Mutual Information-Based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging

Meng Q, Matthew J, Zimmer VA, Gomez A, Lloyd DFA, Rueckert D, Kainz B (2021)

Publication Type: Journal article

Publication year: 2021

Journal

IEEE Transactions on Medical Imaging Institute of Electrical and Electronics Engineers (IEEE)

Book Volume: 40

Pages Range: 722-734

Article Number: 9247170

Journal Issue: 2

DOI: 10.1109/TMI.2020.3035424

Abstract

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 address 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 MIDNet 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 ultrasound 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.

Authors with CRIS profile

Bernhard Kainz

Involved external institutions

Imperial College London / The Imperial College of Science, Technology and Medicine GB United Kingdom (GB) King’s College London GB United Kingdom (GB)

How to cite

APA:

Meng, Q., Matthew, J., Zimmer, V.A., Gomez, A., Lloyd, D.F.A., Rueckert, D., & Kainz, B. (2021). Mutual Information-Based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging. IEEE Transactions on Medical Imaging, 40(2), 722-734. https://doi.org/10.1109/TMI.2020.3035424

MLA:

Meng, Qingjie, et al. "Mutual Information-Based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging." IEEE Transactions on Medical Imaging 40.2 (2021): 722-734.

BibTeX: Download