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

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 time-consuming. 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.).

Confocal reflectance imaging of head and neck surgical specimens. A comparison with histologic analysis.

BACKGROUND: Confocal reflectance microscopy (CRM) is an optical method of imaging tissue noninvasively without the need for fixation, sectioning, and staining as in standard histopathologic analysis. Image contrast is determined by natural differences in refractive indices of organelles and other subcellular structures within the tissues. Gray-scale images are displayed in real time on a video monitor and represent horizontal (en face) optical sections through the tissue. We hypothesized that CRM is capable of discerning histologic characteristics of different tissues in the head and neck. OBJECTIVES: To examine the microscopic anatomy of freshly excised head and neck surgical specimens en bloc using CRM and to compare the findings with those generated by conventional histologic analysis. DESIGN: This was a pilot observational cohort study. Bone, muscle, nerve, thyroid, parotid, and ethmoid mucosa from human surgical specimens were imaged immediately after excision. Confocal images were compared with corresponding routine paraffin-embedded, hematoxylin-eosin-stained sections obtained from the same tissue. RESULTS: Characteristic histologic features of various tissues and cell types were readily discernible by CRM and correlated well with permanent sections. However, in all tissues examined, there was less microscopic detail visible in the CRM images than was appreciated in paraffin-embedded histologic sections. CONCLUSIONS: The CRM images revealed cytologic features without the artifacts of histologic processing and thus may have the potential for use as an adjunct to frozen-section analysis in intraoperative consultation.