TY - GEN
T1 - Regularized Adversarial Training (RAT) for Robust Cellular Electron Cryo Tomograms Classification
AU - Wu, Xindi
AU - Mao, Yijun
AU - Wang, Haohan
AU - Zeng, Xiangrui
AU - Gao, Xin
AU - Xing, Eric P.
AU - Xu, Min
N1 - KAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): FCC/1/1976-18, FCC/1/1976-23, FCC/1/1976-26, BAS/1/1624, FCC/1/1976-25
Acknowledgements: This work was supported in part by U.S. National Institutes of Health (NIH) grant P41 GM103712. HW was supported by the National Institutes of Health grants R01-GM093156 and P30-DA035778. XZ was supported by a fellowship from Carnegie Mellon University’s Center for Machine Learning and Health. XG was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. BAS/1/1624, FCC/1/1976-18, FCC/1/1976-23, FCC/1/1976-25, and FCC/1/1976-26.
PY - 2020/2/7
Y1 - 2020/2/7
N2 - Cellular Electron Cryo Tomography (CECT) 3D imaging has permitted biomedical community to study macromolecule structures inside single cells with deep learning approaches. Many deep learning-based methods have since been developed to classify macromolecule structures from tomograms with high accuracy. However, several recent studies have demonstrated the lack of robustness in these models against often-imperceptible, designed changes of input. Therefore, making existing subtomogram-classification models robust remains a serious challenge. In this paper, we study the robustness of the state-of-the-art subtomogram classifier on CECT images and propose a method called Regularized Adversarial Training (RAT) to defend the classifier against a wide range of designed threats. Our results show that RAT improves robustness for CECT image classification over the previous methods.
AB - Cellular Electron Cryo Tomography (CECT) 3D imaging has permitted biomedical community to study macromolecule structures inside single cells with deep learning approaches. Many deep learning-based methods have since been developed to classify macromolecule structures from tomograms with high accuracy. However, several recent studies have demonstrated the lack of robustness in these models against often-imperceptible, designed changes of input. Therefore, making existing subtomogram-classification models robust remains a serious challenge. In this paper, we study the robustness of the state-of-the-art subtomogram classifier on CECT images and propose a method called Regularized Adversarial Training (RAT) to defend the classifier against a wide range of designed threats. Our results show that RAT improves robustness for CECT image classification over the previous methods.
UR - http://hdl.handle.net/10754/661374
UR - https://ieeexplore.ieee.org/document/8982954/
UR - http://www.scopus.com/inward/record.url?scp=85084337154&partnerID=8YFLogxK
U2 - 10.1109/BIBM47256.2019.8982954
DO - 10.1109/BIBM47256.2019.8982954
M3 - Conference contribution
SN - 9781728118673
SP - 52
EP - 67
BT - 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
PB - IEEE
ER -