Next Article in Journal
Design and Implementation of a Wireless Sensor Network for Seismic Monitoring of Buildings
Previous Article in Journal
Field Test and Numerical Simulation on the Long-Term Thermal Response of PHC Energy Pile in Layered Foundation
 
 
Article

An Analysis of the Vulnerability of Two Common Deep Learning-Based Medical Image Segmentation Techniques to Model Inversion Attacks

by 1,2,3,*, 1,2,3, 1,2,3 and 1,2,3
1
Department of Radiology, University of Calgary, Calgary, AB T2N 1N4, Canada
2
Hotchkiss Brain Institute, University of Calgary, Calgary, AB T2N 1N4, Canada
3
Alberta Children’s Hospital Research Institute, University of Calgary, Calgary, AB T2N 1N4, Canada
*
Author to whom correspondence should be addressed.
Academic Editors: Ben Hamza and Steve Ling
Sensors 2021, 21(11), 3874; https://doi.org/10.3390/s21113874
Received: 15 March 2021 / Revised: 28 May 2021 / Accepted: 31 May 2021 / Published: 4 June 2021
(This article belongs to the Section Intelligent Sensors)
Recent research in computer vision has shown that original images used for training of deep learning models can be reconstructed using so-called inversion attacks. However, the feasibility of this attack type has not been investigated for complex 3D medical images. Thus, the aim of this study was to examine the vulnerability of deep learning techniques used in medical imaging to model inversion attacks and investigate multiple quantitative metrics to evaluate the quality of the reconstructed images. For the development and evaluation of model inversion attacks, the public LPBA40 database consisting of 40 brain MRI scans with corresponding segmentations of the gyri and deep grey matter brain structures were used to train two popular deep convolutional neural networks, namely a U-Net and SegNet, and corresponding inversion decoders. Matthews correlation coefficient, the structural similarity index measure (SSIM), and the magnitude of the deformation field resulting from non-linear registration of the original and reconstructed images were used to evaluate the reconstruction accuracy. A comparison of the similarity metrics revealed that the SSIM is best suited to evaluate the reconstruction accuray, followed closely by the magnitude of the deformation field. The quantitative evaluation of the reconstructed images revealed SSIM scores of 0.73±0.12 and 0.61±0.12 for the U-Net and the SegNet, respectively. The qualitative evaluation showed that training images can be reconstructed with some degradation due to blurring but can be correctly matched to the original images in the majority of the cases. In conclusion, the results of this study indicate that it is possible to reconstruct patient data used for training of convolutional neural networks and that the SSIM is a good metric to assess the reconstruction accuracy. View Full-Text
Keywords: medical imaging; deep neural networks; inversion attacks; patient privacy medical imaging; deep neural networks; inversion attacks; patient privacy
Show Figures

Figure 1

MDPI and ACS Style

Subbanna, N.; Wilms, M.; Tuladhar, A.; Forkert, N.D. An Analysis of the Vulnerability of Two Common Deep Learning-Based Medical Image Segmentation Techniques to Model Inversion Attacks. Sensors 2021, 21, 3874. https://doi.org/10.3390/s21113874

AMA Style

Subbanna N, Wilms M, Tuladhar A, Forkert ND. An Analysis of the Vulnerability of Two Common Deep Learning-Based Medical Image Segmentation Techniques to Model Inversion Attacks. Sensors. 2021; 21(11):3874. https://doi.org/10.3390/s21113874

Chicago/Turabian Style

Subbanna, Nagesh, Matthias Wilms, Anup Tuladhar, and Nils D. Forkert. 2021. "An Analysis of the Vulnerability of Two Common Deep Learning-Based Medical Image Segmentation Techniques to Model Inversion Attacks" Sensors 21, no. 11: 3874. https://doi.org/10.3390/s21113874

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop