TY - GEN
T1 - FSNet
T2 - 2019 9th International Workshop on Computer Science and Engineering, WCSE 2019
AU - Chu, Yakui
AU - Yang, Xilin
AU - Ding, Yuan
AU - Ai, Danni
AU - Fan, Jingfan
AU - Li, Xu
AU - Wang, Yongtian
AU - Yang, Jian
N1 - Publisher Copyright:
© WCSE 2019. All rights reserved.
PY - 2020
Y1 - 2020
N2 - Identification of surgical instruments is important to understand surgical scenarios and provide assistant processing in endoscopic image-guided surgery. In this paper, we propose a novel feature stacked network (FSNet) for the recognition of surgical tools in endoscopic images. With a lateral connection and concatenation operation on the different layers of the feature pyramid network, high-level semantic information is fused to low-level features, and the bounding boxes are regressed for the tool instance proposals. Then, low-level semantic information is propagated to a high-level network through the bottom-up feature concatenating path. The keypoints of tools are detected in each proposed boundary box. Two state-of-the-art end-to-end tool keypoint recognition networks and three backbones are implemented for comparison. The AP and AR of the our FSNet based on ResNeXt101 are 46.1% and 36.5%, respectively, which surpass the results of other methods.
AB - Identification of surgical instruments is important to understand surgical scenarios and provide assistant processing in endoscopic image-guided surgery. In this paper, we propose a novel feature stacked network (FSNet) for the recognition of surgical tools in endoscopic images. With a lateral connection and concatenation operation on the different layers of the feature pyramid network, high-level semantic information is fused to low-level features, and the bounding boxes are regressed for the tool instance proposals. Then, low-level semantic information is propagated to a high-level network through the bottom-up feature concatenating path. The keypoints of tools are detected in each proposed boundary box. Two state-of-the-art end-to-end tool keypoint recognition networks and three backbones are implemented for comparison. The AP and AR of the our FSNet based on ResNeXt101 are 46.1% and 36.5%, respectively, which surpass the results of other methods.
KW - Convolutional neural networks
KW - Endoscopic image
KW - Image-guided surgery
KW - Pose estimation
UR - http://www.scopus.com/inward/record.url?scp=85081106162&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85081106162
T3 - Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, WCSE 2019
SP - 427
EP - 431
BT - Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, WCSE 2019
PB - International Workshop on Computer Science and Engineering (WCSE)
Y2 - 15 June 2019 through 17 June 2019
ER -