Are gastroenterologists willing to implement imaging-guided surveillance for Barrett's esophagus? Results from a national survey

Optical Biopsy of Dysplasia in Barrett's Oesophagus Assisted by Artificial Intelligence

Optical biopsy in Barrett's oesophagus (BE) using endocytoscopy (EC) could optimize endoscopic screening. However, the identification of dysplasia is challenging due to the complex interpretation of the highly detailed images. Therefore, we assessed whether using artificial intelligence (AI) as second assessor could help gastroenterologists in interpreting endocytoscopic BE images. First, we prospectively videotaped 52 BE patients with EC. Then we trained and tested the AI pm distinct datasets drawn from 83,277 frames, developed an endocytoscopic BE classification system, and designed online training and testing modules. We invited two successive cohorts for these online modules: 10 endoscopists to validate the classification system and 12 gastroenterologists to evaluate AI as second assessor by providing six of them with the option to request AI assistance. Training the endoscopists in the classification system established an improved sensitivity of 90.0% (+32.67%, p < 0.001) and an accuracy of 77.67% (+13.0%, p = 0.020) compared with the baseline. However, these values deteriorated at follow-up (-16.67%, p < 0.001 and -8.0%, p = 0.009). Contrastingly, AI-assisted gastroenterologists maintained high sensitivity and accuracy at follow-up, subsequently outperforming the unassisted gastroenterologists (+20.0%, p = 0.025 and +12.22%, p = 0.05). Thus, best diagnostic scores for the identification of dysplasia emerged through human-machine collaboration between trained gastroenterologists with AI as the second assessor. Therefore, AI could support clinical implementation of optical biopsies through EC.

A Survey of Expert Practice and Attitudes Regarding Advanced Imaging Modalities in Surveillance of Barrett's Esophagus

BACKGROUND

Published guidelines do not address what the minimum incremental diagnostic yield (IDY) for detection of dysplasia/cancer is required over the standard Seattle protocol for an advanced imaging modality (AIM) to be implemented in routine surveillance of Barrett's esophagus (BE) patients. We aimed to report expert practice patterns and attitudes, specifically addressing the minimum IDY in the use of AIMs in BE surveillance.

METHODS

An international group of BE experts completed an anonymous electronic survey of domains relevant to surveillance practice patterns and use of AIMs. The evaluated AIMs were conventional chromoendoscopy (CC), virtual chromoendoscopy (VC), volumetric laser endomicroscopy (VLE), confocal laser endomicroscopy (CLE), and wide-area transepithelial sampling (WATS^3D). Responses were recorded using five-point balanced Likert items and analyzed as continuous variables.

RESULTS

The survey response rate was 84% (61/73)-41 US and 20 non-US. Experts were most comfortable with and routinely use VC and CC, and least comfortable with and rarely use VLE, CLE, and WATS^3D. Experts rated data from randomized controlled trials (1.4 ± 0.9) and guidelines (2.6 ± 1.2) as the two most influential factors for implementing AIMs in clinical practice. The minimum IDY of AIMs over standard biopsies to be considered of clinical benefit was lowest for VC (15%, IQR 10-29%) and highest for VLE (30%, IQR 20-50%). Compared to US experts, non-US experts reported higher use of CC for BE surveillance (p < 0.001).

CONCLUSION

These results should inform benchmarks that need to be met for guidelines to recommend the routine use of AIMs in the surveillance of BE patients.

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.

Recent Updates in the Endoscopic Diagnosis of Barrett's Oesophagus

BACKGROUND

Barrett's oesophagus (BO) is a premalignant condition associated with the development of oesophageal adenocarcinoma (OAC). Despite the low risk of progression per annum, OAC is associated with significant morbidity and mortality, with an estimated 5-year survival of 10%. Furthermore, the incidence of OAC continues to rise globally. Therefore, it is imperative to detect the premalignant phase of BO and follow up such patients accordingly.

SUMMARY

The mainstay diagnosis of BO is endoscopy and biopsy sampling. However, limitations with white light endoscopy (WLE) and undertaking biopsies have shifted the current focus towards real-time image analysis. Utilization of additional tools such as chromoendoscopy, narrow-band imaging (NBI), confocal laser endomicroscopy (CLE), and optical coherence tomography (OCT) are proving beneficial. Furthermore, it is also becoming more apparent that often these tools are utilized by experts in the field. Therefore, for the non-expert, training in these systems is key. Currently as yet, the methodologies used for training optimization require further inquiry.

KEY MESSAGE

(1) Real-time imaging can serve to minimize excess biopsies. (2) Tools such as chromoendoscopy, NBI, CLE, and OCT can help to compliment WLE.

PRACTICAL IMPLICATIONS

WLE is associated with limited sensitivity. Biopsy sampling is cost-ineffective and associated with sampling error. Hence, from a practical perspective, endoscopists should aim to utilize additional tools to help in real-time image interpretation and minimize an overreliance on histology.