Xiaogang Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaogang Liu has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
Di Zhang
Department of Gastroenterology, Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital, Chengdu, China
2 shared publicationsLiangping Li
Department of Gastroenterology, Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital, Chengdu, China
2 shared publicationsMengtian Tu
Department of Gastroenterology, Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital, Chengdu, China
2 shared publicationsPeixi Liu
Department of Gastroenterology, Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital, Chengdu, China
2 shared publications- Pu Wang
Department of Gastroenterology, Sichuan Provincial People’s Hospital, University of Electronic Science and Technology of China, China
2 shared publications - Tyler M. Berzin
Division of Gastroenterology, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA
2 shared publications
Latest Publications
- Open Access
- 7 June 2019
- Published by Georg Thieme Verlag KG in Endoscopy
- Vol. 52 (03) , E82-E83
Clip-and-snare traction facilitates difficult biliary cannulation during ERCP
The adequate exposure of the ampullary orifice and reliable fixation of the duodenal papilla are always the basic principles of successful cannulation during endoscopic retrograde cholangiopancreatography (ERCP). In recent years, several traction strategies have proven to be effective in eversion of a hidden papilla within a large diverticulum, such as using a cannula [1], endobiliary forceps [2], or the SpyBite [3] to manipulate the papilla. However, with the above coaxial lifting strategies, it is not possible to optionally adjust the direction and intensity of traction because of interference with the duodenoscope. Therefore, here we report a novel clip-and-snare traction (CST) method to effectively accomplish successful biliary cannulation ([Video 1]), which had not been possible with guidewire-aided cannulation techniques. Video 1 In a patient undergoing endoscopic retrograde cholangiopancreatography for biliary stones, an intradiverticular papilla meant access to the bile duct failed, despite multiple attempts at traditional guidewire-aided cannulation. An endoclip was inserted through the endoscope to grasp the papilla and was interlinked with a snare. The clip-and-snare traction (CST) tools were used to pull the papilla out of the diverticulum, thereby clearly exposing the ampullary orifice. With the CST-assisted cannulation technique, the first guidewire was rapidly advanced into the pancreatic duct and, after several attempts, the bile duct was successfully cannulated with a second guidewire. The patient was being treated by ERCP for common bile duct stones. Attempts were made to access the biliary tree using the guidewire-aided cannulation technique; however, as the ampulla of Vater was hidden inside a diverticulum, attempts to gain access were unsuccessful and, after 15 minutes, the mucosa of the papilla became swollen, with the orifice of papilla becoming obscured ([Fig. 1 a]). Subsequently, the CST method was applied to pull the papilla back out of the diverticulum and the ampullary orifice was eventually turned outward. After several attempts at cannulation, the guidewire smoothly advanced into pancreatic duct ([Fig. 1 b, c]). Attempts were made to perform biliary cannulation in the region towards the upper left orifice of the papilla using a sphincterotome with a second guidewire, and a successful cannulation of the bile duct was finally achieved ([Fig. 1 d, e]). In this patient, the independent lifting technique of CST was employed to optimize the position of the papilla and its orifice by free movements of pull, push, pick, and rotate ([Fig. 2]), which led to successful biliary cannulation in a short time. As the CST method is very simple to manipulate, it may be applied to routine biliary cannulation in any patients where a lifting technique is required. Endoscopy_UCTN_Code_TTT_1AQ_2AC * Contributed equally to this work – both 1st author
- 7 June 2019
- Published by Georg Thieme Verlag KG in Endoscopy
- Vol. 52 (03) , E82-E83
Open AccessClip-and-snare traction facilitates difficult biliary cannulation during ERCP
The adequate exposure of the ampullary orifice and reliable fixation of the duodenal papilla are always the basic principles of successful cannulation during endoscopic retrograde cholangiopancreatography (ERCP). In recent years, several traction strategies have proven to be effective in eversion of a hidden papilla within a large diverticulum, such as using a cannula [1], endobiliary forceps [2], or the SpyBite [3] to manipulate the papilla. However, with the above coaxial lifting strategies, it is not possible to optionally adjust the direction and intensity of traction because of interference with the duodenoscope. Therefore, here we report a novel clip-and-snare traction (CST) method to effectively accomplish successful biliary cannulation ([Video 1]), which had not been possible with guidewire-aided cannulation techniques. Video 1 In a patient undergoing endoscopic retrograde cholangiopancreatography for biliary stones, an intradiverticular papilla meant access to the bile duct failed, despite multiple attempts at traditional guidewire-aided cannulation. An endoclip was inserted through the endoscope to grasp the papilla and was interlinked with a snare. The clip-and-snare traction (CST) tools were used to pull the papilla out of the diverticulum, thereby clearly exposing the ampullary orifice. With the CST-assisted cannulation technique, the first guidewire was rapidly advanced into the pancreatic duct and, after several attempts, the bile duct was successfully cannulated with a second guidewire. The patient was being treated by ERCP for common bile duct stones. Attempts were made to access the biliary tree using the guidewire-aided cannulation technique; however, as the ampulla of Vater was hidden inside a diverticulum, attempts to gain access were unsuccessful and, after 15 minutes, the mucosa of the papilla became swollen, with the orifice of papilla becoming obscured ([Fig. 1 a]). Subsequently, the CST method was applied to pull the papilla back out of the diverticulum and the ampullary orifice was eventually turned outward. After several attempts at cannulation, the guidewire smoothly advanced into pancreatic duct ([Fig. 1 b, c]). Attempts were made to perform biliary cannulation in the region towards the upper left orifice of the papilla using a sphincterotome with a second guidewire, and a successful cannulation of the bile duct was finally achieved ([Fig. 1 d, e]). In this patient, the independent lifting technique of CST was employed to optimize the position of the papilla and its orifice by free movements of pull, push, pick, and rotate ([Fig. 2]), which led to successful biliary cannulation in a short time. As the CST method is very simple to manipulate, it may be applied to routine biliary cannulation in any patients where a lifting technique is required. Endoscopy_UCTN_Code_TTT_1AQ_2AC * Contributed equally to this work – both 1st author
- Top Cited PapersOpen Access
Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study
Objective The effect of colonoscopy on colorectal cancer mortality is limited by several factors, among them a certain miss rate, leading to limited adenoma detection rates (ADRs). We investigated the effect of an automatic polyp detection system based on deep learning on polyp detection rate and ADR. Design In an open, non-blinded trial, consecutive patients were prospectively randomised to undergo diagnostic colonoscopy with or without assistance of a real-time automatic polyp detection system providing a simultaneous visual notice and sound alarm on polyp detection. The primary outcome was ADR. Results Of 1058 patients included, 536 were randomised to standard colonoscopy, and 522 were randomised to colonoscopy with computer-aided diagnosis. The artificial intelligence (AI) system significantly increased ADR (29.1%vs20.3%, pConclusions In a low prevalent ADR population, an automatic polyp detection system during colonoscopy resulted in a significant increase in the number of diminutive adenomas detected, as well as an increase in the rate of hyperplastic polyps. The cost–benefit ratio of such effects has to be determined further. Trial registration number ChiCTR-DDD-17012221; Results.
Top Cited PapersOpen AccessReal-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study
Objective The effect of colonoscopy on colorectal cancer mortality is limited by several factors, among them a certain miss rate, leading to limited adenoma detection rates (ADRs). We investigated the effect of an automatic polyp detection system based on deep learning on polyp detection rate and ADR. Design In an open, non-blinded trial, consecutive patients were prospectively randomised to undergo diagnostic colonoscopy with or without assistance of a real-time automatic polyp detection system providing a simultaneous visual notice and sound alarm on polyp detection. The primary outcome was ADR. Results Of 1058 patients included, 536 were randomised to standard colonoscopy, and 522 were randomised to colonoscopy with computer-aided diagnosis. The artificial intelligence (AI) system significantly increased ADR (29.1%vs20.3%, pConclusions In a low prevalent ADR population, an automatic polyp detection system during colonoscopy resulted in a significant increase in the number of diminutive adenomas detected, as well as an increase in the rate of hyperplastic polyps. The cost–benefit ratio of such effects has to be determined further. Trial registration number ChiCTR-DDD-17012221; Results.
- Top Cited Papers
- 10 October 2018
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 2 (10) , 741-748
Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy
The detection and removal of precancerous polyps via colonoscopy is the gold standard for the prevention of colon cancer. However, the detection rate of adenomatous polyps can vary significantly among endoscopists. Here, we show that a machine-learning algorithm can detect polyps in clinical colonoscopies, in real time and with high sensitivity and specificity. We developed the deep-learning algorithm by using data from 1,290 patients, and validated it on newly collected 27,113 colonoscopy images from 1,138 patients with at least one detected polyp (per-image-sensitivity, 94.38%; per-image-specificity, 95.92%; area under the receiver operating characteristic curve, 0.984), on a public database of 612 polyp-containing images (per-image-sensitivity, 88.24%), on 138 colonoscopy videos with histologically confirmed polyps (per-image-sensitivity of 91.64%; per-polyp-sensitivity, 100%), and on 54 unaltered full-range colonoscopy videos without polyps (per-image-specificity, 95.40%). By using a multi-threaded processing system, the algorithm can process at least 25 frames per second with a latency of 76.80 ± 5.60 ms in real-time video analysis. The software may aid endoscopists while performing colonoscopies, and help assess differences in polyp and adenoma detection performance among endoscopists.
- 10 October 2018
- Published by Springer Nature in Nature Biomedical Engineering
- Vol. 2 (10) , 741-748
Top Cited PapersDevelopment and validation of a deep-learning algorithm for the detection of polyps during colonoscopy
The detection and removal of precancerous polyps via colonoscopy is the gold standard for the prevention of colon cancer. However, the detection rate of adenomatous polyps can vary significantly among endoscopists. Here, we show that a machine-learning algorithm can detect polyps in clinical colonoscopies, in real time and with high sensitivity and specificity. We developed the deep-learning algorithm by using data from 1,290 patients, and validated it on newly collected 27,113 colonoscopy images from 1,138 patients with at least one detected polyp (per-image-sensitivity, 94.38%; per-image-specificity, 95.92%; area under the receiver operating characteristic curve, 0.984), on a public database of 612 polyp-containing images (per-image-sensitivity, 88.24%), on 138 colonoscopy videos with histologically confirmed polyps (per-image-sensitivity of 91.64%; per-polyp-sensitivity, 100%), and on 54 unaltered full-range colonoscopy videos without polyps (per-image-specificity, 95.40%). By using a multi-threaded processing system, the algorithm can process at least 25 frames per second with a latency of 76.80 ± 5.60 ms in real-time video analysis. The software may aid endoscopists while performing colonoscopies, and help assess differences in polyp and adenoma detection performance among endoscopists.