Episode Classification for the Analysis of Tissue/Instrument Interaction with Multiple Visual Cues. Lo, B. P. L., Darzi, A., & Yang, G. In Ellis, R. E. & Peters, T. M., editors, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2003, of Lecture Notes in Computer Science, pages 230--237. Springer Berlin Heidelberg, January, 2003.
Episode Classification for the Analysis of Tissue/Instrument Interaction with Multiple Visual Cues [link]Paper  abstract   bibtex   
The assessment of surgical skills for Minimally Invasive Surgery (MIS) has traditionally been conducted with visual observation and objective scoring. This paper presents a practical framework for the detection of instrument/tissue interaction from MIS video sequences by incorporating multiple visual cues. The proposed technique investigates the characteristics of four major events involved in MIS procedures including idle, retraction, cauterisation and suturing. Constant instrument tracking is maintained and multiple visual cues related to shape, deformation, changes in light reflection and other low level images featured are combined in a Bayesian framework to achieve an overall frame-by-frame classification accuracy of 77% and episode classification accuracy of 85%.
@incollection{lo_episode_2003,
	series = {Lecture {Notes} in {Computer} {Science}},
	title = {Episode {Classification} for the {Analysis} of {Tissue}/{Instrument} {Interaction} with {Multiple} {Visual} {Cues}},
	copyright = {©2003 Springer-Verlag Berlin Heidelberg},
	isbn = {978-3-540-20462-6, 978-3-540-39899-8},
	url = {http://link.springer.com/chapter/10.1007/978-3-540-39899-8_29},
	abstract = {The assessment of surgical skills for Minimally Invasive Surgery (MIS) has traditionally been conducted with visual observation and objective scoring. This paper presents a practical framework for the detection of instrument/tissue interaction from MIS video sequences by incorporating multiple visual cues. The proposed technique investigates the characteristics of four major events involved in MIS procedures including idle, retraction, cauterisation and suturing. Constant instrument tracking is maintained and multiple visual cues related to shape, deformation, changes in light reflection and other low level images featured are combined in a Bayesian framework to achieve an overall frame-by-frame classification accuracy of 77\% and episode classification accuracy of 85\%.},
	number = {2878},
	urldate = {2013-02-12TZ},
	booktitle = {Medical {Image} {Computing} and {Computer}-{Assisted} {Intervention} - {MICCAI} 2003},
	publisher = {Springer Berlin Heidelberg},
	author = {Lo, Benny P. L. and Darzi, Ara and Yang, Guang-Zhong},
	editor = {Ellis, Randy E. and Peters, Terry M.},
	month = jan,
	year = {2003},
	keywords = {Artificial Intelligence (incl. Robotics), Computer Graphics, Health Informatics, Image Processing and Computer Vision, Imaging / Radiology, Pattern Recognition},
	pages = {230--237}
}

Downloads: 0