TY - GEN
T1 - Improving OCTA Imaging Through Cross-Domain Adaptation
T2 - 28th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2025
AU - Yang, Bingyu
AU - Tan, Bingyao
AU - Gu, Zaiwang
AU - Schmetterer, Leopold
AU - Li, Huiqi
AU - Cheng, Jun
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - Deep learning has been introduced into optical coherence tomography angiography (OCTA) imaging, which is a non-invasive technique for visualizing vascular structures. Intralipid injection has shown promise in improving blood cell scattering for better OCTA imaging. However, administering intralipid to human subjects for imaging purposes may raise ethical concerns. To address this challenge, we acquire intralipid-enhanced OCTA in rats and introduce cross-domain learning to address the domain shifts. Specifically, we collect data from eyes of anesthetized rats to obtain motion-free data and introduce a noise-guided self-training framework to bridge the domain gaps between rats and primates. Additionally, an en face enhancement loss is incorporated to further refine en face vectors during adaptation. Compared with other classical and fully supervised OCTA imaging algorithms, our method improves B-scan denoising performance by 53.1% and 65.0% on CNR and BRISQUE in human subjects respectively, while enhancing vessel contrast in en face images.
AB - Deep learning has been introduced into optical coherence tomography angiography (OCTA) imaging, which is a non-invasive technique for visualizing vascular structures. Intralipid injection has shown promise in improving blood cell scattering for better OCTA imaging. However, administering intralipid to human subjects for imaging purposes may raise ethical concerns. To address this challenge, we acquire intralipid-enhanced OCTA in rats and introduce cross-domain learning to address the domain shifts. Specifically, we collect data from eyes of anesthetized rats to obtain motion-free data and introduce a noise-guided self-training framework to bridge the domain gaps between rats and primates. Additionally, an en face enhancement loss is incorporated to further refine en face vectors during adaptation. Compared with other classical and fully supervised OCTA imaging algorithms, our method improves B-scan denoising performance by 53.1% and 65.0% on CNR and BRISQUE in human subjects respectively, while enhancing vessel contrast in en face images.
KW - Domain adaptation
KW - Image enhancement
KW - OCTA
KW - Self-training
UR - https://www.scopus.com/pages/publications/105017856322
U2 - 10.1007/978-3-032-04981-0_27
DO - 10.1007/978-3-032-04981-0_27
M3 - Conference contribution
AN - SCOPUS:105017856322
SN - 9783032049803
T3 - Lecture Notes in Computer Science
SP - 282
EP - 292
BT - Medical Image Computing and Computer Assisted Intervention, MICCAI 2025 - 28th International Conference, Proceedings
A2 - Gee, James C.
A2 - Hong, Jaesung
A2 - Sudre, Carole H.
A2 - Golland, Polina
A2 - Alexander, Daniel C.
A2 - Iglesias, Juan Eugenio
A2 - Venkataraman, Archana
A2 - Kim, Jong Hyo
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 23 September 2025 through 27 September 2025
ER -