Diagnostic Hysteroscopy Video Summarization and Browsing

Diagnostic hysteroscopy videos are continuous (non-interrupted) video sequences, usually recorded in full. However, only a few segments of the recorded videos are relevant from the diagnosis/prognosis point of view, and need to be evaluated and referenced later. This paper proposes statistical techniques to identify clinically relevant segments in diagnostic hysteroscopy videos, and their associated key-frames, to create a rich video summary which supports video browsing. Our preliminary experimental results indicate that our method produces video summaries containing a super set of the clinically relevant video segments. A promising experimental result is that when specialists summarize the same videos manually, they usually choose from segments contained in our video summary