AGA White Paper: Training and Implementation of Endoscopic Image Enhancement Technologies

Endoscopic image-enhancement technologies provide opportunities to visualize normal and abnormal tissues within the gastrointestinal (GI) tract in a manner that complements conventional white light endoscopic imaging. The additional information that is obtained enables the endoscopist to better identify, delineate, and characterize lesions and can facilitate targeted biopsies or, in some cases, eliminate the need to send samples for histologic analysis. Some of these technologies have been available for more than a decade, but despite this fact, there is limited use of these technologies by endoscopists. Lack of formalized training in their use and a scarcity of guidelines on implementation of these technologies into clinical practice are contributing factors. In November 2014, the American Gastroenterological Association’s Center for GI Innovation and Technology conducted a 2-day workshop to discuss endoscopic image-enhancement technologies. This article represents the third of 3 separate documents generated from the workshop and discusses the published literature pertaining to training and outlines a proposed framework for the implementation of endoscopic image-enhancement technologies in clinical practice.There was general agreement among participants in the workshop on several key considerations. Training and competency assessment for endoscopic image-enhancement technologies should incorporate competency-based education paradigms. To facilitate successful training, multiple different educational models that can cater to variations in learning styles need to be developed, including classroom-style and self-directed programs, in-person and web-based options, image and video atlases, and endoscopic simulator programs. To ensure safe and appropriate use of these technologies over time, refresher courses, skill maintenance programs, and options for competency reassessment should be established. Participants also generally agreed that although early adopters of novel endoscopic image-enhancement modalities can successfully implement these technologies by pursuing training and ensuring self-competency, widespread implementation is likely to require support from GI societies and buy-in from other key stakeholders including payors/purchasers and patients. Continued work by manufacturers and the GI societies in providing training programs and patient education, working with payors and purchasers, and creating environments and policies that motivate endoscopists to adopt new practices is essential in creating widespread implementation. Endoscopic image-enhancement technologies provide opportunities to visualize normal and abnormal tissues within the gastrointestinal (GI) tract in a manner that complements conventional white light endoscopic imaging. The additional information that is obtained enables the endoscopist to better identify, delineate, and characterize lesions and can facilitate targeted biopsies or, in some cases, eliminate the need to send samples for histologic analysis. Some of these technologies have been available for more than a decade, but despite this fact, there is limited use of these technologies by endoscopists. Lack of formalized training in their use and a scarcity of guidelines on implementation of these technologies into clinical practice are contributing factors. In November 2014, the American Gastroenterological Association’s Center for GI Innovation and Technology conducted a 2-day workshop to discuss endoscopic image-enhancement technologies. This article represents the third of 3 separate documents generated from the workshop and discusses the published literature pertaining to training and outlines a proposed framework for the implementation of endoscopic image-enhancement technologies in clinical practice. There was general agreement among participants in the workshop on several key considerations. Training and competency assessment for endoscopic image-enhancement technologies should incorporate competency-based education paradigms. To facilitate successful training, multiple different educational models that can cater to variations in learning styles need to be developed, including classroom-style and self-directed programs, in-person and web-based options, image and video atlases, and endoscopic simulator programs. To ensure safe and appropriate use of these technologies over time, refresher courses, skill maintenance programs, and options for competency reassessment should be established. Participants also generally agreed that although early adopters of novel endoscopic image-enhancement modalities can successfully implement these technologies by pursuing training and ensuring self-competency, widespread implementation is likely to require support from GI societies and buy-in from other key stakeholders including payors/purchasers and patients. Continued work by manufacturers and the GI societies in providing training programs and patient education, working with payors and purchasers, and creating environments and policies that motivate endoscopists to adopt new practices is essential in creating widespread implementation. Endoscopic image-enhancement technologies provide opportunities to visualize normal and abnormal tissues within the gastrointestinal (GI) tract, supplying clinicians with information that complements conventional white light endoscopic imaging. Equipped with this information, endoscopists can obtain in vivo optical diagnosis of lesion histology at the time of the endoscopic procedure. Examples of endoscopic image-enhancement technologies include narrow-band imaging (NBI), flexible spectral imaging color enhancement, I-scan, confocal laser endomicroscopy (CLE), and optical coherence tomography. Some of these technologies have been available for more than a decade, but despite this fact, there is limited routine or standardized use of these technologies by endoscopists. In November 2014, the American Gastroenterological Association’s (AGA) Center for GI Innovation and Technology (CGIT) conducted a 2-day workshop to discuss endoscopic image-enhancement technologies, focusing on their role in 2 specific clinical conditions (colon polyps and Barrett’s esophagus) and on issues relating to training and implementation of these technologies. The content of the industry-sponsored workshop was developed entirely by members of the CGIT committee. Workshop participants constituted a wide range of specialists including experts in the fields of endoscopy, imaging, pathology, endoscopic training, and healthcare policy and thus represented a wide spectrum of stakeholders and attitudes regarding endoscopic image-enhancement. Day 1 of the workshop included a series of presentations that included a corporate technology review for each of the aforementioned image-enhancement technologies, summaries of the published evidence for using image-enhancement techniques to detect and characterize colon polyps and Barrett’s neoplasia (including discussion of dye-based chromoendoscopy), an overview of conventional histopathology in these clinical scenarios, and the potential implications associated with promoting more widespread and standardized use of image-enhancement modalities by endoscopists (ie, potential impacts on healthcare costs). Day 2 was dedicated to a roundtable discussion (not including the companies) to affirm the areas of general consensus agreement among the expert participants, to elucidate areas of disagreement, and to define topics requiring further exploration. The AGA CGIT then selected participants of the meeting to develop a series of 3 papers summarizing the discussion (colon polyps, Barrett’s, and training). This article represents the third of 3 separate documents generated from the 2-day workshop. Any recommendations within these summaries are based on expert opinion, and are not intended to serve as “practice guidelines” for the AGA. Instead, they reflect a level of confidence among the workshop participants that, after reviewing the published literature, the desirable effects of a particular intervention (eg, incorporating a “resect and discard” protocol for certain colon polyps in one’s clinical practice based on polyp characterization using endoscopic image-enhancement technologies) outweigh any undesirable effects and that the majority of informed patients would choose the intervention and clinicians would provide the intervention to most patients. The first 2 papers covering the data and rationale for application of these technologies in colon polyps and Barrett’s esophagus have already been published.1Lieberman D. Brill J. Canto M. et al.Management of diminutive colon polyps based on endoluminal imaging.Clin Gastroenterol Hepatol. 2015; 13 (quiz e168-9): 1860-1866Abstract Full Text Full Text PDF PubMed Scopus (15) Google Scholar, 2Sharma P. Brill J. Canto M. et al.White Paper AGA: advanced imaging in Barrett's esophagus.Clin Gastroenterol Hepatol. 2015; 13: 2209-2218Abstract Full Text Full Text PDF PubMed Scopus (37) Google Scholar This white paper outlines a proposed framework for the implementation of endoscopic image-enhancement technologies in routine clinical practice (Figure 1). Although this outline is not the only way these technologies could be implemented, we believe that this serves as a guide for those wanting to adopt these technologies in their current practice and as a foundation for future forward progress in the field. The contents of this paper focus exclusively on training and competency as relates to colon polyps and Barrett’s esophagus and do not address the potential application of these technologies for other purposes, such as margin detection, for which there is less data on efficacy and training. Training based on a fixed amount of time and/or procedures (as opposed to competency-based training) has been the traditional manner in which medical skills are imparted. In the United States, endoscopy is generally taught through postgraduate medical training programs (gastroenterology fellowship, surgical residencies/fellowships, and some internal medicine and family practice residencies) in which the learner spends a fixed amount of time in the training program performing endoscopy under supervision. In addition, competency is generally assumed to be achieved once the learner completes the time period in the training program and completes a prespecified number of procedures. However, this training and competency assessment method has not consistently ensured that all graduates of training programs perform endoscopy with comparable quality. Medical societies (both gastroenterology and nongastroenterology societies) and the American Board of Internal Medicine have begun to move away from this manner of fixed time-based training to a system of competency-based education. The latter is structured on different assumptions: (1) people learn in different ways, (2) learners achieve competency at different rates, and (3) competency must be assessed against fixed criterion rather than comparison against the performance of other learners or “experts.” Training and competency assessment for endoscopic image-enhancement technologies should follow competency-based education models that, over time, get incorporated into the existing curricula of postgraduate training programs that teach endoscopy. Competency-based education programs geared toward endoscopists that are no longer in postgraduate training programs should also be constructed, enabling them to become proficient in novel endoscopic image-enhancement technologies that they may not have learned during their postgraduate training. If developed creatively, these programs could serve the additional benefit of helping to motivate busy endoscopists already in clinical practice to seek and acquire these additional skill sets. For example, one motivating option might be to issue continuing medical education credit or American Board of Internal Medicine maintenance of certification points on successful completion of the program. Several training modules have been developed and used in prior studies evaluating the performance of endoscopic image-enhancement technologies. Classroom-type training programs, varying in length from 20 minutes to 4 hours, have been found to be effective in teaching NBI for characterizing colon polyps to experienced academic endoscopists, endoscopy trainees, and nonendoscopy medical trainees.3Dai J. Shen Y.F. Sano Y. et al.Evaluation of narrow-band imaging in the diagnosis of colorectal lesions: is a learning curve involved?.Dig Endosc. 2013; 25: 180-188Crossref PubMed Scopus (22) Google Scholar, 4Rogart J.N. Jain D. Siddiqui U.D. et al.Narrow-band imaging without high magnification to differentiate polyps during real-time colonoscopy: improvement with experience.Gastrointest Endosc. 2008; 68: 1136-1145Abstract Full Text Full Text PDF PubMed Scopus (108) Google Scholar, 5Raghavendra M. Hewett D.G. Rex D.K. Differentiating adenomas from hyperplastic colorectal polyps: narrow-band imaging can be learned in 20 minutes.Gastrointest Endosc. 2010; 72: 572-576Abstract Full Text Full Text PDF PubMed Scopus (120) Google Scholar, 6Patel S.G. Rastogi A. Austin G. et al.Gastroenterology trainees can easily learn histologic characterization of diminutive colorectal polyps with narrow band imaging.Clin Gastroenterol Hepatol. 2013; 11: 997-1003Abstract Full Text Full Text PDF PubMed Scopus (40) Google Scholar Self-directed, computer-based training modules, ranging from 15 to 20 minutes in length, have also been found to be effective in teaching NBI for characterizing colon polyps to academic endoscopists, endoscopy trainees, nonendoscopy medical trainees, and community endoscopists.7Rastogi A. Rao D.S. Gupta N. et al.Impact of a computer-based teaching module on characterization of diminutive colon polyps by using narrow-band imaging by non-experts in academic and community practice: a video-based study.Gastrointest Endosc. 2014; 79: 390-398Abstract Full Text Full Text PDF PubMed Scopus (58) Google Scholar, 8Sinh P. Gupta N. Rao D.S. et al.Community gastroenterologists can learn diminutive colon polyp histology characterization with narrow band imaging by a computer-based teaching module.Dig Endosc. 2015; 27: 374-380Crossref PubMed Scopus (7) Google Scholar, 9Ignjatovic A. Thomas-Gibson S. East J.E. et al.Development and validation of a training module on the use of narrow-band imaging in differentiation of small adenomas from hyperplastic colorectal polyps.Gastrointest Endosc. 2011; 73: 128-133Abstract Full Text Full Text PDF PubMed Scopus (90) Google Scholar Self-directed, computer- and Web site–based training modules have been combined with ongoing self-directed feedback and were found to be effective in teaching NBI for characterizing colon polyps and gastric lesions.10Dias-Silva D. Pimentel-Nunes P. Magalhaes J. et al.The learning curve for narrow-band imaging in the diagnosis of precancerous gastric lesions by using Web-based video.Gastrointest Endosc. 2014; 79 (quiz 983-e1–983 e4): 910-920Abstract Full Text Full Text PDF PubMed Scopus (53) Google Scholar, 11Singh R. Bhat Y.M. Thurairajah P.H. et al.Is narrow band imaging superior to high-definition white light endoscopy in the assessment of diminutive colorectal polyps?.J Gastroenterol Hepatol. 2013; 28: 472-478Crossref PubMed Scopus (10) Google Scholar However, most of these studies have assessed ex vivo performance. Those that have assessed in vivo performance have found that the training programs improve learner performance, but have not consistently shown that learners can reach all the established performance thresholds.12Vu H.T. Sayuk G.S. Hollander T.G. et al.Resect and discard approach to colon polyps: real-world applicability among academic and community gastroenterologists.Dig Dis Sci. 2015; 60: 502-508Crossref PubMed Scopus (24) Google Scholar, 13McGill S.K. Soetikno R. Rastogi A. et al.Endoscopists can sustain high performance for the optical diagnosis of colorectal polyps following standardized and continued training.Endoscopy. 2015; 47: 200-206Crossref PubMed Scopus (2) Google Scholar, 14Paggi S. Rondonotti E. Amato A. et al.Narrow-band imaging in the prediction of surveillance intervals after polypectomy in community practice.Endoscopy. 2015; 47: 808-814Crossref PubMed Scopus (25) Google Scholar, 15Ladabaum U. Fioritto A. Mitani A. et al.Real-time optical biopsy of colon polyps with narrow band imaging in community practice does not yet meet key thresholds for clinical decisions.Gastroenterology. 2013; 144: 81-91Abstract Full Text Full Text PDF PubMed Scopus (178) Google Scholar, 16Abu Dayyeh B.K. Thosani N. Konda V. et al.ASGE Technology Committee systematic review and meta-analysis assessing the ASGE PIVI thresholds for adopting real-time endoscopic assessment of the histology of diminutive colorectal polyps.Gastrointest Endosc. 2015; 81: 502e1-502e16Abstract Full Text Full Text PDF Scopus (230) Google Scholar, 17Patel S.G. Schoenfeld P. Kim H.M. et al.Real-time characterization of diminutive colorectal polyp histology using narrow-band imaging: implications for the resect and discard strategy.Gastroenterology. 2016; 150: 406-418Abstract Full Text Full Text PDF PubMed Scopus (61) Google Scholar In a study by Ladabaum et al,15Ladabaum U. Fioritto A. Mitani A. et al.Real-time optical biopsy of colon polyps with narrow band imaging in community practice does not yet meet key thresholds for clinical decisions.Gastroenterology. 2013; 144: 81-91Abstract Full Text Full Text PDF PubMed Scopus (178) Google Scholar a computerized training module was effective in having community endoscopists reach thresholds for negative predictive value for diminutive, hyperplastic-appearing polyps in the rectosigmoid colon using NBI, but not for concordance with postpolypectomy surveillance intervals during in vivo testing. In a study by Vu et al,12Vu H.T. Sayuk G.S. Hollander T.G. et al.Resect and discard approach to colon polyps: real-world applicability among academic and community gastroenterologists.Dig Dis Sci. 2015; 60: 502-508Crossref PubMed Scopus (24) Google Scholar a classroom-style training module was not effective in having community or academic endoscopists reach thresholds for concordance with postpolypectomy surveillance intervals using NBI. However, in a study by Patel et al,17Patel S.G. Schoenfeld P. Kim H.M. et al.Real-time characterization of diminutive colorectal polyp histology using narrow-band imaging: implications for the resect and discard strategy.Gastroenterology. 2016; 150: 406-418Abstract Full Text Full Text PDF PubMed Scopus (61) Google Scholar a 2-hour classroom-style training program combined with ongoing in vivo performance feedback was effective in getting endoscopists to reach thresholds for both negative predictive value for diminutive, hyperplastic-appearing polyps in the rectosigmoid colon and concordance with postpolypectomy surveillance intervals using NBI during in vivo testing. Although there have been several studies evaluating training programs for teaching NBI in characterizing colon polyps, there is less training-related data on other disease-specific applications of NBI (eg, Barrett’s esophagus) or for teaching and learning other endoscopic image-enhancement technologies, such as I-scan, flexible spectral imaging color enhancement, or CLE. In learning to characterize Barrett’s esophagus, randomized controlled trials have found no difference between in-classroom training and self-directed training programs for learning to use NBI, but found superiority of in-classroom training when learning to use CLE.18Daly C. Vennalaganti P. Soudagar S. et al.Randomized controlled trial of self-directed versus in-classroom teaching of narrow-band imaging for diagnosis of Barrett's esophagus-associated neoplasia.Gastrointest Endosc. 2016; 83: 101-106Abstract Full Text Full Text PDF PubMed Scopus (10) Google Scholar, 19Rzouq F. Vennalaganti P. Pakseresht K. et al.In-class didactic versus self-directed teaching of the probe-based confocal laser endomicroscopy (pCLE) criteria for Barrett's esophagus.Endoscopy. 2016; 48: 123-127Crossref PubMed Scopus (10) Google Scholar It remains unclear whether training requirements are different based on the imaging technology or disease application. What is clear is that every person’s learning modality of choice and uptake are different. Some may learn better with continued instruction from a teacher, whereas others learn better by self-directed methods. Some individuals learn quickly and some slowly. It would be ideal if one could develop a single training program for endoscopic image-enhancement technologies that is (1) short, (2) reproducible, (3) easily distributed, and which (4) generates a 100% competency rate after completion of the training program regardless of the student’s prior experience or natural ability. However, this Holy Grail is unlikely to be easily found. Therefore, a variety of different training options should be developed, including classroom-type and self-directed programs, in-person and Web site–based, image/video atlases, endoscopy simulators programs, and refresher/skill maintenance programs. Training programs should also be convenient and inexpensive for endoscopists. In addition, the creation of training programs requires establishment of clear and measurable objectives to establish acceptable levels of performance in the use of endoscopic image-enhancement technologies. Future research should foster identification of which types of programs are most effective in taking novices and training them to achieve threshold performance, the length of the learning curve, and quantification of ongoing use required to maintain proficiency. Because endoscopists will likely be learning to use endoscopic image-enhancement technologies through a heterogeneous set of training methods for the foreseeable future, ensuring competency in the use of these technologies becomes critically important. Endoscopists interested in adopting these technologies in their current practice should document competency with the specific technology (eg, NBI, flexible spectral imaging color enhancement, I-scan, CLE, optical coherence tomography) and for the specific disease (eg, Barrett’s esophagus, colon polyps) before adopting a practice where optical diagnosis (without tissue sampling) would replace current standard practice of histologic diagnosis by a pathologist. The ideal method of assessing competency is an ex vivo test that has high correlation with in vivo performance, but this does not currently exist. In fact, prior studies have failed to show a correlation between performance on ex vivo tests using colon polyp images and in vivo performance by the same endoscopists during live cases.4Rogart J.N. Jain D. Siddiqui U.D. et al.Narrow-band imaging without high magnification to differentiate polyps during real-time colonoscopy: improvement with experience.Gastrointest Endosc. 2008; 68: 1136-1145Abstract Full Text Full Text PDF PubMed Scopus (108) Google Scholar Pending development of novel ex vivo tests, competency in using 1 or more endoscopic image-enhancement technology will have to be documented through the measurement of in vivo performance. The endoscopist must demonstrate that they can achieve pre-established thresholds for a particular clinical situation (eg, achieving an established threshold for negative predictive value in excluding adenomatous histology within diminutive rectosigmoid colon polyps using 1 of the endoscopic image-enhancement technologies). An endoscopist would be required to demonstrate competency in achieving pre-established thresholds using the technology for each potential clinical application (eg, colon polyps, Barrett’s esophagus) rather than assuming that competency in 1 condition-specific entity (colon polyps) infers competency in all clinical applications. However, pre-established clinical thresholds for a specific condition would be applied equally to each of the individual technologies when used for that application. For example, an endoscopist should demonstrate ability to achieve the same negative predictive value for excluding adenomatous histology in colon polyps when using NBI or using CLE to document competency in those technologies. Achieving competency by demonstrating ability to meet performance thresholds using NBI does not ensure competency using CLE, and vice versa. In addition, competency should be documented in a robust number of cases to ensure that the 95% confidence interval around the endoscopist’s point estimate of performance does not cross below the pre-established thresholds. For example, if an endoscopist wished to implement the “resect and discard” strategy for diminutive colon polyps, the appropriate competency assessment outcome would be the concordance of the endoscopist’s image-based postpolypectomy surveillance interval and the histopathology-based postpolypectomy surveillance interval. The performance threshold for this outcome would be a concordance of ≥90% when an optical diagnosis is used for diminutive polyps diagnosed with high confidence (as specified in American Society for Gastrointestinal Endoscopy Preservation and Incorporation of Valuable Endoscopic Innovations statement and the AGA CGIT white paper).1Lieberman D. Brill J. Canto M. et al.Management of diminutive colon polyps based on endoluminal imaging.Clin Gastroenterol Hepatol. 2015; 13 (quiz e168-9): 1860-1866Abstract Full Text Full Text PDF PubMed Scopus (15) Google Scholar, 20Rex D.K. Kahi C. O'Brien M. et al.The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps.Gastrointest Endosc. 2011; 73: 419-422Abstract Full Text Full Text PDF PubMed Scopus (429) Google Scholar The endoscopist would perform enhanced imaging with in vivo “optical biopsy” and then perform endoscopic resection for histologic examination of all polyps identified. The endoscopist would record the postpolypectomy surveillance interval recommendation that they made based on their in vivo optical biopsy interpretation, and separately record the postpolypectomy surveillance interval based on the histopathology results for all polyps encountered in a prespecified number of cases. Inclusion of a predefined number of patients would be required to ensure reasonable precision around concordance results. At the end of each block of cases, the concordance between the image-based postpolypectomy surveillance interval and the histopathology-based postpolypectomy surveillance interval would be calculated. Once the endoscopist achieves this performance threshold during 2 consecutive blocks of cases, then they can be considered competent to implement the “resect and discard” strategy for diminutive rectosigmoid polyps in their clinical practice. If they do not achieve the performance thresholds, they could continue to perform additional blocks of assessment cases until they reach the performance thresholds in 2 consecutive blocks of cases. This approach can be easily done in a manner that does not add risks to patients or significant costs to the endoscopic procedures. Performance thresholds for endoscopic image-enhancement technologies are currently limited to only those optical diagnoses made with high confidence.1Lieberman D. Brill J. Canto M. et al.Management of diminutive colon polyps based on endoluminal imaging.Clin Gastroenterol Hepatol. 2015; 13 (quiz e168-9): 1860-1866Abstract Full Text Full Text PDF PubMed Scopus (15) Google Scholar, 20Rex D.K. Kahi C. O'Brien M. et al.The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps.Gastrointest Endosc. 2011; 73: 419-422Abstract Full Text Full Text PDF PubMed Scopus (429) Google Scholar, 21Sharma P. Savides T.J. Canto M.I. et al.The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on imaging in Barrett's esophagus.Gastrointest Endosc. 2012; 76: 252-254Abstract Full Text Full Text PDF PubMed Scopus (104) Google Scholar In general, optical diagnoses made with high confidence should have higher accuracy than those made with low confidence. However, level of confidence is subjective. The time needed to make an optical diagnosis has been found to inversely correlate with optical diagnosis accuracy. Two studies have found that optical diagnoses that can be made in ≤5 seconds have higher accuracy than those taking ≥5 seconds to make.22Gupta N. Kaltenbach T. Sato T. et al.Diagnosis time determines the accuracy of optical diagnosis of diminutive polyp histology.Gastroenterology. 2013; 77: AB553-AB554Google Scholar, 23Rastogi A. Gupta N. Sinh P. et al.Prediction time for characterizing diminutive polyp (DP) histology with NBI during colonoscopy is a marker for high confidence (HC) diagnosis and accuracy.Gastrointest Endosc. 2014; 79: AB163Abstract Full Text Full Text PDF Google Scholar This may be a more objective way to identify optical diagnoses made with high accuracy. It is clear from prior studies on training that there is an inverse relationship between the number of optical diagnoses made with high confidence and the accuracy of high confidence optical diagnoses (ie, the more optical diagnoses an endoscopist makes and categorizes as high confidence, the lower the overall accuracy of those high confidence diagnoses and vice versa). It therefore becomes important to monitor the number of optical diagnoses that an endoscopist can make with high confidence while ensuring their competency. Establishment of a threshold proportion of predictions that can be made with high confidence may also be an appropriate assessment of competence, because the percentage of predictions that can be made with high confidence will impact the realized cost savings of implementing endoscopic image-enhancement technologies. For example, if an individual endoscopist can make very few high-confidence predictions, then little change from current practice is achieved. Once an endoscopic image-enhancement technology is implemented in clinical practice to obtain in vivo optical diagnoses, it is important to monitor the quality of the care provided. Manufacturers need to provide the infrastructure to allow endoscopists to capture and store archival quality images and/or videos that replicate what is visualized in real-time and the ability to integrate them into procedure reports. Archiving of high-quality images/videos allows for review of the optical diagnosis in the event an audit is needed (eg, clinical concerns for incorrect diagnosis or even legal challenges). Archiving also allows the endoscopist to monitor their performance in optical diagnosis and to conduct ongoing self-improvement. Finally, because in vivo optical diagnoses are used in place of histopathology, archived high-quality images/videos are needed for monitoring of histology-based endoscopy quality measures (eg, adenoma detection rate). Capability to store high-quality, uncompressed images is available in several report generator systems but may require adjustment of the software settings by the vendor. None of the available endoscopic image-enhancement technologies currently are Food and Drug Administration (FDA)-labeled for in vivo optical diagnosis of lesion histology in gastroenterology. However, this remains one of the primary goals for use of these technologies during GI endoscopy. Despite the absence of data, practicing endoscopists may be more likely to adopt a technology for an indication if it is FDA-labeled for the indication. Manufacturers may be able to obtain modifications of their FDA labeling to recognize the fact that these technologies allow physicians to perform an in vivo optical diagnosis of histology or allow for targeted biopsies. Manufacturers of these technologies should be encouraged to work toward obtaining FDA labeling where the labeling language is similar to the manner in which endoscopists will be using the technology in clinical practice. Nevertheless, once endoscopic image-enhancement technologies are available for use, the major issue for endoscopists should relate to the supporting evidence in the medical literature and not be purely based on the presence or absence of FDA labeling. Although the American Society for Gastrointestinal Endoscopy previously published its Preservation and Incorporation of Valuable Endoscopic Innovations statements on endoscopic image-enhancement technologies for use in colon polyp management and Barrett’s esophagus, to date there has been little additional subsequent guidance from other GI or surgical endoscopy societies.20Rex D.K. Kahi C. O'Brien M. et al.The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps.Gastrointest Endosc. 2011; 73: 419-422Abstract Full Text Full Text PDF PubMed Scopus (429) Google Scholar, 21Sharma P. Savides T.J. Canto M.I. et al.The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on imaging in Barrett's esophagus.Gastrointest Endosc. 2012; 76: 252-254Abstract Full Text Full Text PDF PubMed Scopus (104) Google Scholar The reason for this is not entirely known, because practices that are recommended by GI societies are often more likely to be adopted by practitioners. Support from GI societies can help early adopters and facilitate more widespread implementation of a technology or technique. This white paper, along with the 2 accompanying white papers on the use of endoscopic image-enhancement technologies for colon polyp management and Barrett’s esophagus, provides additional guidance and addresses potential training and competency assessment issues associated with use of endoscopic image-enhancement technologies.1Lieberman D. Brill J. Canto M. et al.Management of diminutive colon polyps based on endoluminal imaging.Clin Gastroenterol Hepatol. 2015; 13 (quiz e168-9): 1860-1866Abstract Full Text Full Text PDF PubMed Scopus (15) Google Scholar, 2Sharma P. Brill J. Canto M. et al.White Paper AGA: advanced imaging in Barrett's esophagus.Clin Gastroenterol Hepatol. 2015; 13: 2209-2218Abstract Full Text Full Text PDF PubMed Scopus (37) Google Scholar As the process moves forward, there will be an ongoing need for support from GI societies to help endoscopists implement these new technologies in practice through the assessment of evidence, creation of guidelines for use, establishing quality indicators, and assisting practitioners with training and implementation. Although early adopters of new technologies can be successful in implementing new practices by following the previously mentioned framework, widespread implementation is likely to require buy in from other key stakeholders including payors/purchasers and patients.24Appannagari A. Soudagar A.S. Pietrzak C. et al.Are gastroenterologists willing to implement imaging-guided surveillance for Barrett's esophagus? Results from a national survey.Endosc Int Open. 2015; 3: E181-E185Crossref PubMed Google Scholar, 25Soudagar A.S. Nguyen M. Bhatia A. et al.Are gastroenterologists willing to implement the “predict, resect, and discard” management strategy for diminutive colorectal polyps?: Results From a national survey.J Clin Gastroenterol. 2015; 50: e45-e49Google Scholar Payors are unlikely to be willing to pay additional money to endoscopists for obtaining in vivo optical diagnosis until endoscopists can demonstrate value in this practice through achieving similar quality outcomes with reduced cost or improved quality outcomes at similar or reduced cost. A transition toward bundled/episode payment models by payors and purchasers may promote implementation by endoscopists because endoscopists will be assuming the financial risk and the responsibility for acceptable quality for all aspects of the endoscopic procedure (including pathology). The exact cost savings and impact on quality of care generated by implementation of “optical biopsies” in clinical practice need to be determined. Future studies need to define these and other potential benefits of using endoscopic image-enhancement technologies to encourage support from payors and purchasers. Patient acceptance is also important. As it stands today, patients are generally taught that biopsies and histopathology are the best way to diagnose cancer. Patients may be unwilling to eliminate this practice from their care and there may be backlash against healthcare providers who adopt these practices out of concern that it is a lower quality of care. Initial studies evaluating patient acceptance of a “resect and discard” strategy for managing diminutive colon polyps have found that there is a significant proportion of patients who are uncomfortable with abandoning histopathology for an in vivo optical diagnosis.26Vu H.T. Sayuk G.S. Gupta N. et al.Patient preferences of a resect and discard paradigm.Gastrointest Endosc. 2015; 82: 381-384Abstract Full Text Full Text PDF PubMed Scopus (12) Google Scholar, 27Rex D.K. Patel N.J. Vemulapalli K.C. A survey of patient acceptance of resect and discard for diminutive polyps.Gastrointest Endosc. 2015; 82: 376-380Abstract Full Text Full Text PDF PubMed Scopus (18) Google Scholar Patient education needs to be developed to help gain support from these patients. In addition, some of the items previously listed (eg, guidelines from medical societies, FDA labeling, documentation of endoscopist competency, and storage of high-quality images) can all be useful in gaining patient acceptance and alleviating concerns over medical legal risk. Novel financial models, developed in conjunction with payors and purchasers, could provide alternative options for patients who remain unwilling to accept optical biopsy in lieu of tissue sampling. For example, a model wherein patients would have to pay an out-of-pocket fee for histopathology services, if they desire them, may also be effective in gaining patient acceptance. This white paper provides a general pathway as to how endoscopic image-enhancement technologies can be implemented in routine clinical practice and discusses issues related to training and competency assessment. It is hoped that this helps guide endoscopists who are interested in adopting these technologies. This is unlikely to be done by most endoscopists at this time; however, select endoscopists may have the desire, skills, and support needed to move toward this goal. Successful implementation by early adopters may help subsequent groups of endoscopists by identifying solutions to expected and unanticipated barriers. In addition, continued work by manufacturers and the GI societies in providing physician training programs, patient education, advocacy with payors and purchasers, and in creating environments and policies that motivate endoscopists to adopt new practices that demonstrate value are essential in creating widespread implementation in the United States.