Imperial College London
Portrait Picture

DR BERNHARD KAINZ

Faculty of Engineering, Department of Computing

Reader in Medical Image Computing
 
 
 
//

Contact

 

+44 (0)20 7594 8349b.kainz Website CV

 
 
//

Location

 

372Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Meng:2021:10.1109/TMI.2020.3035424,
author = {Meng, Q and Matthew, J and Zimmer, VA and Gomez, A and Lloyd, DFA and Rueckert, D and Kainz, B},
doi = {10.1109/TMI.2020.3035424},
journal = {IEEE Transactions on Medical Imaging},
pages = {722--734},
title = {Mutual information-based disentangled neural networks for classifying unseen categories in different domains: application to fetal ultrasound imaging},
url = {http://dx.doi.org/10.1109/TMI.2020.3035424},
volume = {40},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Deep neural networks exhibit limited generalizability across images with different entangled domain features and categorical features. Learning generalizable features that can form universal categorical decision boundaries  across  domains  is  an  interesting  and  difficult  challenge. This problem occurs frequently in medical imaging applications  when  attempts  are  made  to  deploy  and  improve deep learning models across different image acquisition  devices,  across  acquisition  parameters  or  if  some classes are unavailable in new training databases. To ad-dress this problem, we propose Mutual Information-based Disentangled Neural Networks (MIDNet), which extract generalizable  categorical  features  to  transfer  knowledge  to unseen categories in a target domain. The proposed MID-Net  adopts  a  semi-supervised  learning  paradigm  to  alleviate  the  dependency  on  labeled  data.  This  is  important for real-world applications where data annotation is time-consuming, costly and requires training and expertise. We extensively  evaluate  the  proposed  method  on  fetal  ultra-sound datasets for two different image classification tasks where domain features are respectively defined by shadow artifacts  and  image  acquisition  devices.  Experimental  results  show  that  the  proposed  method  outperforms  the state-of-the-art on the classification of unseen categories in a target domain with sparsely labeled training data.
AU  - Meng,Q
AU  - Matthew,J
AU  - Zimmer,VA
AU  - Gomez,A
AU  - Lloyd,DFA
AU  - Rueckert,D
AU  - Kainz,B
DO  - 10.1109/TMI.2020.3035424
EP  - 734
PY  - 2021///
SN  - 0278-0062
SP  - 722
TI  - Mutual information-based disentangled neural networks for classifying unseen categories in different domains: application to fetal ultrasound imaging
T2  - IEEE Transactions on Medical Imaging
UR  - http://dx.doi.org/10.1109/TMI.2020.3035424
UR  - https://ieeexplore.ieee.org/document/9247170
UR  - http://hdl.handle.net/10044/1/85127
VL  - 40
ER  -
Download