Application of wavelet scattering networks in classification of ultrasound image sequences

Published on Sep 1, 2017
· DOI :10.1109/ULTSYM.2017.8091649
Amir Khan7
Estimated H-index: 7
(GMU: George Mason University),
Ananya S. Dhawan (GMU: George Mason University)+ 2 AuthorsSiddhartha Sikdar16
Estimated H-index: 16
(GMU: George Mason University)
Recently, ultrasound imaging of muscle contractions has been used by several research groups to infer volitional motor intent of the user, and has shown promise as a novel muscle computer interface. Learning spatiotemporal features from ultrasound image sequences is challenging because of deformations introduced by probe repositioning. The image features are sensitive to probe placement and even small displacements during cross-session donning and doffing of the probe could compromise the classification accuracy when using a model trained on a previous session. This requires frequent recalibration. Deep learning based feature extractors have been shown to be invariant to translation, rotation and slight deformations. In this study, we investigated the feasibility of wavelet-based deep scattering features to preserve motion classification accuracy across multiple donning and doffing sessions. It was demonstrated that scattering features, which do not require learning filter weights, can significantly improve the cross-session classification accuracy by 20–30%. It can be concluded that these features are robust to minor probe displacements. They need to be further investigated with a larger data set to investigate their robustness in accurately classifying different muscle movements.
  • References (13)
  • Citations (0)
#1Weichao Guo (SJTU: Shanghai Jiao Tong University)H-Index: 4
#2Xinjun Sheng (SJTU: Shanghai Jiao Tong University)H-Index: 15
Last.Xiangyang Zhu (SJTU: Shanghai Jiao Tong University)H-Index: 21
view all 4 authors...
May 2, 2017 in CHI (Human Factors in Computing Systems)
#1Jess McIntosh (UoB: University of Bristol)H-Index: 5
#2Asier Marzo (UoB: University of Bristol)H-Index: 10
Last.Carol Phillips (University Hospitals Bristol NHS Foundation Trust)H-Index: 1
view all 4 authors...
#1Muhammad Ahmad (National University of Sciences and Technology)H-Index: 4
#2Awais M. Kamboh (National University of Sciences and Technology)H-Index: 7
Last.Amir Khan (National University of Sciences and Technology)H-Index: 7
view all 4 authors...
#1Nima Akhlaghi (GMU: George Mason University)H-Index: 3
#2Clayton A. Baker (GMU: George Mason University)H-Index: 2
Last.Siddhartha Sikdar (GMU: George Mason University)H-Index: 16
view all 10 authors...
Jun 1, 2011 in CVPR (Computer Vision and Pattern Recognition)
#1Joan Bruna (École Polytechnique)H-Index: 21
#2Stéphane Mallat (École Polytechnique)H-Index: 43
Oct 4, 2009 in UIST (User Interface Software and Technology)
#1T. Scott Saponas (UW: University of Washington)H-Index: 21
#2Desney S. Tan (Microsoft)H-Index: 50
Last.James A. Landay (UW: University of Washington)H-Index: 60
view all 6 authors...
View next paperFeature Selection and Non-Linear Classifiers: Effects on Simultaneous Motion Recognition in Upper Limb