FedMed-GAN: Federated domain translation on unsupervised cross-modality brain image synthesis

J Wang, G **e, Y Huang, J Lyu, F Zheng, Y Zheng… - Neurocomputing, 2023‏ - Elsevier
Utilizing multi-modal neuroimaging data is proven to be effective in investigating human
cognitive activities and certain pathologies. However, it is not practical to obtain the full set of …

FPL+: Filtered pseudo label-based unsupervised cross-modality adaptation for 3D medical image segmentation

J Wu, D Guo, G Wang, Q Yue, H Yu… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Adapting a medical image segmentation model to a new domain is important for improving
its cross-domain transferability, and due to the expensive annotation process, Unsupervised …

Dissecting self-supervised learning methods for surgical computer vision

S Ramesh, V Srivastav, D Alapatt, T Yu, A Murali… - Medical Image …, 2023‏ - Elsevier
The field of surgical computer vision has undergone considerable breakthroughs in recent
years with the rising popularity of deep neural network-based methods. However, standard …

Cross-modality neuroimage synthesis: a survey

G **e, Y Huang, J Wang, J Lyu, F Zheng… - ACM computing …, 2023‏ - dl.acm.org
Multi-modality imaging improves disease diagnosis and reveals distinct deviations in tissues
with anatomical properties. The existence of completely aligned and paired multi-modality …

Deep-learning-based methods of attenuation correction for SPECT and PET

X Chen, C Liu - Journal of Nuclear Cardiology, 2023‏ - Elsevier
Attenuation correction (AC) is essential for quantitative analysis and clinical diagnosis of
single-photon emission computed tomography (SPECT) and positron emission tomography …

Carotid vessel wall segmentation through domain aligner, topological learning, and segment anything model for sparse annotation in mr images

X Li, X Ouyang, J Zhang, Z Ding… - … on Medical Imaging, 2024‏ - ieeexplore.ieee.org
Medical image analysis poses significant challenges due to limited availability of clinical
data, which is crucial for training accurate models. This limitation is further compounded by …

A bidirectional multilayer contrastive adaptation network with anatomical structure preservation for unpaired cross-modality medical image segmentation

H Liu, Y Zhuang, E Song, X Xu, CC Hung - Computers in Biology and …, 2022‏ - Elsevier
Multi-modal medical image segmentation has achieved great success through supervised
deep learning networks. However, because of domain shift and limited annotation …

A 3-D anatomy-guided self-training segmentation framework for unpaired cross-modality medical image segmentation

Y Zhuang, H Liu, E Song, X Xu, Y Liao… - … on Radiation and …, 2023‏ - ieeexplore.ieee.org
Unsupervised domain adaptation (UDA) methods have achieved promising performance in
alleviating the domain shift between different imaging modalities. In this article, we propose …

[HTML][HTML] Image-level supervision and self-training for transformer-based cross-modality tumor segmentation

MA de Boisredon d'Assier, A Portafaix… - Medical Image …, 2024‏ - Elsevier
Deep neural networks are commonly used for automated medical image segmentation, but
models will frequently struggle to generalize well across different imaging modalities. This …

FedMed-ATL: Misaligned unpaired cross-modality neuroimage synthesis via affine transform loss

J Wang, G **e, Y Huang, Y Zheng, Y **… - Proceedings of the 30th …, 2022‏ - dl.acm.org
The existence of completely aligned and paired multi-modal neuroimaging data has proved
its effectiveness in the diagnosis of brain diseases. However, collecting the full set of well …