Endoscopic Video Manifolds for Targeted Optical Biopsy

In this work, we introduce a clustering and classification framework to facilitate re-targeting previous optical biopsy sites in surveillance upper GI-endoscopies. A new representation of endoscopic videos based on manifold learning, \emph"Endoscopic Video Manifolds" (EVMs), is proposed. The low dimensional EVM representation is adapted to facilitate two different clustering tasks; \textiti.e. clustering of informative frames and patient specific endoscopic segments, only by changing the similarity measure. Each step of the proposed framework is validated on three \emphin-vivo patient datasets containing 1834, 3445 and 1546 frames, corresponding to endoscopic videos of 73.36, 137.80 and 61.84 seconds, respectively. Improvements achieved by the introduced EVM representation are demonstrated by quantitative analysis in comparison to the original image representation and principal component analysis. Final experiments evaluating the complete framework demonstrate the feasibility of the proposed method as a promising step for assisting the endoscopic expert in re-targeting the optical biopsy sites.     «

In this work, we introduce a clustering and classification framework to facilitate re-targeting previous optical biopsy sites in surveillance upper GI-endoscopies. A new representation of endoscopic videos based on manifold learning, \emph"Endoscopic Video Manifolds" (EVMs), is proposed. The low dimensional EVM representation is adapted to facilitate two different clustering tasks; \textiti.e. clustering of informative frames and patient specific endoscopic segments, only by changing the simila...     »