Large-scale CT image studies often suffer from a lack of homogeneity regarding radiomic characteristics due to the images acquired with scanners from different vendors or with different reconstruction algorithms. We propose a deep learning-based framework called UDA-CT to tackle the homogeneity issue by leveraging both paired and unpaired images. Using UDA-CT, the CT images can be standardized both from different acquisition protocols of the same scanner and CT images acquired using a similar protocol but scanners from different vendors. UDA-CT incorporates recent advances in deep learning including domain adaptation and adversarial augmentation. It includes a unique design for model training batch which integrates nonstandard images and their adversarial variations to enhance model generalizability. The experimental results show that UDA-CT significantly improves the performance of the cross-scanner image standardization by utilizing both paired and unpaired data.
|Title of host publication||Proceedings - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022|
|Editors||Donald Adjeroh, Qi Long, Xinghua Shi, Fei Guo, Xiaohua Hu, Srinivas Aluru, Giri Narasimhan, Jianxin Wang, Mingon Kang, Ananda M. Mondal, Jin Liu|
|Number of pages||4|
|State||Published - 2022|
|Event||2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022 - Las Vegas, United States|
Duration: Dec 6 2022 → Dec 8 2022
|Name||Proceedings - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022|
|Conference||2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022|
|Period||12/6/22 → 12/8/22|
Bibliographical noteFunding Information:
ACKNOWLEDGMENT This research is supported by NIH NCI (grant no. 1R21CA231911) and Kentucky Lung Cancer Research (grant no. KLCR-3048113817).
© 2022 IEEE.
- Computed Tomography
- Domain Adaptation
- Generative Adversarial Network
- Image Synthesis
ASJC Scopus subject areas
- Psychiatry and Mental health
- Information Systems and Management
- Biomedical Engineering
- Medicine (miscellaneous)
- Cardiology and Cardiovascular Medicine
- Health Informatics