A Boosted Segmentation Method for Surgical Workflow Analysis. Padoy, N., Blum, T., Essa, I., Feussner, H., Berger, M., & Navab, N. In Ayache, N., Ourselin, S., & Maeder, A., editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007, of Lecture Notes in Computer Science, pages 102--109. Springer Berlin Heidelberg, January, 2007. ![A Boosted Segmentation Method for Surgical Workflow Analysis [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex As demands on hospital efficiency increase, there is a stronger need for automatic analysis, recovery, and modification of surgical workflows. Even though most of the previous work has dealt with higher level and hospital-wide workflow including issues like document management, workflow is also an important issue within the surgery room. Its study has a high potential, e.g., for building context-sensitive operating rooms, evaluating and training surgical staff, optimizing surgeries and generating automatic reports. In this paper we propose an approach to segment the surgical workflow into phases based on temporal synchronization of multidimensional state vectors. Our method is evaluated on the example of laparoscopic cholecystectomy with state vectors representing tool usage during the surgeries. The discriminative power of each instrument in regard to each phase is estimated using AdaBoost. A boosted version of the Dynamic Time Warping (DTW) algorithm is used to create a surgical reference model and to segment a newly observed surgery. Full cross-validation on ten surgeries is performed and the method is compared to standard DTW and to Hidden Markov Models.
@incollection{padoy_boosted_2007,
series = {Lecture {Notes} in {Computer} {Science}},
title = {A {Boosted} {Segmentation} {Method} for {Surgical} {Workflow} {Analysis}},
copyright = {©2007 Springer-Verlag Berlin Heidelberg},
isbn = {978-3-540-75756-6, 978-3-540-75757-3},
url = {http://link.springer.com/chapter/10.1007/978-3-540-75757-3_13},
abstract = {As demands on hospital efficiency increase, there is a stronger need for automatic analysis, recovery, and modification of surgical workflows. Even though most of the previous work has dealt with higher level and hospital-wide workflow including issues like document management, workflow is also an important issue within the surgery room. Its study has a high potential, e.g., for building context-sensitive operating rooms, evaluating and training surgical staff, optimizing surgeries and generating automatic reports. In this paper we propose an approach to segment the surgical workflow into phases based on temporal synchronization of multidimensional state vectors. Our method is evaluated on the example of laparoscopic cholecystectomy with state vectors representing tool usage during the surgeries. The discriminative power of each instrument in regard to each phase is estimated using AdaBoost. A boosted version of the Dynamic Time Warping (DTW) algorithm is used to create a surgical reference model and to segment a newly observed surgery. Full cross-validation on ten surgeries is performed and the method is compared to standard DTW and to Hidden Markov Models.},
number = {4791},
urldate = {2013-02-14TZ},
booktitle = {Medical {Image} {Computing} and {Computer}-{Assisted} {Intervention} – {MICCAI} 2007},
publisher = {Springer Berlin Heidelberg},
author = {Padoy, N. and Blum, T. and Essa, I. and Feussner, Hubertus and Berger, M.-O. and Navab, Nassir},
editor = {Ayache, Nicholas and Ourselin, Sébastien and Maeder, Anthony},
month = jan,
year = {2007},
keywords = {Artificial Intelligence (incl. Robotics), Computer Graphics, Health Informatics, Image Processing and Computer Vision, Imaging / Radiology, Pattern Recognition},
pages = {102--109}
}
Downloads: 0
{"_id":"ezMj4m7AdPPQKjdyA","bibbaseid":"padoy-blum-essa-feussner-berger-navab-aboostedsegmentationmethodforsurgicalworkflowanalysis-2007","downloads":0,"creationDate":"2017-03-07T13:13:11.300Z","title":"A Boosted Segmentation Method for Surgical Workflow Analysis","author_short":["Padoy, N.","Blum, T.","Essa, I.","Feussner, H.","Berger, M.","Navab, N."],"year":2007,"bibtype":"incollection","biburl":"http://bibbase.org/zotero/remi.wolf","bibdata":{"bibtype":"incollection","type":"incollection","series":"Lecture Notes in Computer Science","title":"A Boosted Segmentation Method for Surgical Workflow Analysis","copyright":"©2007 Springer-Verlag Berlin Heidelberg","isbn":"978-3-540-75756-6, 978-3-540-75757-3","url":"http://link.springer.com/chapter/10.1007/978-3-540-75757-3_13","abstract":"As demands on hospital efficiency increase, there is a stronger need for automatic analysis, recovery, and modification of surgical workflows. Even though most of the previous work has dealt with higher level and hospital-wide workflow including issues like document management, workflow is also an important issue within the surgery room. Its study has a high potential, e.g., for building context-sensitive operating rooms, evaluating and training surgical staff, optimizing surgeries and generating automatic reports. In this paper we propose an approach to segment the surgical workflow into phases based on temporal synchronization of multidimensional state vectors. Our method is evaluated on the example of laparoscopic cholecystectomy with state vectors representing tool usage during the surgeries. The discriminative power of each instrument in regard to each phase is estimated using AdaBoost. A boosted version of the Dynamic Time Warping (DTW) algorithm is used to create a surgical reference model and to segment a newly observed surgery. Full cross-validation on ten surgeries is performed and the method is compared to standard DTW and to Hidden Markov Models.","number":"4791","urldate":"2013-02-14TZ","booktitle":"Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007","publisher":"Springer Berlin Heidelberg","author":[{"propositions":[],"lastnames":["Padoy"],"firstnames":["N."],"suffixes":[]},{"propositions":[],"lastnames":["Blum"],"firstnames":["T."],"suffixes":[]},{"propositions":[],"lastnames":["Essa"],"firstnames":["I."],"suffixes":[]},{"propositions":[],"lastnames":["Feussner"],"firstnames":["Hubertus"],"suffixes":[]},{"propositions":[],"lastnames":["Berger"],"firstnames":["M.-O."],"suffixes":[]},{"propositions":[],"lastnames":["Navab"],"firstnames":["Nassir"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Ayache"],"firstnames":["Nicholas"],"suffixes":[]},{"propositions":[],"lastnames":["Ourselin"],"firstnames":["Sébastien"],"suffixes":[]},{"propositions":[],"lastnames":["Maeder"],"firstnames":["Anthony"],"suffixes":[]}],"month":"January","year":"2007","keywords":"Artificial Intelligence (incl. Robotics), Computer Graphics, Health Informatics, Image Processing and Computer Vision, Imaging / Radiology, Pattern Recognition","pages":"102--109","bibtex":"@incollection{padoy_boosted_2007,\n\tseries = {Lecture {Notes} in {Computer} {Science}},\n\ttitle = {A {Boosted} {Segmentation} {Method} for {Surgical} {Workflow} {Analysis}},\n\tcopyright = {©2007 Springer-Verlag Berlin Heidelberg},\n\tisbn = {978-3-540-75756-6, 978-3-540-75757-3},\n\turl = {http://link.springer.com/chapter/10.1007/978-3-540-75757-3_13},\n\tabstract = {As demands on hospital efficiency increase, there is a stronger need for automatic analysis, recovery, and modification of surgical workflows. Even though most of the previous work has dealt with higher level and hospital-wide workflow including issues like document management, workflow is also an important issue within the surgery room. Its study has a high potential, e.g., for building context-sensitive operating rooms, evaluating and training surgical staff, optimizing surgeries and generating automatic reports. In this paper we propose an approach to segment the surgical workflow into phases based on temporal synchronization of multidimensional state vectors. Our method is evaluated on the example of laparoscopic cholecystectomy with state vectors representing tool usage during the surgeries. The discriminative power of each instrument in regard to each phase is estimated using AdaBoost. A boosted version of the Dynamic Time Warping (DTW) algorithm is used to create a surgical reference model and to segment a newly observed surgery. Full cross-validation on ten surgeries is performed and the method is compared to standard DTW and to Hidden Markov Models.},\n\tnumber = {4791},\n\turldate = {2013-02-14TZ},\n\tbooktitle = {Medical {Image} {Computing} and {Computer}-{Assisted} {Intervention} – {MICCAI} 2007},\n\tpublisher = {Springer Berlin Heidelberg},\n\tauthor = {Padoy, N. and Blum, T. and Essa, I. and Feussner, Hubertus and Berger, M.-O. and Navab, Nassir},\n\teditor = {Ayache, Nicholas and Ourselin, Sébastien and Maeder, Anthony},\n\tmonth = jan,\n\tyear = {2007},\n\tkeywords = {Artificial Intelligence (incl. Robotics), Computer Graphics, Health Informatics, Image Processing and Computer Vision, Imaging / Radiology, Pattern Recognition},\n\tpages = {102--109}\n}\n\n","author_short":["Padoy, N.","Blum, T.","Essa, I.","Feussner, H.","Berger, M.","Navab, N."],"editor_short":["Ayache, N.","Ourselin, S.","Maeder, A."],"key":"padoy_boosted_2007","id":"padoy_boosted_2007","bibbaseid":"padoy-blum-essa-feussner-berger-navab-aboostedsegmentationmethodforsurgicalworkflowanalysis-2007","role":"author","urls":{"Paper":"http://link.springer.com/chapter/10.1007/978-3-540-75757-3_13"},"keyword":["Artificial Intelligence (incl. Robotics)","Computer Graphics","Health Informatics","Image Processing and Computer Vision","Imaging / Radiology","Pattern Recognition"],"downloads":0},"search_terms":["boosted","segmentation","method","surgical","workflow","analysis","padoy","blum","essa","feussner","berger","navab"],"keywords":["artificial intelligence (incl. robotics)","computer graphics","health informatics","image processing and computer vision","imaging / radiology","pattern recognition"],"authorIDs":[],"dataSources":["AvgwXzHNvzrPfaxbA"]}