez M, et al. Automated polyp detection in the colorectum: A prospective study (with videos). Gastrointest Endosc 2019;89:576-82.e1.  Back to cited text no. 11
    
12.
Endoscopic Classification Review Group. Update on the Paris classification of superficial neoplastic lesions in the digestive tract. Endoscopy 2005;37:570-8.  Back to cited text no. 12
    
13.
Torre LA, Bray F, Siegel RL, Ferlay J, Lortet-Tieulent J, Jemal A. Global cancer statistics, 2012. CA Cancer J Clin 2015;65:87-108.  Back to cited text no. 13
    
14.
Corley DA, Jensen CD, Marks AR, Zhao WK, Lee JK, Doubeni CA, et al. Adenoma detection rate and risk of colorectal cancer and death. N Engl J Med 2014;370:1298-306.  Back to cited text no. 14
    
15.
Kaminski MF, Regula J, Kraszewska E, Polkowski M, Wojciechowska U, Didkowska J, et al. Quality indicators for colonoscopy and the risk of interval cancer. N Engl J Med 2010;362:1795-803.  Back to cited text no. 15
    
16.
Chen SC, Rex DK. Endoscopist can be more powerful than age and male gender in predicting adenoma detection at colonoscopy. Am J Gastroenterol 2007;102:856-61.  Back to cited text no. 16
    
17.
Barclay RL, Vicari JJ, Doughty AS, Johanson JF, Greenlaw RL. Colonoscopic withdrawal times and adenoma detection during screening colonoscopy. N Engl J Med 2006;355:2533-41.  Back to cited text no. 17
    
18.
Mori Y, Kudo SE, Berzin TM, Misawa M, Takeda K. Computer-aided diagnosis for colonoscopy. Endoscopy 2017;49:813-9.  Back to cited text no. 18
    
19.
Fernandez-Esparrach G, Bernal J, Lopez-Ceron M, Córdova H, Sánchez-Montes C, Rodríguez de Miguel C, et al. Exploring the clinical potential of an automatic colonic polyp detection method based on the creation of energy maps. Endoscopy 2016;48:837-42.  Back to cited text no. 19
    
20.
Urban G, Tripathi P, Alkayali T, Mittal M, Jalali F, Karnes W, et al. Deep learning localizes and identifies polyps in real time with 96% accuracy in screening colonoscopy. Gastroenterology 2018;155:1069-78.  Back to cited text no. 20
    
21.
Halpern Z, Gross SA, Gralnek IM, Shpak B, Pochapin M, Hoffman A, et al. Comparison of adenoma detection and miss rates between a novel balloon colonoscope and standard colonoscopy: A randomized tandem study. Endoscopy 2015;47:238-44.  Back to cited text no. 21
    
22.
Chin M, Karnes W, Jamal MM, Lee JG, Lee R, Samarasena J, et al. Use of the endocuff during routine colonoscopy examination improves adenoma detection: A meta-analysis. World J Gastroenterol 2016;22:9642-9.  Back to cited text no. 22
    
23.
Barclay RL, Vicari JJ, Doughty AS, Johanson JF, Greenlaw RL. Colonoscopic withdrawal times and adenoma detection during screening colonoscopy. N Engl J Med 2006;355:2533–41.  Back to cited text no. 23
    
24.
Horton N, garber A, Hasson H, Lopez R, Burke CA. Impact of single- vs. split-dose low-volume bowel preparations on bowel movement kinetics, patient inconvenience, and polyp detection: A prospective trial. Am J Gastroenterol 2016;111:1330-7.  Back to cited text no. 24
    
25.
Misawa M, Kudo SE, Mori Y, Cho T, Kataoka S, Yamauchi A, et al. Artificial intelligence-assisted polyp detection for colonoscopy: Initial experience. Gastroenterology 2018;154:2027-9 e3.  Back to cited text no. 25
    

Top
Correspondence Address:
Dr. Jin Huang
Department of Digestive Endoscopy, No. 988 Hospital of Joint Logistic Support Force of PLA, Zhengzhou - 450000
China
Login to access the Email id

Source of Support: None, Conflict of Interest: None


DOI: 10.4103/sjg.SJG_377_19

Rights and Permissions


    Figures

  [Figure 1]
 
 
    Tables

  [Table 1], [Table 2], [Table 3], [Table 4], [Table 5]

This article has been cited by
1 Artificial intelligence in colonoscopy: A review on the current status
Solveig Linnea Veen Larsen, Yuichi Mori
DEN Open. 2022; 2(1)
[Pubmed] | [DOI]
2 Detection of colorectal lesions during colonoscopy
Hiroaki Ikematsu, Tatsuro Murano, Kensuke Shinmura
DEN Open. 2022; 2(1)
[Pubmed] | [DOI]
3 Implementation of artificial intelligence in upper gastrointestinal endoscopy
Sayaka Nagao, Yasuhiro Tani, Junichi Shibata, Yosuke Tsuji, Tomohiro Tada, Ryu Ishihara, Mitsuhiro Fujishiro
DEN Open. 2022; 2(1)
[Pubmed] | [DOI]
4 Pilot study of a new freely available computer-aided polyp detection system in clinical practice
Thomas J. Lux, Michael Banck, Zita Saßmannshausen, Joel Troya, Adrian Krenzer, Daniel Fitting, Boban Sudarevic, Wolfram G. Zoller, Frank Puppe, Alexander Meining, Alexander Hann
International Journal of Colorectal Disease. 2022;
[Pubmed] | [DOI]
5 Real-time colorectal polyp detection using a novel computer-aided detection system (CADe): a feasibility study
E. Soons, T. Rath, Y. Hazewinkel, W. A. van Dop, D. Esposito, P. A. Testoni, P. D. Siersema
International Journal of Colorectal Disease. 2022;
[Pubmed] | [DOI]
6 Randomized Clinical Trials of Machine Learning Interventions in Health Care
Deborah Plana, Dennis L. Shung, Alyssa A. Grimshaw, Anurag Saraf, Joseph J. Y. Sung, Benjamin H. Kann
JAMA Network Open. 2022; 5(9): e2233946
[Pubmed] | [DOI]
7 Impact of Artificial Intelligence on Colonoscopy Surveillance After Polyp Removal: A Pooled Analysis of Randomized Trials
Yuichi Mori, Pu Wang, Magnus Lřberg, Masashi Misawa, Alessandro Repici, Marco Spadaccini, Loredana Correale, Giulio Antonelli, Honggang Yu, Dexin Gong, Misaki Ishiyama, Shin-ei Kudo, Shunsuke Kamba, Kazuki Sumiyama, Yutaka Saito, Haruo Nishino, Peixi Liu, Jeremy R. Glissen Brown, Nabil M. Mansour, Seth A. Gross, Mette Kalager, Michael Bretthauer, Douglas K. Rex, Prateek Sharma, Tyler M. Berzin, Cesare Hassan
Clinical Gastroenterology and Hepatology. 2022;
[Pubmed] | [DOI]
8 The application of artificial intelligence in improving colonoscopic adenoma detection rate: Where are we and where are we going
Peiling Gan, Peiling Li, Huifang Xia, Xian Zhou, Xiaowei Tang
Gastroenterología y Hepatología. 2022;
[Pubmed] | [DOI]
9 Cost-effectiveness of artificial intelligence for screening colonoscopy: a modelling study
Miguel Areia, Yuichi Mori, Loredana Correale, Alessandro Repici, Michael Bretthauer, Prateek Sharma, Filipe Taveira, Marco Spadaccini, Giulio Antonelli, Alanna Ebigbo, Shin-ei Kudo, Julia Arribas, Ishita Barua, Michal F Kaminski, Helmut Messmann, Douglas K Rex, Mário Dinis-Ribeiro, Cesare Hassan
The Lancet Digital Health. 2022;
[Pubmed] | [DOI]
10 Strengths and Weaknesses of an Artificial Intelligence Polyp Detection Program as Assessed by a High-Detecting Endoscopist
Douglas K. Rex, Yuichi Mori, Prateek Sharma, Rachel E. Lahr, Krishna C. Vemulapalli, Cesare Hassan
Gastroenterology. 2022;
[Pubmed] | [DOI]
11 High-quality Studies of Artificial Intelligence in Colonoscopy Illuminate a Next Important Step
Amisha Ahuja, Yuichi Mori
Gastroenterology. 2022;
[Pubmed] | [DOI]
12 Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement
Helmut Messmann, Raf Bisschops, Giulio Antonelli, Diogo Libânio, Pieter Sinonquel, Mohamed Abdelrahim, Omer F. Ahmad, Miguel Areia, Jacques J. G. H. M. Bergman, Pradeep Bhandari, Ivo Boskoski, Evelien Dekker, Dirk Domagk, Alanna Ebigbo, Tom Eelbode, Rami Eliakim, Michael Häfner, Rehan J. Haidry, Rodrigo Jover, Michal F. Kaminski, Roman Kuvaev, Yuichi Mori, Maxime Palazzo, Alessandro Repici, Emanuele Rondonotti, Matthew D. Rutter, Yutaka Saito, Prateek Sharma, Cristiano Spada, Marco Spadaccini, Andrew Veitch, Ian M. Gralnek, Cesare Hassan, Mario Dinis-Ribeiro
Endoscopy. 2022;
[Pubmed] | [DOI]
13 A video based benchmark data set (ENDOTEST) to evaluate computer-aided polyp detection systems
Daniel Fitting, Adrian Krenzer, Joel Troya, Michael Banck, Boban Sudarevic, Markus Brand, Wolfgang Böck, Wolfram G. Zoller, Thomas Rösch, Frank Puppe, Alexander Meining, Alexander Hann
Scandinavian Journal of Gastroenterology. 2022; : 1
[Pubmed] | [DOI]
14 Comparing the number and relevance of false activations between 2 artificial intelligence computer-aided detection systems: the NOISE study
Marco Spadaccini, Cesare Hassan, Ludovico Alfarone, Leonardo Da Rio, Roberta Maselli, Silvia Carrara, Piera Alessia Galtieri, Gaia Pellegatta, Alessandro Fugazza, Glenn Koleth, James Emmanuel, Andrea Anderloni, Yuichi Mori, Michael B. Wallace, Prateek Sharma, Alessandro Repici
Gastrointestinal Endoscopy. 2022;
[Pubmed] | [DOI]
15 Polypectomy for Diminutive and Small Colorectal Polyps
Melissa Zarandi-Nowroozi, Roupen Djinbachian, Daniel von Renteln
Gastrointestinal Endoscopy Clinics of North America. 2022;
[Pubmed] | [DOI]
16 Polyp detection on video colonoscopy using a hybrid 2D/3D CNN
Juana González-Bueno Puyal, Patrick Brandao, Omer F. Ahmad, Kanwal K. Bhatia, Daniel Toth, Rawen Kader, Laurence Lovat, Peter Mountney, Danail Stoyanov
Medical Image Analysis. 2022; : 102625
[Pubmed] | [DOI]
17 Artificial intelligence-assisted colonoscopy: a narrative review of current data and clinical applications
JW Li, LM Wang, TL Ang
Singapore Medical Journal. 2022; 63(3): 118
[Pubmed] | [DOI]
18 Performance of Convolutional Neural Networks for Polyp Localization on Public Colonoscopy Image Datasets
Alba Nogueira-Rodríguez, Miguel Reboiro-Jato, Daniel Glez-Peńa, Hugo López-Fernández
Diagnostics. 2022; 12(4): 898
[Pubmed] | [DOI]
19 Gastrointestinal Tract Polyp Anomaly Segmentation on Colonoscopy Images Using Graft-U-Net
Muhammad Ramzan, Mudassar Raza, Muhammad Imran Sharif, Seifedine Kadry
Journal of Personalized Medicine. 2022; 12(9): 1459
[Pubmed] | [DOI]
20 Discovering the first FDA-approved computer-aided polyp detection system
Marco Spadaccini, Alessandro De Marco, Gianluca Franchellucci, Prateek Sharma, Cesare Hassan, Alessandro Repici
Future Oncology. 2022;
[Pubmed] | [DOI]
21 Artificial Intelligence-Aid Colonoscopy Vs. Conventional Colonoscopy for Polyp and Adenoma Detection: A Systematic Review of 7 Discordant Meta-Analyses
Hui Pan, Mingyan Cai, Qi Liao, Yong Jiang, Yige Liu, Xiaolong Zhuang, Ying Yu
Frontiers in Medicine. 2022; 8
[Pubmed] | [DOI]
22 From advanced diagnosis to advanced resection in early neoplastic colorectal lesions: Never-ending and trending topics in the 2020s
Francesco Auriemma, Sandro Sferrazza, Mario Bianchetti, Maria Flavia Savarese, Laura Lamonaca, Danilo Paduano, Nicole Piazza, Enrica Giuffrida, Lupe Sanchez Mete, Alessandra Tucci, Sebastian Manuel Milluzzo, Chiara Iannelli, Alessandro Repici, Benedetto Mangiavillano
World Journal of Gastrointestinal Surgery. 2022; 14(7): 632
[Pubmed] | [DOI]
23 Scoping out the future: The application of artificial intelligence to gastrointestinal endoscopy
Scott B Minchenberg, Trent Walradt, Jeremy R Glissen Brown
World Journal of Gastrointestinal Oncology. 2022; 14(5): 989
[Pubmed] | [DOI]
24 Does computer-aided diagnostic endoscopy improve the detection of commonly missed polyps? A meta-analysis
Arun Sivananthan, Scarlet Nazarian, Lakshmana Ayaru, Kinesh Patel, Hutan Ashrafian, Ara Darzi, Nisha Patel
Clinical Endoscopy. 2022; 55(3): 355
[Pubmed] | [DOI]
25 Artificial Intelligence in Lower Gastrointestinal Endoscopy: The Current Status and Future Perspective
Sebastian Manuel Milluzzo, Paola Cesaro, Leonardo Minelli Grazioli, Nicola Olivari, Cristiano Spada
Clinical Endoscopy. 2021; 54(3): 329
[Pubmed] | [DOI]
26 Artificial Intelligence in Colorectal Cancer Screening, Diagnosis and Treatment. A New Era
Athanasia Mitsala, Christos Tsalikidis, Michail Pitiakoudis, Constantinos Simopoulos, Alexandra K. Tsaroucha
Current Oncology. 2021; 28(3): 1581
[Pubmed] | [DOI]
27 Computer-Aided Detection False Positives in Colonoscopy
Yu-Hsi Hsieh, Chia-Pei Tang, Chih-Wei Tseng, Tu-Liang Lin, Felix W. Leung
Diagnostics. 2021; 11(6): 1113
[Pubmed] | [DOI]
28 Artificial intelligence for identification and characterization of colonic polyps
Nasim Parsa, Michael F. Byrne
Therapeutic Advances in Gastrointestinal Endoscopy. 2021; 14: 2631774521
[Pubmed] | [DOI]
29 Role of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review
Jiamin Yin, Kee Yuan Ngiam, Hock Hai Teo
Journal of Medical Internet Research. 2021; 23(4): e25759
[Pubmed] | [DOI]
30 Diagnostic Accuracy of Artificial Intelligence and Computer-Aided Diagnosis for the Detection and Characterization of Colorectal Polyps: Systematic Review and Meta-analysis
Scarlet Nazarian, Ben Glover, Hutan Ashrafian, Ara Darzi, Julian Teare
Journal of Medical Internet Research. 2021; 23(7): e27370
[Pubmed] | [DOI]
31 Artificial intelligence in colonoscopy
Joel Joseph, Ella Marie LePage, Catherine Phillips Cheney, Rishi Pawa
World Journal of Gastroenterology. 2021; 27(29): 4802
[Pubmed] | [DOI]
32 Artificial intelligence in gastroenterology: A state-of-the-art review
Paul T Kröner, Megan ML Engels, Benjamin S Glicksberg, Kipp W Johnson, Obaie Mzaik, Jeanin E van Hooft, Michael B Wallace, Hashem B El-Serag, Chayakrit Krittanawong
World Journal of Gastroenterology. 2021; 27(40): 6794
[Pubmed] | [DOI]
33 Artificial intelligence-assisted colonoscopy: A review of current state of practice and research
Mahsa Taghiakbari, Yuichi Mori, Daniel von Renteln
World Journal of Gastroenterology. 2021; 27(47): 8103
[Pubmed] | [DOI]
34 Artificial intelligence and colorectal cancer: How far can you go?
Rita Alloro, Emanuele Sinagra
WArtificial Intelligence in Cancer. 2021; 2(2): 7
[Pubmed] | [DOI]
35 Colonoscopy and artificial intelligence: Bridging the gap or a gap needing to be bridged?
Tiing Leong Ang, James Weiquan Li
Artificial Intelligence in Gastrointestinal Endoscopy. 2021; 2(2): 36
[Pubmed] | [DOI]
36 Utility of artificial intelligence in colonoscopy
Niel Shah, Abhilasha Jyala, Harish Patel, Jasbir Makker
Artificial Intelligence in Gastrointestinal Endoscopy. 2021; 2(3): 78
[Pubmed] | [DOI]
37 Utility of artificial intelligence in colonoscopy
Niel Shah, Abhilasha Jyala, Harish Patel, Jasbir Makker
Artificial Intelligence in Gastrointestinal Endoscopy. 2021; 2(3): 79
[Pubmed] | [DOI]
38 Artificial intelligence and colonoscopy - enhancements and improvements
Byung Soo Yoo, Steve M D'Souza, Kevin Houston, Ankit Patel, James Lau, Alsiddig Elmahdi, Parth J Parekh, David Johnson
Artificial Intelligence in Gastrointestinal Endoscopy. 2021; 2(4): 157
[Pubmed] | [DOI]
39 Artificial intelligence in polyp detection - where are we and where are we headed?
Kristen E Dougherty, Vatche J Melkonian, Grace A Montenegro
Artificial Intelligence in Gastrointestinal Endoscopy. 2021; 2(6): 211
[Pubmed] | [DOI]
40 Development of multi-class computer-aided diagnostic systems using the NICE/JNET classifications for colorectal lesions
Yuki Okamoto, Shigeto Yoshida, Seiji Izakura, Daisuke Katayama, Ryuichi Michida, Tetsushi Koide, Toru Tamaki, Yuki Kamigaichi, Hirosato Tamari, Yasutsugu Shimohara, Tomoyuki Nishimura, Katsuaki Inagaki, Hidenori Tanaka, Ken Yamashita, Kyoku Sumimoto, Shiro Oka, Shinji Tanaka
Journal of Gastroenterology and Hepatology. 2021;
[Pubmed] | [DOI]
41 Artificial intelligence and colonoscopy experience: lessons from two randomised trials
Alessandro Repici, Marco Spadaccini, Giulio Antonelli, Loredana Correale, Roberta Maselli, Piera Alessia Galtieri, Gaia Pellegatta, Antonio Capogreco, Sebastian Manuel Milluzzo, Gianluca Lollo, Dhanai Di Paolo, Matteo Badalamenti, Elisa Ferrara, Alessandro Fugazza, Silvia Carrara, Andrea Anderloni, Emanuele Rondonotti, Arnaldo Amato, Andrea De Gottardi, Cristiano Spada, Franco Radaelli, Victor Savevski, Michael B Wallace, Prateek Sharma, Thomas Rösch, Cesare Hassan
Gut. 2021; : gutjnl-202
[Pubmed] | [DOI]
42 Artificial Intelligence in Endoscopy
Alexander Hann, Alexander Meining
Visceral Medicine. 2021; 37(6): 471
[Pubmed] | [DOI]
43 Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: a systematic review and network meta-analysis
Marco Spadaccini, Andrea Iannone, Roberta Maselli, Matteo Badalamenti, Madhav Desai, Viveksandeep Thoguluva Chandrasekar, Harsh K Patel, Alessandro Fugazza, Gaia Pellegatta, Piera Alessia Galtieri, Gianluca Lollo, Silvia Carrara, Andrea Anderloni, Douglas K Rex, Victor Savevski, Michael B Wallace, Pradeep Bhandari, Thomas Roesch, Ian M Gralnek, Prateek Sharma, Cesare Hassan, Alessandro Repici
The Lancet Gastroenterology & Hepatology. 2021; 6(10): 793
[Pubmed] | [DOI]
44 Artificial Intelligence-Aided Colonoscopy for Polyp Detection: A Systematic Review and Meta-Analysis of Randomized Clinical Trials
Yuanchuan Zhang, Xubing zhang, Qingbin Wu, Chaoyang Gu, Ziqiang Wang
Journal of Laparoendoscopic & Advanced Surgical Techniques. 2021; 31(10): 1143
[Pubmed] | [DOI]
45 A Polyp Worth Removing
William E. Karnes, David A. Johnson, Tyler M. Berzin, Seth A. Gross, John J. Vargo, Prateek Sharma, Robin Zachariah, Jason B. Samarasena, Joseph C. Anderson
Journal of Clinical Gastroenterology. 2021; Publish Ah
[Pubmed] | [DOI]
46 Artificial intelligence can increase the detection rate of colorectal polyps and adenomas: a systematic review and meta-analysis
Jianglei Li, Jiaxi Lu, Jin Yan, Yuyong Tan, Deliang Liu
European Journal of Gastroenterology & Hepatology. 2021; 33(8): 1041
[Pubmed] | [DOI]
47 Computer-aided detection of colorectal polyps using a newly generated deep convolutional neural network: from development to first clinical experience
Lukas Pfeifer, Clemens Neufert, Moritz Leppkes, Maximilian J. Waldner, Michael Häfner, Albert Beyer, Arthur Hoffman, Peter D. Siersema, Markus F. Neurath, Timo Rath
European Journal of Gastroenterology & Hepatology. 2021; 33(1S): e662
[Pubmed] | [DOI]
48 A Gratifying Step forward for the Application of Artificial Intelligence in the Field of Endoscopy: A Narrative Review
Yixin Xu, Yulin Tan, Yibo Wang, Jie Gao, Dapeng Wu, Xuezhong Xu
Surgical Laparoscopy, Endoscopy & Percutaneous Techniques. 2021; 31(2): 254
[Pubmed] | [DOI]
49 Artificial intelligence in endoscopy: Present and future perspectives
Kazuki Sumiyama, Toshiki Futakuchi, Shunsuke Kamba, Hiroaki Matsui, Naoto Tamai
Digestive Endoscopy. 2021; 33(2): 218
[Pubmed] | [DOI]
50 Current status and future perspective on artificial intelligence for lower endoscopy
Masashi Misawa, Shin-ei Kudo, Yuichi Mori, Yasuharu Maeda, Yushi Ogawa, Katsuro Ichimasa, Toyoki Kudo, Kunihiko Wakamura, Takemasa Hayashi, Hideyuki Miyachi, Toshiyuki Baba, Fumio Ishida, Hayato Itoh, Masahiro Oda, Kensaku Mori
Digestive Endoscopy. 2021; 33(2): 273
[Pubmed] | [DOI]
51 Artificial intelligence for polyp detection during colonoscopy: a systematic review and meta-analysis
Ishita Barua, Daniela Guerrero Vinsard, Henriette C. Jodal, Magnus Lřberg, Mette Kalager, Řyvind Holme, Masashi Misawa, Michael Bretthauer, Yuichi Mori
Endoscopy. 2021; 53(03): 277
[Pubmed] | [DOI]
52 Establishing key research questions for the implementation of artificial intelligence in colonoscopy: a modified Delphi method
Omer F. Ahmad, Yuichi Mori, Masashi Misawa, Shin-ei Kudo, John T. Anderson, Jorge Bernal, Tyler M. Berzin, Raf Bisschops, Michael F. Byrne, Peng-Jen Chen, James E. East, Tom Eelbode, Daniel S. Elson, Suryakanth R. Gurudu, Aymeric Histace, William E. Karnes, Alessandro Repici, Rajvinder Singh, Pietro Valdastri, Michael B. Wallace, Pu Wang, Danail Stoyanov, Laurence B. Lovat
Endoscopy. 2021; 53(09): 893
[Pubmed] | [DOI]
53 Amalgamation of cloud-based colonoscopy videos with patient-level metadata to facilitate large-scale machine learning
Rajesh N. Keswani, Daniel Byrd, Florencia Garcia Vicente, J. Alex Heller, Matthew Klug, Nikhilesh R. Mazumder, Jordan Wood, Anthony D. Yang, Mozziyar Etemadi
Endoscopy International Open. 2021; 09(02): E233
[Pubmed] | [DOI]
54 Impact of real-time use of artificial intelligence in improving adenoma detection during colonoscopy: A systematic review and meta-analysis
Munish Ashat, Jagpal Singh Klair, Dhruv Singh, Arvind Rangarajan Murali, Rajesh Krishnamoorthi
Endoscopy International Open. 2021; 09(04): E513
[Pubmed] | [DOI]
55 Artificial intelligence for colonoscopy: the new Silk Road
Alessandro Repici, Cesare Hassan
Endoscopy. 2021; 53(03): 285
[Pubmed] | [DOI]
56 Performance of artificial intelligence in colonoscopy for adenoma and polyp detection: a systematic review and meta-analysis
Cesare Hassan, Marco Spadaccini, Andrea Iannone, Roberta Maselli, Manol Jovani, Viveksandeep Thoguluva Chandrasekar, Giulio Antonelli, Honggang Yu, Miguel Areia, Mario Dinis-Ribeiro, Pradeep Bhandari, Prateek Sharma, Douglas K. Rex, Thomas Rösch, Michael Wallace, Alessandro Repici
Gastrointestinal Endoscopy. 2021; 93(1): 77
[Pubmed] | [DOI]
57 Artificial intelligence (computer-assisted detection) is the most recent novel approach to increase adenoma detection
Felix W. Leung, Yu-Hsi Hsieh
Gastrointestinal Endoscopy. 2021; 93(1): 86
[Pubmed] | [DOI]
58 Development of a computer-aided detection system for colonoscopy and a publicly accessible large colonoscopy video database (with video)
Masashi Misawa, Shin-ei Kudo, Yuichi Mori, Kinichi Hotta, Kazuo Ohtsuka, Takahisa Matsuda, Shoichi Saito, Toyoki Kudo, Toshiyuki Baba, Fumio Ishida, Hayato Itoh, Masahiro Oda, Kensaku Mori
Gastrointestinal Endoscopy. 2021; 93(4): 960
[Pubmed] | [DOI]
59 Impact of the clinical use of artificial intelligence–assisted neoplasia detection for colonoscopy: a large-scale prospective, propensity score–matched study (with video)
Misaki Ishiyama, Shin-ei Kudo, Masashi Misawa, Yuichi Mori, Yasuhara Maeda, Katsuro Ichimasa, Toyoki Kudo, Takemasa Hayashi, Kunihiko Wakamura, Hideyuki Miyachi, Fumio Ishida, Hayato Itoh, Masahiro Oda, Kensaku Mori
Gastrointestinal Endoscopy. 2021;
[Pubmed] | [DOI]
60 Polyp detection and false-positive rates by computer-aided analysis of withdrawal-phase videos of colonoscopy of the right-sided colon segment in a randomized controlled trial comparing water exchange and air insufflation
Chia-Pei Tang, Tu-Liang Lin, Yu-Hsi Hsieh, Chen-Hung Hsieh, Chih-Wei Tseng, Felix W. Leung
Gastrointestinal Endoscopy. 2021;
[Pubmed] | [DOI]
61 Artificial intelligence-assisted colonoscopy: A prospective, multicenter, randomized controlled trial of polyp detection
Lei Xu, Xinjue He, Jianbo Zhou, Jie Zhang, Xinli Mao, Guoliang Ye, Qiang Chen, Feng Xu, Jianzhong Sang, Jun Wang, Yong Ding, Youming Li, Chaohui Yu
Cancer Medicine. 2021; 10(20): 7184
[Pubmed] | [DOI]
62 Real-time polyp detection model using convolutional neural networks
Alba Nogueira-Rodríguez, Rubén Domínguez-Carbajales, Fernando Campos-Tato, Jesús Herrero, Manuel Puga, David Remedios, Laura Rivas, Eloy Sánchez, Águeda Iglesias, Joaquín Cubiella, Florentino Fdez-Riverola, Hugo López-Fernández, Miguel Reboiro-Jato, Daniel Glez-Peńa
Neural Computing and Applications. 2021;
[Pubmed] | [DOI]
63 Künstliche Intelligenz in der Endoskopie – neue Wege zur Polypendetektion und Charakterisierung
H.- D. Allescher, M. Mangold, V. Weingart
Der Gastroenterologe. 2021; 16(1): 3
[Pubmed] | [DOI]
64 Impact of artificial intelligence on colorectal polyp detection
Giulio Antonelli, Matteo Badalamenti, Cesare Hassan, Alessandro Repici
Best Practice & Research Clinical Gastroenterology. 2021; 52-53: 101713
[Pubmed] | [DOI]
65 Striving for quality improvement: can artificial intelligence help?
P. Sinonquel, R. Bisschops
Best Practice & Research Clinical Gastroenterology. 2021; 52-53: 101722
[Pubmed] | [DOI]
66 Current status and limitations of artificial intelligence in colonoscopy
Alexander Hann, Joel Troya, Daniel Fitting
United European Gastroenterology Journal. 2021; 9(5): 527
[Pubmed] | [DOI]
67 Effect of artificial intelligence-aided colonoscopy for adenoma and polyp detection: a meta-analysis of randomized clinical trials
Ding Huang, Jingyi Shen, Jiaze Hong, Yi Zhang, Senjie Dai, Nannan Du, Mengting Zhang, Daxin Guo
International Journal of Colorectal Disease. 2021;
[Pubmed] | [DOI]
68 Real-time computer aided colonoscopy versus standard colonoscopy for improving adenoma detection rate: A meta-analysis of randomized-controlled trials
Babu P. Mohan, Antonio Facciorusso, Shahab R. Khan, Saurabh Chandan, Lena L. Kassab, Paraskevas Gkolfakis, Georgios Tziatzios, Konstantinos Triantafyllou, Douglas G. Adler
EClinicalMedicine. 2020; 29-30: 100622
[Pubmed] | [DOI]
69 The impact of deep convolutional neural network-based artificial intelligence on colonoscopy outcomes: A systematic review with meta-analysis
Muhammad Aziz, Rawish Fatima, Charles Dong, Wade Lee-Smith, Ali Nawras
Journal of Gastroenterology and Hepatology. 2020; 35(10): 1676
[Pubmed] | [DOI]
70 Artificial intelligence in luminal endoscopy
Shraddha Gulati, Andrew Emmanuel, Mehul Patel, Sophie Williams, Amyn Haji, Bu’Hussain Hayee, Helmut Neumann
Therapeutic Advances in Gastrointestinal Endoscopy. 2020; 13: 2631774520
[Pubmed] | [DOI]
71 Potential applications of artificial intelligence in colorectal polyps and cancer: Recent advances and prospects
Ke-Wei Wang, Ming Dong
World Journal of Gastroenterology. 2020; 26(34): 5090
[Pubmed] | [DOI]
72 Artificial intelligence technologies for the detection of colorectal lesions: The future is now
Simona Attardo, Viveksandeep Thoguluva Chandrasekar, Marco Spadaccini, Roberta Maselli, Harsh K Patel, Madhav Desai, Antonio Capogreco, Matteo Badalamenti, Piera Alessia Galtieri, Gaia Pellegatta, Alessandro Fugazza, Silvia Carrara, Andrea Anderloni, Pietro Occhipinti, Cesare Hassan, Prateek Sharma, Alessandro Repici
World Journal of Gastroenterology. 2020; 26(37): 5606
[Pubmed] | [DOI]
73 Use of artificial intelligence in improving adenoma detection rate during colonoscopy: Might both endoscopists and pathologists be further helped
Emanuele Sinagra, Matteo Badalamenti, Marcello Maida, Marco Spadaccini, Roberta Maselli, Francesca Rossi, Giuseppe Conoscenti, Dario Raimondo, Socrate Pallio, Alessandro Repici, Andrea Anderloni
World Journal of Gastroenterology. 2020; 26(39): 5911
[Pubmed] | [DOI]
74 Artificial intelligence-aided colonoscopy: Recent developments and future perspectives
Giulio Antonelli, Paraskevas Gkolfakis, Georgios Tziatzios, Ioannis S Papanikolaou, Konstantinos Triantafyllou, Cesare Hassan
World Journal of Gastroenterology. 2020; 26(47): 7436
[Pubmed] | [DOI]



 

Top
  
 
  Search
 
  
  
    Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
 Related articles
    Email Alert *
    Add to My List *
* Registration required (free)  


    Abstract
   Introduction
    Materials and Me...
   Results
   Discussion
    References
    Article Figures
    Article Tables

 Article Access Statistics
    Viewed7780    
    Printed122    
    Emailed0    
    PDF Downloaded1286    
    Comments [Add]    
    Cited by others 74    

Recommend this journal