1
|
Parasa S, Berzin T, Leggett C, Gross S, Repici A, Ahmad OF, Chiang A, Coelho-Prabhu N, Cohen J, Dekker E, Keswani RN, Kahn CE, Hassan C, Petrick N, Mountney P, Ng J, Riegler M, Mori Y, Saito Y, Thakkar S, Waxman I, Wallace MB, Sharma P. Consensus statements on the current landscape of artificial intelligence applications in endoscopy, addressing roadblocks, and advancing artificial intelligence in gastroenterology. Gastrointest Endosc 2024:S0016-5107(23)03139-5. [PMID: 38639679 DOI: 10.1016/j.gie.2023.12.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/01/2023] [Accepted: 12/02/2023] [Indexed: 04/20/2024]
Abstract
BACKGROUND AND AIMS The American Society for Gastrointestinal Endoscopy (ASGE) AI Task Force along with experts in endoscopy, technology space, regulatory authorities, and other medical subspecialties initiated a consensus process that analyzed the current literature, highlighted potential areas, and outlined the necessary research in artificial intelligence (AI) to allow a clearer understanding of AI as it pertains to endoscopy currently. METHODS A modified Delphi process was used to develop these consensus statements. RESULTS Statement 1: Current advances in AI allow for the development of AI-based algorithms that can be applied to endoscopy to augment endoscopist performance in detection and characterization of endoscopic lesions. Statement 2: Computer vision-based algorithms provide opportunities to redefine quality metrics in endoscopy using AI, which can be standardized and can reduce subjectivity in reporting quality metrics. Natural language processing-based algorithms can help with the data abstraction needed for reporting current quality metrics in GI endoscopy effortlessly. Statement 3: AI technologies can support smart endoscopy suites, which may help optimize workflows in the endoscopy suite, including automated documentation. Statement 4: Using AI and machine learning helps in predictive modeling, diagnosis, and prognostication. High-quality data with multidimensionality are needed for risk prediction, prognostication of specific clinical conditions, and their outcomes when using machine learning methods. Statement 5: Big data and cloud-based tools can help advance clinical research in gastroenterology. Multimodal data are key to understanding the maximal extent of the disease state and unlocking treatment options. Statement 6: Understanding how to evaluate AI algorithms in the gastroenterology literature and clinical trials is important for gastroenterologists, trainees, and researchers, and hence education efforts by GI societies are needed. Statement 7: Several challenges regarding integrating AI solutions into the clinical practice of endoscopy exist, including understanding the role of human-AI interaction. Transparency, interpretability, and explainability of AI algorithms play a key role in their clinical adoption in GI endoscopy. Developing appropriate AI governance, data procurement, and tools needed for the AI lifecycle are critical for the successful implementation of AI into clinical practice. Statement 8: For payment of AI in endoscopy, a thorough evaluation of the potential value proposition for AI systems may help guide purchasing decisions in endoscopy. Reliable cost-effectiveness studies to guide reimbursement are needed. Statement 9: Relevant clinical outcomes and performance metrics for AI in gastroenterology are currently not well defined. To improve the quality and interpretability of research in the field, steps need to be taken to define these evidence standards. Statement 10: A balanced view of AI technologies and active collaboration between the medical technology industry, computer scientists, gastroenterologists, and researchers are critical for the meaningful advancement of AI in gastroenterology. CONCLUSIONS The consensus process led by the ASGE AI Task Force and experts from various disciplines has shed light on the potential of AI in endoscopy and gastroenterology. AI-based algorithms have shown promise in augmenting endoscopist performance, redefining quality metrics, optimizing workflows, and aiding in predictive modeling and diagnosis. However, challenges remain in evaluating AI algorithms, ensuring transparency and interpretability, addressing governance and data procurement, determining payment models, defining relevant clinical outcomes, and fostering collaboration between stakeholders. Addressing these challenges while maintaining a balanced perspective is crucial for the meaningful advancement of AI in gastroenterology.
Collapse
Affiliation(s)
| | | | | | - Seth Gross
- NYU Langone Health, New York, New York, USA
| | | | | | - Austin Chiang
- Medtronic Gastrointestinal, Santa Clara, California, USA
| | | | | | | | | | - Charles E Kahn
- University of Pennsylvania, Philadelphia, Pennsylvania, USA
| | - Cesare Hassan
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Italy
| | - Nicholas Petrick
- Center for Devices and Radiological Health, U.S. Food and Drug Administration
| | | | - Jonathan Ng
- Iterative Health, Boston, Massachusetts, USA
| | | | | | | | - Shyam Thakkar
- West Virginia University Medicine, Morgantown, West Virginia, USA
| | - Irving Waxman
- Rush University Medical Center, Chicago, Illinois, USA
| | | | | |
Collapse
|
2
|
Kader R, Cid‐Mejias A, Brandao P, Islam S, Hebbar S, Puyal JG, Ahmad OF, Hussein M, Toth D, Mountney P, Seward E, Vega R, Stoyanov D, Lovat LB. Polyp characterization using deep learning and a publicly accessible polyp video database. Dig Endosc 2023; 35:645-655. [PMID: 36527309 PMCID: PMC10570984 DOI: 10.1111/den.14500] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Accepted: 12/13/2022] [Indexed: 01/20/2023]
Abstract
OBJECTIVES Convolutional neural networks (CNN) for computer-aided diagnosis of polyps are often trained using high-quality still images in a single chromoendoscopy imaging modality with sessile serrated lesions (SSLs) often excluded. This study developed a CNN from videos to classify polyps as adenomatous or nonadenomatous using standard narrow-band imaging (NBI) and NBI-near focus (NBI-NF) and created a publicly accessible polyp video database. METHODS We trained a CNN with 16,832 high and moderate quality frames from 229 polyp videos (56 SSLs). It was evaluated with 222 polyp videos (36 SSLs) across two test-sets. Test-set I consists of 14,320 frames (157 polyps, 111 diminutive). Test-set II, which is publicly accessible, 3317 video frames (65 polyps, 41 diminutive), which was benchmarked with three expert and three nonexpert endoscopists. RESULTS Sensitivity for adenoma characterization was 91.6% in test-set I and 89.7% in test-set II. Specificity was 91.9% and 88.5%. Sensitivity for diminutive polyps was 89.9% and 87.5%; specificity 90.5% and 88.2%. In NBI-NF, sensitivity was 89.4% and 89.5%, with a specificity of 94.7% and 83.3%. In NBI, sensitivity was 85.3% and 91.7%, with a specificity of 87.5% and 90.0%, respectively. The CNN achieved preservation and incorporation of valuable endoscopic innovations (PIVI)-1 and PIVI-2 thresholds for each test-set. In the benchmarking of test-set II, the CNN was significantly more accurate than nonexperts (13.8% difference [95% confidence interval 3.2-23.6], P = 0.01) with no significant difference with experts. CONCLUSIONS A single CNN can differentiate adenomas from SSLs and hyperplastic polyps in both NBI and NBI-NF. A publicly accessible NBI polyp video database was created and benchmarked.
Collapse
Affiliation(s)
- Rawen Kader
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | | | | | - Shahraz Islam
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
| | | | - Juana González‐Bueno Puyal
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Odin Vision LtdLondonUK
| | - Omer F. Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | - Mohamed Hussein
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | | | | | - Ed Seward
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | - Roser Vega
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
| | - Laurence B. Lovat
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| |
Collapse
|
3
|
Ahmad OF, Mazomenos E, Chadebecq F, Kader R, Hussein M, Haidry RJ, Puyal JG, Brandao P, Toth D, Mountney P, Seward E, Vega R, Stoyanov D, Lovat LB. Identifying key mechanisms leading to visual recognition errors for missed colorectal polyps using eye-tracking technology. J Gastroenterol Hepatol 2023; 38:768-774. [PMID: 36652526 PMCID: PMC10601973 DOI: 10.1111/jgh.16127] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/22/2022] [Revised: 01/04/2023] [Accepted: 01/14/2023] [Indexed: 01/20/2023]
Abstract
BACKGROUND AND AIM Lack of visual recognition of colorectal polyps may lead to interval cancers. The mechanisms contributing to perceptual variation, particularly for subtle and advanced colorectal neoplasia, have scarcely been investigated. We aimed to evaluate visual recognition errors and provide novel mechanistic insights. METHODS Eleven participants (seven trainees and four medical students) evaluated images from the UCL polyp perception dataset, containing 25 polyps, using eye-tracking equipment. Gaze errors were defined as those where the lesion was not observed according to eye-tracking technology. Cognitive errors occurred when lesions were observed but not recognized as polyps by participants. A video study was also performed including 39 subtle polyps, where polyp recognition performance was compared with a convolutional neural network. RESULTS Cognitive errors occurred more frequently than gaze errors overall (65.6%), with a significantly higher proportion in trainees (P = 0.0264). In the video validation, the convolutional neural network detected significantly more polyps than trainees and medical students, with per-polyp sensitivities of 79.5%, 30.0%, and 15.4%, respectively. CONCLUSIONS Cognitive errors were the most common reason for visual recognition errors. The impact of interventions such as artificial intelligence, particularly on different types of perceptual errors, needs further investigation including potential effects on learning curves. To facilitate future research, a publicly accessible visual perception colonoscopy polyp database was created.
Collapse
Affiliation(s)
- Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | - Evangelos Mazomenos
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
| | - Francois Chadebecq
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
| | - Rawen Kader
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
| | - Mohamed Hussein
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
| | - Rehan J Haidry
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | - Juana González‐Bueno Puyal
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Odin Vision LtdLondonUK
| | - Patrick Brandao
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Odin Vision LtdLondonUK
| | | | | | - Ed Seward
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | - Roser Vega
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
| | - Laurence B Lovat
- Wellcome/EPSRC Centre for Interventional and Surgical SciencesUniversity College LondonLondonUK
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Gastrointestinal ServicesUniversity College London HospitalLondonUK
| |
Collapse
|
4
|
Bretthauer M, Gerke S, Hassan C, Ahmad OF, Mori Y. The New European Medical Device Regulation: Balancing Innovation and Patient Safety. Ann Intern Med 2023. [PMID: 37068279 DOI: 10.7326/m23-0454] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 04/19/2023] Open
Abstract
The European Union has introduced stricter provisions for medical devices under the new Medical Device Regulation (MDR). The MDR increases requirements for clinical trial testing for many devices before they can legally be placed on the market and extends requirements for rigorous clinical surveillance of benefits and harms to the entire life cycle of devices. New "expert panels" have been established by the European Commission to advise in the assessment of devices toward certification, and the role of previous "notified bodies" (private companies charged by the Commission with ensuring that manufacturers follow the requirements for device testing) is being expanded. The MDR does not contain a grandfathering clause; thus, all existing medical devices must be recertified under the stricter regulation. The recertification deadline has recently been extended to 2027 or 2028, depending on the device's risk class. Whether most device manufacturers can meet these new requirements is uncertain, and the MDR will likely have important consequences for manufacturers, researchers, clinicians, and patients. Enhanced collaborations between the medical device industry and physician partners will be needed to meet the new requirements in a timely manner to avoid shortages of existing devices and to mitigate barriers to development of new devices.
Collapse
Affiliation(s)
- Michael Bretthauer
- Clinical Effectiveness Research Group, University of Oslo, and Department of Transplantation Medicine, Oslo University Hospital, Oslo, Norway, and Institute of Clinical Medicine, University of Tromsø, Tromsø, Norway (M.B.)
| | - Sara Gerke
- Penn State Dickinson Law, Carlisle, Pennsylvania (S.G.)
| | - Cesare Hassan
- Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Italy, and Humanitas Clinical and Research Center-IRCCS, Endoscopy Unit, Rozzano, Italy (C.H.)
| | - Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, United Kingdom (O.F.A.)
| | - Yuichi Mori
- Clinical Effectiveness Research Group, University of Oslo, and Department of Transplantation Medicine, Oslo University Hospital, Oslo, Norway, and Showa University Northern Yokohama Hospital, Digestive Disease Center, Yokohama, Japan (Y.M.)
| |
Collapse
|
5
|
Hussein M, Lines D, González-Bueno Puyal J, Kader R, Bowman N, Sehgal V, Toth D, Ahmad OF, Everson M, Esteban JM, Bisschops R, Banks M, Haefner M, Mountney P, Stoyanov D, Lovat LB, Haidry R. Computer-aided characterization of early cancer in Barrett's esophagus on i-scan magnification imaging: a multicenter international study. Gastrointest Endosc 2023; 97:646-654. [PMID: 36460087 PMCID: PMC10590905 DOI: 10.1016/j.gie.2022.11.020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/25/2022] [Revised: 11/08/2022] [Accepted: 11/18/2022] [Indexed: 12/02/2022]
Abstract
BACKGROUND AND AIMS We aimed to develop a computer-aided characterization system that could support the diagnosis of dysplasia in Barrett's esophagus (BE) on magnification endoscopy. METHODS Videos were collected in high-definition magnification white-light and virtual chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging in patients with dysplastic and nondysplastic BE (NDBE) from 4 centers. We trained a neural network with a Resnet101 architecture to classify frames as dysplastic or nondysplastic. The network was tested on 3 different scenarios: high-quality still images, all available video frames, and a selected sequence within each video. RESULTS Fifty-seven patients, each with videos of magnification areas of BE (34 dysplasia, 23 NDBE), were included. Performance was evaluated by a leave-1-patient-out cross-validation method. In all, 60,174 (39,347 dysplasia, 20,827 NDBE) magnification video frames were used to train the network. The testing set included 49,726 i-scan-3/optical enhancement magnification frames. On 350 high-quality still images, the network achieved a sensitivity of 94%, specificity of 86%, and area under the receiver operator curve (AUROC) of 96%. On all 49,726 available video frames, the network achieved a sensitivity of 92%, specificity of 82%, and AUROC of 95%. On a selected sequence of frames per case (total of 11,471 frames), we used an exponentially weighted moving average of classifications on consecutive frames to characterize dysplasia. The network achieved a sensitivity of 92%, specificity of 84%, and AUROC of 96%. The mean assessment speed per frame was 0.0135 seconds (SD ± 0.006). CONCLUSION Our network can characterize BE dysplasia with high accuracy and speed on high-quality magnification images and sequence of video frames, moving it toward real-time automated diagnosis.
Collapse
Affiliation(s)
- Mohamed Hussein
- Division of Surgery and Interventional Sciences, University College London, UK; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, UK.
| | | | - Juana González-Bueno Puyal
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, UK; Odin Vision, UK
| | - Rawen Kader
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, UK
| | - Nicola Bowman
- Division of Surgery and Interventional Sciences, University College London, UK
| | - Vinay Sehgal
- Department of Gastroenterology, University College London Hospital, UK
| | | | - Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, UK; Department of Gastroenterology, University College London Hospital, UK
| | - Martin Everson
- Division of Surgery and Interventional Sciences, University College London, UK
| | - Jose Miguel Esteban
- Department of Gastroenterology and Hepatology, Clínico San Carlos, Madrid, Spain
| | - Raf Bisschops
- Department of Gastroenterology and Hepatology, University Hospitals Leuven, Leuven, Belgium
| | - Matthew Banks
- Department of Gastroenterology, University College London Hospital, UK
| | - Michael Haefner
- Krankenhaus der Barmherzigen Schwestern, Department of Internal Medicine II, Vienna, Austria
| | | | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, UK
| | - Laurence B Lovat
- Division of Surgery and Interventional Sciences, University College London, UK; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, UK; Department of Gastroenterology, University College London Hospital, UK
| | - Rehan Haidry
- Division of Surgery and Interventional Sciences, University College London, UK; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, UK; Department of Gastroenterology, University College London Hospital, UK
| |
Collapse
|
6
|
Mori Y, East JE, Hassan C, Halvorsen N, Berzin TM, Byrne M, von Renteln D, Hewett DG, Repici A, Ramchandani M, Al Khatry M, Kudo SE, Wang P, Yu H, Saito Y, Misawa M, Parasa S, Matsubayashi CO, Ogata H, Tajiri H, Pausawasdi N, Dekker E, Ahmad OF, Sharma P, Rex DK. Benefits and challenges in implementation of artificial intelligence in colonoscopy: World Endoscopy Organization position statement. Dig Endosc 2023; 35:422-429. [PMID: 36749036 DOI: 10.1111/den.14531] [Citation(s) in RCA: 8] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/25/2022] [Accepted: 02/06/2023] [Indexed: 02/08/2023]
Abstract
The number of artificial intelligence (AI) tools for colonoscopy on the market is increasing with supporting clinical evidence. Nevertheless, their implementation is not going smoothly for a variety of reasons, including lack of data on clinical benefits and cost-effectiveness, lack of trustworthy guidelines, uncertain indications, and cost for implementation. To address this issue and better guide practitioners, the World Endoscopy Organization (WEO) has provided its perspective about the status of AI in colonoscopy as the position statement. WEO Position Statement: Statement 1.1: Computer-aided detection (CADe) for colorectal polyps is likely to improve colonoscopy effectiveness by reducing adenoma miss rates and thus increase adenoma detection; Statement 1.2: In the short term, use of CADe is likely to increase health-care costs by detecting more adenomas; Statement 1.3: In the long term, the increased cost by CADe could be balanced by savings in costs related to cancer treatment (surgery, chemotherapy, palliative care) due to CADe-related cancer prevention; Statement 1.4: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADe to support its use in clinical practice; Statement 2.1: Computer-aided diagnosis (CADx) for diminutive polyps (≤5 mm), when it has sufficient accuracy, is expected to reduce health-care costs by reducing polypectomies, pathological examinations, or both; Statement 2.2: Health-care delivery systems and authorities should evaluate the cost-effectiveness of CADx to support its use in clinical practice; Statement 3: We recommend that a broad range of high-quality cost-effectiveness research should be undertaken to understand whether AI implementation benefits populations and societies in different health-care systems.
Collapse
Affiliation(s)
- Yuichi Mori
- Clinical Effectiveness Research Group, University of Oslo, Oslo, Norway.,Department of Transplantation Medicine, Oslo University Hospital, Oslo, Norway.,Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - James E East
- Translational Gastroenterology Unit, John Radcliffe Hospital, University of Oxford, Oxford, UK.,NIHR Oxford Biomedical Research Centre, Oxford, UK.,Division of Gastroenterology and Hepatology, Mayo Clinic Healthcare, London, UK
| | - Cesare Hassan
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Italy.,Endoscopy Unit, Humanitas Clinical and Research Center - IRCCS, Rozzano, Italy
| | - Natalie Halvorsen
- Clinical Effectiveness Research Group, University of Oslo, Oslo, Norway
| | - Tyler M Berzin
- Division of Gastroenterology, Beth Israel Deaconess Medical Center and Harvard Medical School, Boston, USA
| | - Michael Byrne
- Department of Medicine, The University of British Columbia, Vancouver, Canada
| | - Daniel von Renteln
- Division of Gastroenterology, University of Montreal Medical Center (CHUM) and Research Center (CRCHUM), Montreal, Canada
| | - David G Hewett
- School of Medicine, The University of Queensland, Brisbane, Australia
| | - Alessandro Repici
- Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Italy.,Endoscopy Unit, Humanitas Clinical and Research Center - IRCCS, Rozzano, Italy
| | | | - Maryam Al Khatry
- Department of Gastroenterology, Obaidulla Hospital, Ras Al Khaimah, United Arab Emirates
| | - Shin-Ei Kudo
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | - Pu Wang
- Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China
| | - Honggang Yu
- Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China
| | - Yutaka Saito
- Endoscopy Division, National Cancer Center Hospital, Tokyo, Japan
| | - Masashi Misawa
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan
| | | | - Carolina Ogawa Matsubayashi
- Gastrointestinal Endoscopy Unit, Gastroenterology Department, University of São Paulo Medical School, São Paulo, Brazil
| | - Haruhiko Ogata
- Center for Diagnostic and Therapeutic Endoscopy, School of Medicine, Keio University, Tokyo, Japan
| | - Hisao Tajiri
- Jikei University School of Medicine, Tokyo, Japan
| | - Nonthalee Pausawasdi
- Vikit Viranuvatti Siriraj GI Endoscopy Center,, Mahidol University, Bangkok, Thailand.,Division of Gastroenterology, Department of Medicine, Faculty of Medicine, Siriraj Hospital, Mahidol University, Bangkok, Thailand
| | - Evelien Dekker
- Department of Gastroenterology and Hepatology, Amsterdam University Medical Center, Amsterdam, The Netherlands
| | | | - Prateek Sharma
- Division of Gastroenterology and Hepatology, University of Kansas School of Medicine and VA Medical Center, Kansas City, USA
| | - Douglas K Rex
- Division of Gastroenterology, Indiana University School of Medicine, Indianapolis, USA
| |
Collapse
|
7
|
González-Bueno Puyal J, Brandao P, Ahmad OF, Bhatia KK, Toth D, Kader R, Lovat L, Mountney P, Stoyanov D. Spatio-temporal classification for polyp diagnosis. Biomed Opt Express 2023; 14:593-607. [PMID: 36874484 PMCID: PMC9979670 DOI: 10.1364/boe.473446] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/17/2022] [Revised: 11/25/2022] [Accepted: 12/06/2022] [Indexed: 06/18/2023]
Abstract
Colonoscopy remains the gold standard investigation for colorectal cancer screening as it offers the opportunity to both detect and resect pre-cancerous polyps. Computer-aided polyp characterisation can determine which polyps need polypectomy and recent deep learning-based approaches have shown promising results as clinical decision support tools. Yet polyp appearance during a procedure can vary, making automatic predictions unstable. In this paper, we investigate the use of spatio-temporal information to improve the performance of lesions classification as adenoma or non-adenoma. Two methods are implemented showing an increase in performance and robustness during extensive experiments both on internal and openly available benchmark datasets.
Collapse
Affiliation(s)
- Juana González-Bueno Puyal
- Wellcome/EPSRC Centre for Interventional
and Surgical Sciences (WEISS), University College London, London
W1W 7TY, UK
- Odin Vision, London W1W 7TY, UK
| | | | - Omer F. Ahmad
- Wellcome/EPSRC Centre for Interventional
and Surgical Sciences (WEISS), University College London, London
W1W 7TY, UK
| | | | | | - Rawen Kader
- Wellcome/EPSRC Centre for Interventional
and Surgical Sciences (WEISS), University College London, London
W1W 7TY, UK
| | - Laurence Lovat
- Wellcome/EPSRC Centre for Interventional
and Surgical Sciences (WEISS), University College London, London
W1W 7TY, UK
| | | | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional
and Surgical Sciences (WEISS), University College London, London
W1W 7TY, UK
| |
Collapse
|
8
|
Ahmad OF. Artificial intelligence for polyp characterization: easy as ABC. Endoscopy 2023; 55:23-24. [PMID: 36162423 DOI: 10.1055/a-1931-4332] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Affiliation(s)
- Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, UK.,Gastrointestinal Services, University College London Hospital, London, UK
| |
Collapse
|
9
|
Messmann H, Bisschops R, Antonelli G, Libânio D, Sinonquel P, Abdelrahim M, Ahmad OF, Areia M, Bergman JJGHM, Bhandari P, Boskoski I, Dekker E, Domagk D, Ebigbo A, Eelbode T, Eliakim R, Häfner M, Haidry RJ, Jover R, Kaminski MF, Kuvaev R, Mori Y, Palazzo M, Repici A, Rondonotti E, Rutter MD, Saito Y, Sharma P, Spada C, Spadaccini M, Veitch A, Gralnek IM, Hassan C, Dinis-Ribeiro M. Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement. Endoscopy 2022; 54:1211-1231. [PMID: 36270318 DOI: 10.1055/a-1950-5694] [Citation(s) in RCA: 36] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/10/2023]
Abstract
This ESGE Position Statement defines the expected value of artificial intelligence (AI) for the diagnosis and management of gastrointestinal neoplasia within the framework of the performance measures already defined by ESGE. This is based on the clinical relevance of the expected task and the preliminary evidence regarding artificial intelligence in artificial or clinical settings. MAIN RECOMMENDATIONS:: (1) For acceptance of AI in assessment of completeness of upper GI endoscopy, the adequate level of mucosal inspection with AI should be comparable to that assessed by experienced endoscopists. (2) For acceptance of AI in assessment of completeness of upper GI endoscopy, automated recognition and photodocumentation of relevant anatomical landmarks should be obtained in ≥90% of the procedures. (3) For acceptance of AI in the detection of Barrett's high grade intraepithelial neoplasia or cancer, the AI-assisted detection rate for suspicious lesions for targeted biopsies should be comparable to that of experienced endoscopists with or without advanced imaging techniques. (4) For acceptance of AI in the management of Barrett's neoplasia, AI-assisted selection of lesions amenable to endoscopic resection should be comparable to that of experienced endoscopists. (5) For acceptance of AI in the diagnosis of gastric precancerous conditions, AI-assisted diagnosis of atrophy and intestinal metaplasia should be comparable to that provided by the established biopsy protocol, including the estimation of extent, and consequent allocation to the correct endoscopic surveillance interval. (6) For acceptance of artificial intelligence for automated lesion detection in small-bowel capsule endoscopy (SBCE), the performance of AI-assisted reading should be comparable to that of experienced endoscopists for lesion detection, without increasing but possibly reducing the reading time of the operator. (7) For acceptance of AI in the detection of colorectal polyps, the AI-assisted adenoma detection rate should be comparable to that of experienced endoscopists. (8) For acceptance of AI optical diagnosis (computer-aided diagnosis [CADx]) of diminutive polyps (≤5 mm), AI-assisted characterization should match performance standards for implementing resect-and-discard and diagnose-and-leave strategies. (9) For acceptance of AI in the management of polyps ≥ 6 mm, AI-assisted characterization should be comparable to that of experienced endoscopists in selecting lesions amenable to endoscopic resection.
Collapse
Affiliation(s)
- Helmut Messmann
- III Medizinische Klinik, Universitatsklinikum Augsburg, Augsburg, Germany
| | - Raf Bisschops
- Department of Gastroenterology and Hepatology, Catholic University of Leuven (KUL), TARGID, University Hospital Leuven, Leuven, Belgium
| | - Giulio Antonelli
- Gastroenterology and Digestive Endoscopy Unit, Ospedale dei Castelli Hospital, Ariccia, Rome, Italy
- Department of Anatomical, Histological, Forensic Medicine and Orthopedics Sciences, Sapienza University of Rome, Italy
| | - Diogo Libânio
- Department of Gastroenterology, Porto Comprehensive Cancer Center, and RISE@CI-IPOP (Health Research Network), Porto, Portugal
- MEDCIDS, Faculty of Medicine, University of Porto, Porto, Portugal
| | - Pieter Sinonquel
- Department of Gastroenterology and Hepatology, Catholic University of Leuven (KUL), TARGID, University Hospital Leuven, Leuven, Belgium
| | - Mohamed Abdelrahim
- Endoscopy Department, Portsmouth Hospitals University NHS Trust, Portsmouth, UK
| | - Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London Hospital, London, UK
- Division of Surgery and Interventional Sciences, University College London Hospital, London, UK
- Gastrointestinal Services, University College London Hospital, London, UK
| | - Miguel Areia
- Gastroenterology Department, Portuguese Oncology Institute of Coimbra, Coimbra, Portugal
| | | | - Pradeep Bhandari
- Endoscopy Department, Portsmouth Hospitals University NHS Trust, Portsmouth, UK
| | - Ivo Boskoski
- Digestive Endoscopy Unit, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy
| | - Evelien Dekker
- Department of Gastroenterology and Hepatology, Amsterdam UMC, Amsterdam, The Netherlands
| | - Dirk Domagk
- Department of Medicine I, Josephs-Hospital Warendorf, Academic Teaching Hospital, University of Muenster, Warendorf, Germany
| | - Alanna Ebigbo
- III Medizinische Klinik, Universitatsklinikum Augsburg, Augsburg, Germany
| | - Tom Eelbode
- Department of Electrical Engineering (ESAT/PSI), Medical Imaging Research Center, KU Leuven, Leuven, Belgium
| | - Rami Eliakim
- Department of Gastroenterology, Sheba Medical Center Tel Hashomer & Sackler School of Medicine, Tel-Aviv University, Ramat Gan, Israel
| | - Michael Häfner
- 2nd Medical Department, Barmherzige Schwestern Krankenhaus, Vienna, Austria
| | - Rehan J Haidry
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London Hospital, London, UK
- Division of Surgery and Interventional Sciences, University College London Hospital, London, UK
| | - Rodrigo Jover
- Servicio de Gastroenterología, Hospital General Universitario Dr. Balmis, Instituto de Investigación Biomédica de Alicante ISABIAL, Departamento de Medicina Clínica, Universidad Miguel Hernández, Alicante, Spain
| | - Michal F Kaminski
- Clinical Effectiveness Research Group, University of Oslo, Oslo, Norway
- Department of Gastroenterology, Hepatology and Clinical Oncology, Centre of Postgraduate Medical Education, Warsaw, Poland
- Department of Oncological Gastroenterology and Department of Cancer Prevention, Maria Sklodowska-Curie National Research Institute of Oncology, Warsaw, Poland
| | - Roman Kuvaev
- Endoscopy Department, Yaroslavl Regional Cancer Hospital, Yaroslavl, Russian Federation
- Department of Gastroenterology, Faculty of Additional Professional Education, N.A. Pirogov Russian National Research Medical University, Moscow, Russian Federation
| | - Yuichi Mori
- Clinical Effectiveness Research Group, University of Oslo, Oslo, Norway
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan
| | | | - Alessandro Repici
- Department of Biomedical Sciences, Humanitas University, Rozzano, Milan, Italy
- IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | | | - Matthew D Rutter
- North Tees and Hartlepool NHS Foundation Trust, Stockton-on-Tees, UK
- Population Health Sciences Institute, Newcastle University, Newcastle, UK
| | - Yutaka Saito
- Endoscopy Division, National Cancer Center Hospital, Tokyo, Japan
| | - Prateek Sharma
- Gastroenterology and Hepatology Division, University of Kansas School of Medicine, Kansas, USA
- Kansas City VA Medical Center, Kansas City, USA
| | - Cristiano Spada
- Digestive Endoscopy Unit, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy
- Digestive Endoscopy, Fondazione Poliambulanza Istituto Ospedaliero, Brescia, Italy
| | - Marco Spadaccini
- Department of Biomedical Sciences, Humanitas University, Rozzano, Milan, Italy
- IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Andrew Veitch
- Department of Gastroenterology, Royal Wolverhampton Hospitals NHS Trust, Wolverhampton, UK
| | - Ian M Gralnek
- Ellen and Pinchas Mamber Institute of Gastroenterology and Hepatology, Emek Medical Center, Afula, Israel
- Rappaport Faculty of Medicine, Technion Israel Institute of Technology, Haifa, Israel
| | - Cesare Hassan
- Department of Biomedical Sciences, Humanitas University, Rozzano, Milan, Italy
- IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy
| | - Mario Dinis-Ribeiro
- Department of Gastroenterology, Porto Comprehensive Cancer Center, and RISE@CI-IPOP (Health Research Network), Porto, Portugal
| |
Collapse
|
10
|
Hussein M, González‐Bueno Puyal J, Lines D, Sehgal V, Toth D, Ahmad OF, Kader R, Everson M, Lipman G, Fernandez‐Sordo JO, Ragunath K, Esteban JM, Bisschops R, Banks M, Haefner M, Mountney P, Stoyanov D, Lovat LB, Haidry R. A new artificial intelligence system successfully detects and localises early neoplasia in Barrett's esophagus by using convolutional neural networks. United European Gastroenterol J 2022; 10:528-537. [PMID: 35521666 PMCID: PMC9278593 DOI: 10.1002/ueg2.12233] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/05/2021] [Accepted: 03/31/2022] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND AND AIMS Seattle protocol biopsies for Barrett's Esophagus (BE) surveillance are labour intensive with low compliance. Dysplasia detection rates vary, leading to missed lesions. This can potentially be offset with computer aided detection. We have developed convolutional neural networks (CNNs) to identify areas of dysplasia and where to target biopsy. METHODS 119 Videos were collected in high-definition white light and optical chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging in patients with dysplastic and non-dysplastic BE (NDBE). We trained an indirectly supervised CNN to classify images as dysplastic/non-dysplastic using whole video annotations to minimise selection bias and maximise accuracy. The CNN was trained using 148,936 video frames (31 dysplastic patients, 31 NDBE, two normal esophagus), validated on 25,161 images from 11 patient videos and tested on 264 iscan-1 images from 28 dysplastic and 16 NDBE patients which included expert delineations. To localise targeted biopsies/delineations, a second directly supervised CNN was generated based on expert delineations of 94 dysplastic images from 30 patients. This was tested on 86 i-scan one images from 28 dysplastic patients. FINDINGS The indirectly supervised CNN achieved a per image sensitivity in the test set of 91%, specificity 79%, area under receiver operator curve of 93% to detect dysplasia. Per-lesion sensitivity was 100%. Mean assessment speed was 48 frames per second (fps). 97% of targeted biopsy predictions matched expert and histological assessment at 56 fps. The artificial intelligence system performed better than six endoscopists. INTERPRETATION Our CNNs classify and localise dysplastic Barrett's Esophagus potentially supporting endoscopists during surveillance.
Collapse
Affiliation(s)
- Mohamed Hussein
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS)University College LondonLondonUK
- Department of GastroenterologyUniversity College London HospitalLondonUK
| | - Juana González‐Bueno Puyal
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS)University College LondonLondonUK
- Odin VisionLondonUK
| | | | - Vinay Sehgal
- Department of GastroenterologyUniversity College London HospitalLondonUK
| | | | - Omer F. Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS)University College LondonLondonUK
- Department of GastroenterologyUniversity College London HospitalLondonUK
| | - Rawen Kader
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS)University College LondonLondonUK
| | - Martin Everson
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
| | - Gideon Lipman
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
| | | | - Krish Ragunath
- NIHR Nottingham Digestive Diseases Biomedical Research CentreNottinghamUK
| | | | | | - Matthew Banks
- Department of GastroenterologyUniversity College London HospitalLondonUK
| | | | | | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS)University College LondonLondonUK
| | - Laurence B. Lovat
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS)University College LondonLondonUK
- Department of GastroenterologyUniversity College London HospitalLondonUK
| | - Rehan Haidry
- Division of Surgery and Interventional SciencesUniversity College LondonLondonUK
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS)University College LondonLondonUK
- Department of GastroenterologyUniversity College London HospitalLondonUK
| |
Collapse
|
11
|
Ahmad OF, González-Bueno Puyal J, Brandao P, Kader R, Abbasi F, Hussein M, Haidry RJ, Toth D, Mountney P, Seward E, Vega R, Stoyanov D, Lovat LB. Performance of artificial intelligence for detection of subtle and advanced colorectal neoplasia. Dig Endosc 2022; 34:862-869. [PMID: 34748665 DOI: 10.1111/den.14187] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/10/2021] [Revised: 10/22/2021] [Accepted: 11/05/2021] [Indexed: 02/05/2023]
Abstract
OBJECTIVES There is uncertainty regarding the efficacy of artificial intelligence (AI) software to detect advanced subtle neoplasia, particularly flat lesions and sessile serrated lesions (SSLs), due to low prevalence in testing datasets and prospective trials. This has been highlighted as a top research priority for the field. METHODS An AI algorithm was evaluated on four video test datasets containing 173 polyps (35,114 polyp-positive frames and 634,988 polyp-negative frames) specifically enriched with flat lesions and SSLs, including a challenging dataset containing subtle advanced neoplasia. The challenging dataset was also evaluated by eight endoscopists (four independent, four trainees, according to the Joint Advisory Group on gastrointestinal endoscopy [JAG] standards in the UK). RESULTS In the first two video datasets, the algorithm achieved per-polyp sensitivities of 100% and 98.9%. Per-frame sensitivities were 84.1% and 85.2%. In the subtle dataset, the algorithm detected a significantly higher number of polyps (P < 0.0001), compared to JAG-independent and trainee endoscopists, achieving per-polyp sensitivities of 79.5%, 37.2% and 11.5%, respectively. Furthermore, when considering subtle polyps detected by both the algorithm and at least one endoscopist, the AI detected polyps significantly faster on average. CONCLUSIONS The AI based algorithm achieved high per-polyp sensitivities for advanced colorectal neoplasia, including flat lesions and SSLs, outperforming both JAG independent and trainees on a very challenging dataset containing subtle lesions that could have been overlooked easily and contribute to interval colorectal cancer. Further prospective trials should evaluate AI to detect subtle advanced neoplasia in higher risk populations for colorectal cancer.
Collapse
Affiliation(s)
- Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London
- Division of Surgery and Interventional Sciences, University College London, London, UK
- Gastrointestinal Services, University College London Hospital, London, UK
| | - Juana González-Bueno Puyal
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London
- Odin Vision Ltd, London, UK
| | - Patrick Brandao
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London
- Odin Vision Ltd, London, UK
| | - Rawen Kader
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London
- Division of Surgery and Interventional Sciences, University College London, London, UK
| | - Faisal Abbasi
- Division of Surgery and Interventional Sciences, University College London, London, UK
| | - Mohamed Hussein
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London
- Division of Surgery and Interventional Sciences, University College London, London, UK
| | - Rehan J Haidry
- Division of Surgery and Interventional Sciences, University College London, London, UK
- Gastrointestinal Services, University College London Hospital, London, UK
| | | | | | - Ed Seward
- Gastrointestinal Services, University College London Hospital, London, UK
| | - Roser Vega
- Gastrointestinal Services, University College London Hospital, London, UK
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London
| | - Laurence B Lovat
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London
- Division of Surgery and Interventional Sciences, University College London, London, UK
- Gastrointestinal Services, University College London Hospital, London, UK
| |
Collapse
|
12
|
Van Berkel N, Opie J, Ahmad OF, Lovat L, Stoyanov D, Blandford A. Initial Responses to False Positives in AI-Supported Continuous Interactions: A Colonoscopy Case Study. ACM T INTERACT INTEL 2022. [DOI: 10.1145/3480247] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/01/2022]
Abstract
The use of artificial intelligence (AI) in clinical support systems is increasing. In this article, we focus on AI support for continuous interaction scenarios. A thorough understanding of end-user behaviour during these continuous human-AI interactions, in which user input is sustained over time and during which AI suggestions can appear at any time, is still missing. We present a controlled lab study involving 21 endoscopists and an AI colonoscopy support system. Using a custom-developed application and an off-the-shelf videogame controller, we record participants’ navigation behaviour and clinical assessment across 14 endoscopic videos. Each video is manually annotated to mimic an AI recommendation, being either true positive or false positive in nature. We find that time between AI recommendation and clinical assessment is significantly longer for incorrect assessments. Further, the type of medical content displayed significantly affects decision time. Finally, we discover that the participant’s clinical role plays a large part in the perception of clinical AI support systems. Our study presents a realistic assessment of the effects of imperfect and continuous AI support in a clinical scenario.
Collapse
Affiliation(s)
- Niels Van Berkel
- Aalborg University, Denmark and University College London, London, United Kingdom
| | - Jeremy Opie
- University College London, London, United Kingdom
| | | | - Laurence Lovat
- University College London Hospitals, London, United Kingdom
| | | | | |
Collapse
|
13
|
Kader R, Baggaley RF, Hussein M, Ahmad OF, Patel N, Corbett G, Dolwani S, Stoyanov D, Lovat LB. Survey on the perceptions of UK gastroenterologists and endoscopists to artificial intelligence. Frontline Gastroenterol 2022; 13:423-429. [PMID: 36046492 PMCID: PMC9380773 DOI: 10.1136/flgastro-2021-101994] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/23/2021] [Accepted: 12/21/2021] [Indexed: 02/05/2023] Open
Abstract
BACKGROUND AND AIMS With the potential integration of artificial intelligence (AI) into clinical practice, it is essential to understand end users' perception of this novel technology. The aim of this study, which was endorsed by the British Society of Gastroenterology (BSG), was to evaluate the UK gastroenterology and endoscopy communities' views on AI. METHODS An online survey was developed and disseminated to gastroenterologists and endoscopists across the UK. RESULTS One hundred four participants completed the survey. Quality improvement in endoscopy (97%) and better endoscopic diagnosis (92%) were perceived as the most beneficial applications of AI to clinical practice. The most significant challenges were accountability for incorrect diagnoses (85%) and potential bias of algorithms (82%). A lack of guidelines (92%) was identified as the greatest barrier to adopting AI in routine clinical practice. Participants identified real-time endoscopic image diagnosis (95%) as a research priority for AI, while the most perceived significant barriers to AI research were funding (82%) and the availability of annotated data (76%). Participants consider the priorities for the BSG AI Task Force to be identifying research priorities (96%), guidelines for adopting AI devices in clinical practice (93%) and supporting the delivery of multicentre clinical trials (91%). CONCLUSION This survey has identified views from the UK gastroenterology and endoscopy community regarding AI in clinical practice and research, and identified priorities for the newly formed BSG AI Task Force.
Collapse
Affiliation(s)
- Rawen Kader
- Division of Surgery and Interventional Sciences, University College London, London, UK
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
- Department of Gastroenterology, University College London Hospitals NHS Foundation Trust, London, UK
| | - Rebecca F Baggaley
- Department of Respiratory Infections, University of Leicester, Leicester, UK
| | - Mohamed Hussein
- Division of Surgery and Interventional Sciences, University College London, London, UK
- Department of Gastroenterology, University College London Hospitals NHS Foundation Trust, London, UK
| | - Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
- Department of Gastroenterology, University College London Hospitals NHS Foundation Trust, London, UK
| | - Nisha Patel
- Department of Gastroenterology, Imperial College Healthcare NHS Trust, London, UK
| | - Gareth Corbett
- Department of Gastroenterology, Addenbrooke's Hospital, Cambridge, UK
| | - Sunil Dolwani
- Division of Population Medicine, School of Medicine, Cardiff University, Cardiff, UK
| | - Danail Stoyanov
- Division of Surgery and Interventional Sciences, University College London, London, UK
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Laurence B Lovat
- Division of Surgery and Interventional Sciences, University College London, London, UK
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
- Department of Gastroenterology, University College London Hospitals NHS Foundation Trust, London, UK
| |
Collapse
|
14
|
Ahmad OF, Mori Y, Misawa M, Kudo SE, Anderson JT, Bernal J, Berzin TM, Bisschops R, Byrne MF, Chen PJ, East JE, Eelbode T, Elson DS, Gurudu SR, Histace A, Karnes WE, Repici A, Singh R, Valdastri P, Wallace MB, Wang P, Stoyanov D, Lovat LB. Establishing key research questions for the implementation of artificial intelligence in colonoscopy: a modified Delphi method. Endoscopy 2021; 53:893-901. [PMID: 33167043 PMCID: PMC8390295 DOI: 10.1055/a-1306-7590] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
Abstract
BACKGROUND : Artificial intelligence (AI) research in colonoscopy is progressing rapidly but widespread clinical implementation is not yet a reality. We aimed to identify the top implementation research priorities. METHODS : An established modified Delphi approach for research priority setting was used. Fifteen international experts, including endoscopists and translational computer scientists/engineers, from nine countries participated in an online survey over 9 months. Questions related to AI implementation in colonoscopy were generated as a long-list in the first round, and then scored in two subsequent rounds to identify the top 10 research questions. RESULTS : The top 10 ranked questions were categorized into five themes. Theme 1: clinical trial design/end points (4 questions), related to optimum trial designs for polyp detection and characterization, determining the optimal end points for evaluation of AI, and demonstrating impact on interval cancer rates. Theme 2: technological developments (3 questions), including improving detection of more challenging and advanced lesions, reduction of false-positive rates, and minimizing latency. Theme 3: clinical adoption/integration (1 question), concerning the effective combination of detection and characterization into one workflow. Theme 4: data access/annotation (1 question), concerning more efficient or automated data annotation methods to reduce the burden on human experts. Theme 5: regulatory approval (1 question), related to making regulatory approval processes more efficient. CONCLUSIONS : This is the first reported international research priority setting exercise for AI in colonoscopy. The study findings should be used as a framework to guide future research with key stakeholders to accelerate the clinical implementation of AI in endoscopy.
Collapse
Affiliation(s)
- Omer F. Ahmad
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, UK
| | - Yuichi Mori
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan,Clinical Effectiveness Research Group, Institute of Health and Society, University of Oslo, Oslo, Norway
| | - Masashi Misawa
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan
| | - Shin-ei Kudo
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Yokohama, Japan
| | - John T. Anderson
- Department of Gastroenterology, Gloucestershire Hospitals NHS Foundation Trust, Gloucester, UK
| | - Jorge Bernal
- Computer Science Department, Universitat Autonoma de Barcelona and Computer Vision Center, Barcelona, Spain
| | - Tyler M. Berzin
- Center for Advanced Endoscopy, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, Massachusetts, USA
| | - Raf Bisschops
- Department of Gastroenterology and Hepatology, University Hospitals Leuven, TARGID KU Leuven, Leuven, Belgium
| | - Michael F. Byrne
- Division of Gastroenterology, Vancouver General Hospital, University of British Columbia, Vancouver, British Columbia, Canada
| | - Peng-Jen Chen
- Division of Gastroenterology, Tri-Service General Hospital, National Defense Medical Center, Taipei, Taiwan
| | - James E. East
- Translational Gastroenterology Unit, John Radcliffe Hospital, Oxford, UK,Oxford NIHR Biomedical Research Centre, University of Oxford, Oxford, UK
| | - Tom Eelbode
- Medical Imaging Research Center, ESAT/PSI, KU Leuven, Leuven, Belgium
| | - Daniel S. Elson
- Hamlyn Centre for Robotic Surgery, Institute of Global Health Innovation, Imperial College London, London, UK,Department of Surgery and Cancer, Imperial College London, London, UK
| | - Suryakanth R. Gurudu
- Division of Gastroenterology and Hepatology, Mayo Clinic, Scottsdale, Arizona, USA
| | - Aymeric Histace
- ETIS, Universite de Cergy-Pointoise, ENSEA, CNRS, Cergy-Pointoise Cedex, France
| | - William E. Karnes
- H. H. Chao Comprehensive Digestive Disease Center, Division of Gastroenterology & Hepatology, Department of Medicine, University of California, Irvine, California, USA
| | - Alessandro Repici
- Department of Gastroenterology, Humanitas Clinical and Research Center, IRCCS, Rozzano, Milan, Italy,Humanitas University, Department of Biomedical Sciences, Pieve Emanuele, Milan, Italy
| | - Rajvinder Singh
- Department of Gastroenterology and Hepatology, Lyell McEwan Hospital, Adelaide, South Australia, Australia
| | - Pietro Valdastri
- School of Electronics and Electrical Engineering, University of Leeds, Leeds, UK
| | - Michael B. Wallace
- Division of Gastroenterology & Hepatology, Mayo Clinic, Jacksonville, Florida, USA
| | - Pu Wang
- Department of Gastroenterology, Sichuan Academy of Medical Sciences and Sichuan Provincial People’s Hospital, Chengdu, China
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, UK
| | - Laurence B. Lovat
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, UK,Gastrointestinal Services, University College London Hospital, London, UK
| |
Collapse
|
15
|
Ahmad OF. Early detection of gastric neoplasia: is artificial intelligence the solution? Lancet Gastroenterol Hepatol 2021; 6:678-679. [PMID: 34297943 DOI: 10.1016/s2468-1253(21)00254-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/24/2021] [Accepted: 06/25/2021] [Indexed: 11/30/2022]
Affiliation(s)
- Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London W1W 7TS, UK.
| |
Collapse
|
16
|
Ahmad OF, Stassen P, Webster GJ. Artificial intelligence in biliopancreatic endoscopy: Is there any role? Best Pract Res Clin Gastroenterol 2020; 52-53:101724. [PMID: 34172251 DOI: 10.1016/j.bpg.2020.101724] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/21/2020] [Accepted: 12/22/2020] [Indexed: 01/31/2023]
Abstract
Artificial intelligence (AI) research in endoscopy is being translated at rapid pace with a number of approved devices now available for use in luminal endoscopy. However, the published literature for AI in biliopancreatic endoscopy is predominantly limited to early pre-clinical studies including applications for diagnostic EUS and patient risk stratification. Potential future use cases are highlighted in this manuscript including optical characterisation of strictures during cholangioscopy, prediction of post-ERCP acute pancreatitis and selective biliary duct cannulation difficulty, automated report generation and novel AI-based quality key performance metrics. To realise the full potential of AI and accelerate innovation, it is crucial that robust inter-disciplinary collaborations are formed between biliopancreatic endoscopists and AI researchers.
Collapse
Affiliation(s)
- Omer F Ahmad
- Department of Gastroenterology, University College London Hospitals NHS Foundation Trust, 250 Euston Road, London, NW1 2BU, United Kingdom; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, Charles Bell House, 43-45 Foley Street, London, W1W 7TS, United Kingdom.
| | - Pauline Stassen
- Erasmus MC University Medical Center, Doctor Molewaterplein 40, 3015 GD, Rotterdam, Netherlands
| | - George J Webster
- Department of Gastroenterology, University College London Hospitals NHS Foundation Trust, 250 Euston Road, London, NW1 2BU, United Kingdom
| |
Collapse
|
17
|
Kader R, Dart RJ, Sebepos‐Rogers G, Shakweh E, Middleton P, McGuire J, Pavlidis P, Ahmad OF, Segal J, Samaan MA, Gahir J, Black G, Theaker H, Calderbank T, Meade S, Ibraheim H, Clough J, Bancil A, Honap S, Hampal R, Tavabie O, Tai C, Tern P, Akbar S, Patel R, Rhead C, Kabir M, Bashyam M, Fofaria R, Hiner G, Ravindran S, Walton H, King J, Dhillon A, Seller P, Mukherjee S, Harlow C. Implementation of an intervention bundle leads to quality improvement in ulcerative colitis endoscopy reporting. GastroHep 2020. [DOI: 10.1002/ygh2.427] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/05/2023]
Affiliation(s)
- Rawen Kader
- Gastroenterology University College London Hospitals NHS Foundation Trust London UK
| | - Robin J. Dart
- Gastroenterology Department Royal Free Hospital London UK
- School of Immunology and Microbial Sciences King's College London London UK
| | | | - Eathar Shakweh
- Gastroenterology Imperial College Healthcare NHS Trust London UK
| | - Paul Middleton
- Metabolism, Digestion and Reproduction Imperial College London London UK
| | - Joshua McGuire
- Gastroenterology University College London Hospitals NHS Foundation Trust London UK
| | - Polychronis Pavlidis
- School of Immunology and Microbial Sciences King's College London London UK
- Gastroenterology Guy’s & St Thomas’ NHS Foundation Trust London UK
| | - Omer F. Ahmad
- Gastroenterology University College London Hospitals NHS Foundation Trust London UK
| | - Jonathan Segal
- Gastroenterology and Hepatology St Mary’s Hospital London UK
| | - Mark A. Samaan
- Gastroenterology Guy’s & St Thomas’ NHS Foundation Trust London UK
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
18
|
Abstract
Microscopic colitis encompasses both collagenous and lymphocytic colitis and is a relatively common condition with rising incidence. Diagnosis is by colonoscopy (which is usually normal but may show some mild changes) and biopsies which reveal characteristic histological findings. Symptoms include non-bloody diarrhoea with urgency which may be associated with faecal incontinence and abdominal pain. Microscopic colitis is associated with a reduced health-related quality of life, and treatment is aimed at symptom control. Medications linked with the development of microscopic colitis, including proton pump inhibitors, non-steroidal anti-inflammatory drugs and selective serotonin-reuptake inhibitors, should be discontinued. If symptoms persist, budesonide is a licensed treatment for microscopic colitis which has been shown to be effective in clinical trials and real-world practice.
Collapse
Affiliation(s)
- Omer F Ahmad
- Department of Gastroenterology, University College Hospital, London, UK
| | - Ayesha Akbar
- Department of Gastroenterology, St Mark's Hospital, LNWH Trust, Harrow, UK
- Department of Surgery, Imperial College London, London, UK
| |
Collapse
|
19
|
He Q, Bano S, Ahmad OF, Yang B, Chen X, Valdastri P, Lovat LB, Stoyanov D, Zuo S. Deep learning-based anatomical site classification for upper gastrointestinal endoscopy. Int J Comput Assist Radiol Surg 2020; 15:1085-1094. [PMID: 32377939 PMCID: PMC7316667 DOI: 10.1007/s11548-020-02148-5] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2019] [Accepted: 03/31/2020] [Indexed: 02/07/2023]
Abstract
Purpose Upper gastrointestinal (GI) endoscopic image documentation has provided an efficient, low-cost solution to address quality control for endoscopic reporting. The problem is, however, challenging for computer-assisted techniques, because different sites have similar appearances. Additionally, across different patients, site appearance variation may be large and inconsistent. Therefore, according to the British and modified Japanese guidelines, we propose a set of oesophagogastroduodenoscopy (EGD) images to be routinely captured and evaluate its efficiency for deep learning-based classification methods. Methods A novel EGD image dataset standardising upper GI endoscopy to several steps is established following landmarks proposed in guidelines and annotated by an expert clinician. To demonstrate the discrimination of proposed landmarks that enable the generation of an automated endoscopic report, we train several deep learning-based classification models utilising the well-annotated images. Results We report results for a clinical dataset composed of 211 patients (comprising a total of 3704 EGD images) acquired during routine upper GI endoscopic examinations. We find close agreement between predicted labels using our method and the ground truth labelled by human experts. We observe the limitation of current static image classification scheme for EGD image classification. Conclusion Our study presents a framework for developing automated EGD reports using deep learning. We demonstrate that our method is feasible to address EGD image classification and can lead towards improved performance and additionally qualitatively demonstrate its performance on our dataset.
Collapse
Affiliation(s)
- Qi He
- Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, Tianjin University, Tianjin, China
| | - Sophia Bano
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Bo Yang
- General Hospital, Tianjin Medical University, Tianjin, China
| | - Xin Chen
- General Hospital, Tianjin Medical University, Tianjin, China
| | - Pietro Valdastri
- School of Electronic and Electrical Engineering, University of Leeds, Leeds, UK
| | - Laurence B Lovat
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Siyang Zuo
- Key Laboratory of Mechanism Theory and Equipment Design of Ministry of Education, Tianjin University, Tianjin, China.
| |
Collapse
|
20
|
Ahmad OF, Stoyanov D, Lovat LB. Barriers and pitfalls for artificial intelligence in gastroenterology: Ethical and regulatory issues. ACTA ACUST UNITED AC 2020. [DOI: 10.1016/j.tgie.2019.150636] [Citation(s) in RCA: 21] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
|
21
|
Affiliation(s)
- Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London W1W 7TS, UK.
| |
Collapse
|
22
|
Rosenfeld A, Graham DG, Jevons S, Ariza J, Hagan D, Wilson A, Lovat SJ, Sami SS, Ahmad OF, Novelli M, Rodriguez Justo M, Winstanley A, Heifetz EM, Ben-Zecharia M, Noiman U, Fitzgerald RC, Sasieni P, Lovat LB. Development and validation of a risk prediction model to diagnose Barrett's oesophagus (MARK-BE): a case-control machine learning approach. Lancet Digit Health 2020; 2:E37-E48. [PMID: 32133440 PMCID: PMC7056359 DOI: 10.1016/s2589-7500(19)30216-x] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/02/2023]
Abstract
Background Screening for Barrett's Oesophagus (BE) relies on endoscopy which is invasive and has a low yield. This study aimed to develop and externally validate a simple symptom and risk-factor questionnaire to screen for patients with BE. Methods Questionnaires from 1299 patients in the BEST2 case-controlled study were analysed: 880 had BE including 40 with invasive oesophageal adenocarcinoma (OAC) and 419 were controls. This was randomly split into a training cohort of 776 patients and an internal validation cohort of 523 patients. External validation included 398 patients from the BOOST case-controlled study: 198 with BE (23 with OAC) and 200 controls. Identification of independently important diagnostic features was undertaken using machine learning techniques information gain (IG) and correlation based feature selection (CFS). Multiple classification tools were assessed to create a multi-variable risk prediction model. Internal validation was followed by external validation in the independent dataset. Findings The BEST2 study included 40 features. Of these, 24 added IG but following CFS, only 8 demonstrated independent diagnostic value including age, gender, smoking, waist circumference, frequency of stomach pain, duration of heartburn and acid taste and taking of acid suppression medicines. Logistic regression offered the highest prediction quality with AUC (area under the receiver operator curve) of 0.87. In the internal validation set, AUC was 0.86. In the BOOST external validation set, AUC was 0.81. Interpretation The diagnostic model offers valid predictions of diagnosis of BE in patients with symptomatic gastroesophageal reflux, assisting in identifying who should go forward to invasive testing. Overweight men who have been taking stomach medicines for a long time may merit particular consideration for further testing. The risk prediction tool is quick and simple to administer but will need further calibration and validation in a prospective study in primary care. Funding Charles Wolfson Trust and Guts UK.
Collapse
Affiliation(s)
- Avi Rosenfeld
- Department of Industrial Engineering Jerusalem College of Technology (JCT), Jerusalem, Israel
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
| | - David G Graham
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
- Gastrointestinal Services, University College London Hospital (UCLH), London, United Kingdom
| | - Sarah Jevons
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
| | - Jose Ariza
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
- Gastrointestinal Services, University College London Hospital (UCLH), London, United Kingdom
| | - Daryl Hagan
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
| | - Ash Wilson
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
| | - Samuel J Lovat
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
| | - Sarmed S Sami
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
- Gastrointestinal Services, University College London Hospital (UCLH), London, United Kingdom
| | - Omer F Ahmad
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
- Gastrointestinal Services, University College London Hospital (UCLH), London, United Kingdom
| | - Marco Novelli
- Dept of Pathology, University College London Hospital (UCLH), London, United Kingdom
| | | | - Alison Winstanley
- Dept of Pathology, University College London Hospital (UCLH), London, United Kingdom
| | - Eliyahu M Heifetz
- Department of Health Informatics, Jerusalem College of Technology (JCT), Jerusalem, Israel
| | - Mordehy Ben-Zecharia
- Department of Health Informatics, Jerusalem College of Technology (JCT), Jerusalem, Israel
| | - Uria Noiman
- Department of Health Informatics, Jerusalem College of Technology (JCT), Jerusalem, Israel
| | | | - Peter Sasieni
- Cancer Prevention Trials Unit, Queen Mary University of London, London, United Kingdom
- School of Cancer & Pharmaceutical Sciences, King's College London, London, United Kingdom
| | - Laurence B Lovat
- GENIE GastroENterological IntervEntion Group, Department for Targeted Intervention, University College London (UCL), London, United Kingdom
- Gastrointestinal Services, University College London Hospital (UCLH), London, United Kingdom
| |
Collapse
|
23
|
Shivaji UN, Jeffery L, Gui X, Smith SCL, Ahmad OF, Akbar A, Ghosh S, Iacucci M. Immune checkpoint inhibitor-associated gastrointestinal and hepatic adverse events and their management. Therap Adv Gastroenterol 2019; 12:1756284819884196. [PMID: 31723355 PMCID: PMC6831976 DOI: 10.1177/1756284819884196] [Citation(s) in RCA: 48] [Impact Index Per Article: 9.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/10/2019] [Accepted: 09/18/2019] [Indexed: 02/04/2023] Open
Abstract
BACKGROUND Drug-induced colitis is a known complication of therapies that alter the immune balance, damage the intestinal barrier or disturb intestinal microbiota. Immune checkpoint inhibitors (ICI) directed against cancer cells may result in activated T lymphocyte-induced immune-related adverse events (AEs), including immune-related colitis and hepatitis. The aim of this review article is to summarize the incidence of gastrointestinal (GI) and hepatic AEs related to ICI therapy. We have also looked at the pathogenesis of immune-mediated AEs and propose management strategies based on current available evidence. METHODS A literature search using PubMed and Medline databases was undertaken using relevant search terms pertaining to names of individual drugs, mechanism of action, related AEs and their management. RESULTS ICI-related GI AEs are common, and colitis appears to be the most common side effect, with some studies reporting incidence as high as 30%. The incidence of both all-grade colitis and hepatitis were highest with combination therapy with anti-CTLA-4/PD-1; severity of colitis was dose-dependent (anti-CTLA-4). Early intervention is associated with better outcomes. CONCLUSION ICI-related GI and hepatic AEs are common and clinicians need to be aware. Patients with GI AEs benefit from early diagnosis using endoscopy and computed tomography. Early intervention with oral steroids is effective in the majority of patients, and in steroid-refractory colitis infliximab and vedolizumab have been reported to be useful; mycophenolate has been used for steroid-refractory hepatitis.
Collapse
Affiliation(s)
- Uday N. Shivaji
- National Institute for Health Research (NIHR)
Birmingham Biomedical Research Centre, UK,Institute of Immunology and Immunotherapy,
University of Birmingham, UK
| | - Louisa Jeffery
- National Institute for Health Research (NIHR)
Birmingham Biomedical Research Centre, UK,Institute of Immunology and Immunotherapy,
University of Birmingham, UK
| | - Xianyong Gui
- Department of Pathology, University of
Washington, Seattle, WA, USA
| | - Samuel C. L. Smith
- Institute of Immunology and Immunotherapy,
University of Birmingham, UK,Institute of Translational Medicine, Birmingham,
UK
| | - Omer F. Ahmad
- Department of Gastroenterology, University
College London Hospital, London, UK
| | | | | | - Marietta Iacucci
- National Institute for Health Research (NIHR)
Birmingham Biomedical Research Centre, UK,Institute of Immunology and Immunotherapy,
University of Birmingham, UK,Institute of Translational Medicine,
Birmingham, UK
| |
Collapse
|
24
|
Rau A, Edwards PJE, Ahmad OF, Riordan P, Janatka M, Lovat LB, Stoyanov D. Implicit domain adaptation with conditional generative adversarial networks for depth prediction in endoscopy. Int J Comput Assist Radiol Surg 2019; 14:1167-1176. [PMID: 30989505 PMCID: PMC6570710 DOI: 10.1007/s11548-019-01962-w] [Citation(s) in RCA: 47] [Impact Index Per Article: 9.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2019] [Accepted: 04/02/2019] [Indexed: 02/08/2023]
Abstract
PURPOSE Colorectal cancer is the third most common cancer worldwide, and early therapeutic treatment of precancerous tissue during colonoscopy is crucial for better prognosis and can be curative. Navigation within the colon and comprehensive inspection of the endoluminal tissue are key to successful colonoscopy but can vary with the skill and experience of the endoscopist. Computer-assisted interventions in colonoscopy can provide better support tools for mapping the colon to ensure complete examination and for automatically detecting abnormal tissue regions. METHODS We train the conditional generative adversarial network pix2pix, to transform monocular endoscopic images to depth, which can be a building block in a navigational pipeline or be used to measure the size of polyps during colonoscopy. To overcome the lack of labelled training data in endoscopy, we propose to use simulation environments and to additionally train the generator and discriminator of the model on unlabelled real video frames in order to adapt to real colonoscopy environments. RESULTS We report promising results on synthetic, phantom and real datasets and show that generative models outperform discriminative models when predicting depth from colonoscopy images, in terms of both accuracy and robustness towards changes in domains. CONCLUSIONS Training the discriminator and generator of the model on real images, we show that our model performs implicit domain adaptation, which is a key step towards bridging the gap between synthetic and real data. Importantly, we demonstrate the feasibility of training a single model to predict depth from both synthetic and real images without the need for explicit, unsupervised transformer networks mapping between the domains of synthetic and real data.
Collapse
Affiliation(s)
- Anita Rau
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK.
| | - P J Eddie Edwards
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | | | - Mirek Janatka
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Laurence B Lovat
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| |
Collapse
|
25
|
Ahmad OF, Stoyanov D, Lovat LB. Human-machine collaboration: bringing artificial intelligence into colonoscopy. Frontline Gastroenterol 2019; 10:198-199. [PMID: 31205664 PMCID: PMC6540265 DOI: 10.1136/flgastro-2018-101047] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/16/2018] [Revised: 09/26/2018] [Accepted: 10/01/2018] [Indexed: 02/04/2023] Open
Affiliation(s)
- Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK
| | - Laurence B Lovat
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, London, UK,Division of Surgery and Interventional Science, University College London, London, UK
| |
Collapse
|
26
|
Ahmad OF, Soares AS, Mazomenos E, Brandao P, Vega R, Seward E, Stoyanov D, Chand M, Lovat LB. Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions. Lancet Gastroenterol Hepatol 2018; 4:71-80. [PMID: 30527583 DOI: 10.1016/s2468-1253(18)30282-6] [Citation(s) in RCA: 108] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/29/2018] [Revised: 08/10/2018] [Accepted: 08/20/2018] [Indexed: 12/15/2022]
Abstract
Computer-aided diagnosis offers a promising solution to reduce variation in colonoscopy performance. Pooled miss rates for polyps are as high as 22%, and associated interval colorectal cancers after colonoscopy are of concern. Optical biopsy, whereby in-vivo classification of polyps based on enhanced imaging replaces histopathology, has not been incorporated into routine practice because it is limited by interobserver variability and generally only meets accepted standards in expert settings. Real-time decision-support software has been developed to detect and characterise polyps, and also to offer feedback on the technical quality of inspection. Some of the current algorithms, particularly with recent advances in artificial intelligence techniques, match human expert performance for optical biopsy. In this Review, we summarise the evidence for clinical applications of computer-aided diagnosis and artificial intelligence in colonoscopy.
Collapse
Affiliation(s)
- Omer F Ahmad
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, UK; Gastrointestinal Services, University College London Hospital, London, UK.
| | - Antonio S Soares
- Division of Surgery & Interventional Science, University College London, London, UK
| | - Evangelos Mazomenos
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, UK
| | - Patrick Brandao
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, UK
| | - Roser Vega
- Gastrointestinal Services, University College London Hospital, London, UK
| | - Edward Seward
- Gastrointestinal Services, University College London Hospital, London, UK
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, UK
| | - Manish Chand
- Division of Surgery & Interventional Science, University College London, London, UK; Gastrointestinal Services, University College London Hospital, London, UK
| | - Laurence B Lovat
- Wellcome/EPSRC Centre for Interventional & Surgical Sciences, University College London, London, UK; Division of Surgery & Interventional Science, University College London, London, UK; Gastrointestinal Services, University College London Hospital, London, UK
| |
Collapse
|
27
|
Abstract
INTRODUCTION Irritable bowel syndrome (IBS) is the most prevalent functional gastrointestinal (GI) disorder. Increasing evidence implicates the GI microbiota in IBS pathogenesis and its modulation represents an emerging therapeutic strategy. SOURCES OF DATA Original and review articles were identified through selective searches performed on PubMed and Google Scholar. AREAS OF AGREEMENT The role of gut microbiota in IBS is supported by evidence from animal and human studies. Randomized controlled trials demonstrate efficacy of the non-systemic antibiotic rifaximin in reducing IBS symptoms. AREAS OF CONTROVERSY Existing studies on microbiota alterations are often inconsistent and limited by the heterogeneity of IBS. The exact mechanism of rifaximin remains to be elucidated. Identifying predictors of response to rifaximin and treatment strategies for symptom recurrence are important clinical questions. GROWING POINTS High-throughput molecular methods are leading to rapid advances in our understanding of GI microbiota in IBS AREAS TIMELY FOR DEVELOPING RESEARCH: Future well designed longitudinal studies are required to identify characteristic microbial signatures and potential biomarkers to identify therapeutic targets and predict clinical response.
Collapse
Affiliation(s)
- O F Ahmad
- Department of Gastroenterology, Whittington Hospital, Magdala Avenue, London N19 5NF, UK
| | - A Akbar
- Department of Gastroenterology, St Mark's Hospital, Watford Road, Harrow, Middlesex HA1 3UJ, UK
| |
Collapse
|
28
|
Abstract
INTRODUCTION Food is a recognized trigger for most patients with irritable bowel syndrome (IBS). In recent years, an emerging evidence base has identified dietary manipulation as an important therapeutic approach in IBS. SOURCES OF DATA Original and review articles were identified through selective searches performed on PubMed and Google Scholar. AREAS OF AGREEMENT Randomized controlled trials have supported the use of a diet that restricts a group of short-chain carbohydrates known collectively as fermentable oligosaccharides, disaccharides, monosaccharides and polyols (FODMAPs). There is evidence that specific probiotics may improve symptoms in IBS. AREAS OF CONTROVERSY The role of a high-fibre diet remains subject to ongoing debate with a lack of high-quality evidence. The long-term durability and safety of a low FODMAP diet are unclear. GROWING POINTS A paradigm shift has led to a focus on the relationship between diet and pathophysiological mechanisms in IBS such as effects on intestinal microbiota, inflammation, motility, permeability and visceral hypersensitivity. AREAS TIMELY FOR DEVELOPING RESEARCH Future large, randomized controlled trials with rigorous end points are required. In addition, predictors of response need to be identified to offer personalized therapy.
Collapse
Affiliation(s)
- O F Ahmad
- Department of Gastroenterology, Whittington Hospital, Magdala Avenue, London N19 5NF, UK
| | - A Akbar
- Department of Gastroenterology, St Mark's Hospital, Watford Road, Harrow, Middlesex HA1 3UJ, UK
| |
Collapse
|
29
|
Affiliation(s)
- Omer F Ahmad
- Core Medical Trainee in the Department of Gastroenterology, Whittington Hospital, London N19 5NF
| | - Ayesha Akbar
- Consultant Gastroenterologist in the Department of Gastroenterology, St Marks Hospital, and Honorary Senior Lecturer, Imperial College London
| |
Collapse
|
30
|
Abstract
Intussusception in adults is a rare condition, in contrast to paediatric intussusception where the majority of cases are idiopathic, ∼90% of adult cases have identifiable aetiology. The clinical presentation is often non-specific abdominal pain. We report the case of a 49-year-old gentleman who presented to our emergency department with a 10-day history of colicky abdominal pain. Computed tomography imaging revealed a lipomatous mass lesion in the transverse colon leading to intussusception. An extended right hemicolectomy was performed with a good result. Histology confirmed that the leading point of the intussusception was a large submucosal lipoma. Gastrointestinal lipomas are rare and largely asymptomatic. However, they may cause abdominal pain, bleeding per rectum, obstruction or intussusception. Since adult colonic intussusception is frequently associated with malignant organic lesions, the differential diagnosis is important, and timely surgical intervention paramount.
Collapse
Affiliation(s)
- Khalid N Shehzad
- Department of General Surgery, Watford General Hospital, Watford, UK
| | - Sherif Monib
- Department of General Surgery, Watford General Hospital, Watford, UK
| | - Omer F Ahmad
- Department of General Surgery, Watford General Hospital, Watford, UK
| | - Amjid A Riaz
- Department of General Surgery, Watford General Hospital, Watford, UK
| |
Collapse
|
31
|
Ahmad OF, Keane MG, McCartney S, Khwaja A, Bloom SL. Azathioprine-associated myelodysplastic syndrome in two patients with ulcerative colitis. Frontline Gastroenterol 2013; 4:205-209. [PMID: 28839727 PMCID: PMC5369798 DOI: 10.1136/flgastro-2012-100276] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/22/2012] [Revised: 02/24/2013] [Accepted: 02/25/2013] [Indexed: 02/04/2023] Open
Abstract
Azathioprine is a commonly used immunosuppressive agent in post-transplantation regimens and autoimmune diseases. An increased risk of lymphoma with thiopurine therapy in patients with inflammatory bowel disease has been described previously; however, there are few reported cases of azathioprine therapy-related myelodysplastic syndrome and acute myeloid leukaemia. We report two patients with ulcerative colitis who subsequently developed azathioprine-related myelodysplastic syndrome. It is imperative that gastroenterologists remain vigilant for this rare complication as this subset of patients has a particularly poor prognosis. These cases are also important in considering the risk of open-ended thiopurine therapy.
Collapse
Affiliation(s)
- Omer F Ahmad
- Department of Gastroenterology, University College London Hospital, London, UK
| | - Margaret G Keane
- Department of Gastroenterology, University College London Hospital, London, UK
| | - Sara McCartney
- Department of Gastroenterology, University College London Hospital, London, UK
| | - Asim Khwaja
- Department of Haematology, University College London Hospital, London, UK
| | - Stuart L Bloom
- Department of Gastroenterology, University College London Hospital, London, UK
| |
Collapse
|