TY - GEN
T1 - Recognizing surgeon's actions during suture operations from video sequences
AU - Li, Ye
AU - Ohya, Jun
AU - Chiba, Toshio
AU - Xu, Rong
AU - Yamashita, Hiromasa
PY - 2014/1/1
Y1 - 2014/1/1
N2 - Because of the shortage of nurses in the world, the realization of a robotic nurse that can support surgeries autonomously is very important. More specifically, the robotic nurse should be able to autonomously recognize different situations of surgeries so that the robotic nurse can pass necessary surgical tools to the medical doctors in a timely manner. This paper proposes and explores methods that can classify suture and tying actions during suture operations from the video sequence that observes the surgery scene that includes the surgeon's hands. First, the proposed method uses skin pixel detection and foreground extraction to detect the hand area. Then, interest points are randomly chosen from the hand area so that their 3D SIFT descriptors are computed. A word vocabulary is built by applying hierarchical K-means to these descriptors, and the words frequency histogram, which corresponds to the feature space, is computed. Finally, to classify the actions, either SVM (Support Vector Machine), Nearest Neighbor rule (NN) for the feature space or a method that combines sliding window with NN is performed. We collect 53 suture videos and 53 tying videos to build the training set and to test the proposed method experimentally. It turns out that the NN gives higher than 90% accuracies, which are better recognition than SVM. Negative actions, which are different from either suture or tying action, are recognized with quite good accuracies, while Sliding window did not show significant improvements for suture and tying and cannot recognize negative actions.
AB - Because of the shortage of nurses in the world, the realization of a robotic nurse that can support surgeries autonomously is very important. More specifically, the robotic nurse should be able to autonomously recognize different situations of surgeries so that the robotic nurse can pass necessary surgical tools to the medical doctors in a timely manner. This paper proposes and explores methods that can classify suture and tying actions during suture operations from the video sequence that observes the surgery scene that includes the surgeon's hands. First, the proposed method uses skin pixel detection and foreground extraction to detect the hand area. Then, interest points are randomly chosen from the hand area so that their 3D SIFT descriptors are computed. A word vocabulary is built by applying hierarchical K-means to these descriptors, and the words frequency histogram, which corresponds to the feature space, is computed. Finally, to classify the actions, either SVM (Support Vector Machine), Nearest Neighbor rule (NN) for the feature space or a method that combines sliding window with NN is performed. We collect 53 suture videos and 53 tying videos to build the training set and to test the proposed method experimentally. It turns out that the NN gives higher than 90% accuracies, which are better recognition than SVM. Negative actions, which are different from either suture or tying action, are recognized with quite good accuracies, while Sliding window did not show significant improvements for suture and tying and cannot recognize negative actions.
KW - 3D SIFT
KW - Action recognition
KW - Hierarchical K-means
KW - Nearest neighbor rule
KW - SVM
KW - Sliding window
KW - Suture surgery
UR - http://www.scopus.com/inward/record.url?scp=84902097168&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84902097168&partnerID=8YFLogxK
U2 - 10.1117/12.2043464
DO - 10.1117/12.2043464
M3 - Conference contribution
AN - SCOPUS:84902097168
SN - 9780819498274
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2014
PB - SPIE
T2 - Medical Imaging 2014: Image Processing
Y2 - 16 February 2014 through 18 February 2014
ER -