Clinical utility of wide-area transepithelial sampling with three-dimensional computer-assisted analysis (WATS3D) in identifying Barrett's esophagus and associated neoplasia

Benefit of adjunctive wide-area transepithelial sampling with 3-dimensional computer-assisted analysis plus forceps biopsy based on Barrett's esophagus segment length

BACKGROUND AND AIMS

Wide-area transepithelial sampling with 3-dimensional computer-assisted analysis (WATS-3D) has been shown to increase the diagnostic yield of intestinal metaplasia (IM) and dysplasia within a segment of suspected or known Barrett's esophagus (BE) when used as an adjunct to forceps biopsies. Few data are available regarding how segment length affects WATS-3D yield. The purpose of this study was to evaluate adjunctive WATS-3D use in patients with varying lengths of BE.

METHODS

A total of 8471 patients (52.5% male; mean age, 63 years) enrolled in 2 registry studies were included in this study. All patients were being screened or surveyed for BE with both forceps biopsies and WATS-3D. The adjunctive and absolute yield of WATS-3D was calculated according to the length of the patient's BE segment.

RESULTS

The overall adjunctive and absolute increased diagnostic yields with WATS-3D were 47.6% and 17.5%, respectively, for detection of IM, and 139% and 2.4% for detection of dysplasia. IM and dysplasia detection both increased with the use of WATS-3D regardless of segment length. Increase in IM diagnostic yield was significantly higher in short- versus long-segment cases but higher in long-segment cases for dysplasia detection.

CONCLUSIONS

This study shows that when WATS-3D is added as an adjunct to forceps biopsies, it is effective at increasing the diagnostic yield of both BE and associated dysplasia in patients with both short and long segments of esophageal columnar-lined epithelium.

Role of Wide-Area Transepithelial Sampling With 3D Computer-Assisted Analysis in the Diagnosis and Management of Barrett's Esophagus

Barrett's esophagus (BE) is a premalignant condition in which cancer prevention is performed by endoscopic surveillance combined with Seattle protocol mucosal biopsies. The Seattle protocol has significant limitations, including a high rate of sampling error due to the focality of dysplasia/carcinoma, low endoscopist adherence to the protocol, and a high degree of variability in pathologic interpretation. These factors all contribute to a high incidence of cancers missed within 1 year of surveillance endoscopy. Wide-area transepithelial sampling with computer-assisted three-dimensional analysis (WATS3D) is a relatively new technique that minimizes sampling error by using a brush biopsy device that extensively samples "at risk" mucosa and helps pathologists diagnose dysplasia/neoplasia by generating three-dimensional images of whole crypts using a neural network-based software program. Several large prospective trials (involving both academic and community practices) have shown significantly increased rates of detection of dysplasia and intestinal metaplasia in both screening and surveillance in patients with BE when used as an adjunct to Seattle protocol-based forceps biopsies. The WATS3D diagnostic platform was included in the most recent American Society for Gastrointestinal Endoscopy Barrett's guideline as an adjunct to forceps biopsies (conditional recommendation and low quality of evidence). This review summarizes the scientific and pathologic basis of WATS3D technology, its potential impact on BE surveillance and management, and its limitations and future directions.

Applications of Artificial Intelligence for the Diagnosis of Gastrointestinal Diseases

The development of convolutional neural networks has achieved impressive advances of machine learning in recent years, leading to an increasing use of artificial intelligence (AI) in the field of gastrointestinal (GI) diseases. AI networks have been trained to differentiate benign from malignant lesions, analyze endoscopic and radiological GI images, and assess histological diagnoses, obtaining excellent results and high overall diagnostic accuracy. Nevertheless, there data are lacking on side effects of AI in the gastroenterology field, and high-quality studies comparing the performance of AI networks to health care professionals are still limited. Thus, large, controlled trials in real-time clinical settings are warranted to assess the role of AI in daily clinical practice. This narrative review gives an overview of some of the most relevant potential applications of AI for gastrointestinal diseases, highlighting advantages and main limitations and providing considerations for future development.