Evaluating the mid-secretory endometrium appearance using hysteroscopic digital video summarization

摘要

Often, it is necessary to evaluate the mid-secretory endometrium appearance in Gynecology. For this purpose, hysteroscopic videos have been used, and are of fundamental importance nowadays for diagnosis/prognosis of several uterine pathologies. These videos are continuous (non-interrupted) video sequences, usually recorded in full. However, only a few segments of the recorded videos are relevant for diagnosis/prognosis, and need to be evaluated and referenced later. This paper proposes a new technique to identify clinically relevant segments in diagnostic hysteroscopy videos and, consequently, to find images that present the best view of the endometrium details (e.g. glandular openings and vascularization). Our method produce a rich and compact video summary which supports fast video browsing. This method is based on an extension of known properties of the singular value decomposition (SVD), and it is adaptive, in the sense that it minimizes the need of parameter adjustments. Our preliminary experimental results indicate that our method produces compact video summaries containing a selection of clinically relevant video segments. These experimental results were validated by specialists.