Prospective development and validation of a volumetric laser endomicroscopy computer algorithm for detection of Barrett’s neoplasia

Abstract

Background and Aims: Volumetric laser endomicroscopy (VLE) is an advanced imaging modality used to detect Barrett's esophagus (BE) dysplasia. However, real-time interpretation of VLE scans is complex and timeconsuming. Computer-aided detection (CAD) may help in the process of VLE image interpretation. Our aim was to train and validate a CAD algorithm for VLE-based detection of BE neoplasia. Methods: The multicenter, VLE PREDICT study, prospectively enrolled 47 patients with BE. In total, 229 nondysplastic BE and 89 neoplastic (high-grade dysplasia/esophageal adenocarcinoma) targets were laser marked under VLE guidance and subsequently underwent a biopsy for histologic diagnosis. Deep convolutional neural networks were used to construct a CAD algorithm for differentiation between nondysplastic and neoplastic BE tissue. The CAD algorithm was trained on a set consisting of the first 22 patients (134 nondysplastic BE and 38 neoplastic targets) and validated on a separate test set from patients 23 to 47 (95 nondysplastic BE and 51 neoplastic targets). The performance of the algorithm was benchmarked against the performance of 10 VLE experts. Results: Using the training set to construct the algorithm resulted in an accuracy of 92%, sensitivity of 95%, and specificity of 92%. When performance was assessed on the test set, accuracy, sensitivity, and specificity were 85%, 91%, and 82%, respectively. The algorithm outperformed all 10 VLE experts, who demonstrated an overall accuracy of 77%, sensitivity of 70%, and specificity of 81%. Conclusions: We developed, validated, and benchmarked a VLE CAD algorithm for detection of BE neoplasia using prospectively collected and biopsy-correlated VLE targets. The algorithm detected neoplasia with high accuracy and outperformed 10 VLE experts. (The Netherlands National Trials Registry (NTR) number: NTR 6728.) (Gastrointest Endosc 2020;-:1-9.)

AGA Clinical Practice Update on New Technology and Innovation for Surveillance and Screening in Barrett’s Esophagus: Expert Review

“…21 Volumetric laser endomicroscopy, though not currently available commercially, has introduced several new advances with regards to imaging in BE, including laser marking and the interpretation of imaging using artificial intelligence. 22,23 The panelists felt strongly this was an important area where further innovation is needed, but that the use of these techniques was not required for a high-quality exam and the data to date did not support its routine use. However, the panel felt these technologies were promising and carried potential benefits in select cases and currently might be best utilized in expert centers.…”

Role of artificial intelligence in diagnosing Barrett’s esophagus-related neoplasia

“…37 In addition to standardized threshold performance requirements, guidelines that ensure quality standards during the developmental process of AI systems are urgently needed (Table 1). [19][20][21][22][23][25][26][27][28]30,35,36 Computer-aided quality control of upper gastrointestinal endoscopy AI has the potential to improve various aspects of GI endoscopy such as inter-examiner variability. For example, Pan et al 38 developed an AI system that automatically identifies the squamous-columnar junction and gastroesophageal junction on images.…”

“…In a case report of a patient with long-segment BE with no visual cues on HD-WLE or NBI and negative random biopsies, VLE-guided histological acquisition demonstrated focal low-grade dysplasia. Struyvenberg et al 35 developed an AI system with a sensitivity of 91% and specificity of 82% compared to VLE experts with a pooled sensitivity and specificity of 70% and 81%, respectively.…”

Development of Advanced Imaging and Molecular Imaging for Barrett’s Neoplasia

“…First, Qi et al demonstrated that automatic interpretation of the OCT images for diagnosing dysplastic lesions in BE patients had a sensitivity and specificity of 82% and 74%, respectively [ 40 , 102 ]. Next, Leggett et al revealed that the diagnostic accuracy for Barrett’s dysplasia by the CAD system of the VLE imaging (CAD-VLE) was better than those by manual diagnosis using the criteria of a single-center study with 50 VLE datasets for 50 EMRs, whose specimens were imaged with VLE and classified histologically into a neoplastic category (HGD/IMC) and a non-neoplastic category (LGD/ NDBE) [ 103 ]. In detail, the diagnostic accuracy of the CAD-VLE had a sensitivity of 86%, specificity of 88%, and accuracy of 87%.…”