Computer-aided diagnosis of dysplasia in Barrett’s esophagus using endoscopic optical coherence tomography

Abstract

Barrett's esophagus (BE) and associated adenocarcinoma have emerged as a major health care problem over the last two decades. Because of the widespread use of endoscopy, BE is being recognized increasingly in all Western countries. In clinical trials of endoscopic optical coherence tomography (EOCT), we defined certain image features that appear to be characteristic of precancerous (dysplastic) mucosa: decreased scattering and disorganization in the microscopic morphology. The objective of the present work is to develop computer-aided diagnosis (CAD) algorithms that aid the detection of dysplasia in BE. The image dataset used in the present study was derived from a total of 405 EOCT images (13 patients) that were paired with highly correlated histologic sections of corresponding biopsies. Of these, 106 images were included in the study. The CAD algorithm used was based on a standard texture analysis method (center-symmetric auto-correlation). Using histology as the reference standard, this CAD algorithm had a sensitivity of 82%, specificity of 74%, and accuracy of 83%. CAD has the potential to quantify and standardize the diagnosis of dysplasia and allows high throughput image evaluation for EOCT screening applications. With further refinements, CAD could also improve the accuracy of EOCT identification of dysplasia in BE.

In vivoOptical Coherence Tomography Imaging of Preinvasive Bronchial Lesions

“…However, image analysis techniques can be implemented to further investigate the ability of OCT to statistically distinguish different grades of dysplasia from CIS. These techniques include quantifying the SD in OCT signal within a region of interest (27) or texture analysis (28). Architectural measurement of the epithelial changes similar to what has been achieved in morphometric measurements in biopsy specimens (29) may provide an objective grading that is better than the visual grading of the nuclear changes in the present study.…”

Computer-aided detection of early Barrett’s neoplasia using volumetric laser endomicroscopy

“…19 12 In a successive study, a larger OCT dataset (690 OCT images from almost 100 biopsy sites) and improved image analysis methodology was used. 13 The image classification features were based on similar characteristics of neoplastic mucosa as in our study.…”

“…11 Other studies have shown that image analysis and computer-aided diagnosis can aid in classification of neoplasia in OCT images. 12,13 The aim of this study was to investigate the feasibility of a computer algorithm to detect early BE neoplasia on ex vivo VLE images.…”

Optical Coherence Tomography for Quantitative Diagnosis in Nasopharyngeal carcinoma

“…The relative strength of the optical scattering [10] and attenuation [11] in OCT images provides another parameter to differentiate normal from cancerous tissues. Joint spatial frequency and textural image analysis, which is sensitive to speckle patterns as well as tissue architectural features, can also provide distinction between cancerous and normal tissues [10][11][12] .…”