Post-surgical Endometriosis Segmentation in Laparoscopic Videos
This addresses the difficulty in identifying endometriosis for gynecologic physicians, but it is incremental as it focuses on one specific visual appearance.
The paper tackles the problem of segmenting dark endometrial implants in laparoscopic surgery videos to assist gynecologic physicians, resulting in a system that annotates identified regions with multi-colored overlays and provides a detection summary for improved video browsing.
Endometriosis is a common women's condition exhibiting a manifold visual appearance in various body-internal locations. Having such properties makes its identification very difficult and error-prone, at least for laymen and non-specialized medical practitioners. In an attempt to provide assistance to gynecologic physicians treating endometriosis, this demo paper describes a system that is trained to segment one frequently occurring visual appearance of endometriosis, namely dark endometrial implants. The system is capable of analyzing laparoscopic surgery videos, annotating identified implant regions with multi-colored overlays and displaying a detection summary for improved video browsing.