5,496 Hits in 5.4 sec

Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation

Anirudh Choudhary, Li Tong, Yuanda Zhu, May D. Wang
2020 IMIA Yearbook of Medical Informatics  
Domain adaptation (DA) has been developed to transfer the knowledge from a labeled data domain to a related but unlabeled domain in either image space or feature space.  ...  We highlighted the role of unsupervised DA in image segmentation and described opportunities for future development.  ...  For example, in cross-modality adaptation, Zhang et al., [75] applied a domain discriminator to adapt models trained for pathology images to microscopy images.  ... 
doi:10.1055/s-0040-1702009 pmid:32823306 fatcat:gtlhoh6m3fh4hcumfzdlpdohr4

MT-UDA: Towards Unsupervised Cross-modality Medical Image Segmentation with Limited Source Labels [chapter]

Ziyuan Zhao, Kaixin Xu, Shumeng Li, Zeng Zeng, Cuntai Guan
2021 Lecture Notes in Computer Science  
We aim to investigate how to efficiently leverage unlabeled data from the source and target domains with limited source annotations for cross-modality image segmentation.  ...  Although deep unsupervised domain adaptation (UDA) can leverage well-established source domain annotations and abundant target domain data to facilitate cross-modality image segmentation and also mitigate  ...  This research is supported by Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR), Singapore.  ... 
doi:10.1007/978-3-030-87193-2_28 fatcat:cmqrhlvgpvba5kape4qawz5eti

Unsupervised Black-Box Model Domain Adaptation for Brain Tumor Segmentation

Xiaofeng Liu, Chaehwa Yoo, Fangxu Xing, C.-C. Jay Kuo, Georges El Fakhri, Je-Won Kang, Jonghye Woo
2022 Frontiers in Neuroscience  
The majority of prior work has relied on both source and target domain data for adaptation.  ...  To address this issue, we propose a practical framework for UDA with a black-box segmentation model trained in the source domain only, without relying on source data or a white-box source model in which  ...  ., 2021k) and UDA with source data (Shanis et al., 2019) , there are two evaluation protocols for UDA, i.e., cross-subtype and cross-modality UDA segmentation.  ... 
doi:10.3389/fnins.2022.837646 pmid:35720708 pmcid:PMC9201342 fatcat:srpmcqkmybhedcqxu64ef7bm7u

Unsupervised Domain Adaptation Network With Category-Centric Prototype Aligner for Biomedical Image Segmentation

Ping Gong, Wenwen Yu, Qiuwen Sun, Ruohan Zhao, Junfeng Hu
2021 IEEE Access  
INDEX TERMS Biomedical image segmentation, cross-modality learning, unsupervised domain adaptation, category-centric prototype aligner.  ...  To alleviate this problem, we present a novel unsupervised domain adaptation network, for generalizing models learned from the labeled source domain to the unlabeled target domain for cross-modality biomedical  ...  These works are not used for the field of unsupervised domain adaptation for cross-modal biomedical image segmentation.  ... 
doi:10.1109/access.2021.3063634 fatcat:vkyhta5eyjc5facjxfrdbbpwte

Unsupervised Wasserstein Distance Guided Domain Adaptation for 3D Multi-Domain Liver Segmentation [article]

Chenyu You, Junlin Yang, Julius Chapiro, James S. Duncan
2020 arXiv   pre-print
Unsupervised domain adaptation aims to improve network performance when applying robust models trained on medical images from source domains to a new target domain.  ...  Experiments demonstrate that our method outperforms the state-of-the-art on the multi-modality liver segmentation task.  ...  In this paper, we present a novel unsupervised cross-modality domain adaptation method for medical image segmentation.  ... 
arXiv:2009.02831v1 fatcat:wpbw6uci6jds3iihkgynffmj4q

Dual-Teacher: Integrating Intra-domain and Inter-domain Teachers for Annotation-efficient Cardiac Segmentation [article]

Kang Li, Shujun Wang, Lequan Yu, Pheng-Ann Heng
2020 arXiv   pre-print
In this paper, we aim to investigate the feasibility of simultaneously leveraging abundant unlabeled data and well-established cross-modality data for annotation-efficient medical image segmentation.  ...  ,semi-supervised learning further exploring plentiful unlabeled data, domain adaptation including multi-modality learning and unsupervised domain adaptation resorting to the prior knowledge from additional  ...  Conclusion We present a novel annotation-efficient semi-supervised domain adaptation framework for multi-modality cardiac segmentation.  ... 
arXiv:2007.06279v1 fatcat:rtungnerpvhs5bav2tkymvvdsq

Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation [article]

Kelei He, Wen Ji, Tao Zhou, Zhuoyuan Li, Jing Huo, Xin Zhang, Yang Gao, Dinggang Shen, Bing Zhang, Junfeng Zhang
2021 arXiv   pre-print
Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor using the intermediate data distributions generated for the two domains, which includes an image-to-image  ...  To overcome this, unsupervised domain adaptation (UDA) methods provide effective solutions to alleviate the domain shift between labeled source data and unlabeled target data.  ...  CONCLUSION In this paper, we have proposed an unsupervised attention domain adaptation method for cross-modality brain tumor segmentation.  ... 
arXiv:2105.07715v1 fatcat:yo7hv3xwwncwhohp2j3kxncrqy

Dispensed Transformer Network for Unsupervised Domain Adaptation [article]

Yunxiang Li, Jingxiong Li, Ruilong Dan, Shuai Wang, Kai Jin, Guodong Zeng, Jun Wang, Xiangji Pan, Qianni Zhang, Huiyu Zhou, Qun Jin, Li Wang (+1 others)
2021 arXiv   pre-print
degrade system performance over cross-site or cross-modality datasets.  ...  However, it is costly to perform data annotation that provides ground truth labels for training the supervised algorithms, and the high variance of data that comes from different domains tends to severely  ...  CONCLUSION In this paper, we have presented a novel unsupervised domain adaptation method for the segmentation of crosssite and cross-modality datasets.  ... 
arXiv:2110.14944v1 fatcat:khwdtqdxanftnka64q563ibl74

Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation [article]

Lu Zhang, Siqi Zhang, Xu Yang, Zhiyong Liu
2022 arXiv   pre-print
The proposed method can be efficiently conducted with test-time images, without requiring annotations or revisiting the large-scale synthetic training data.  ...  Moreover, we design a cross-modality knowledge distillation module to encourage the information transfer during test time.  ...  Unsupervised Domain Adaptation Our work is also related to unsupervised domain adaptation (UDA) since we aim to mitigate the domain shift between the synthetic and realistic data in UOIS.  ... 
arXiv:2204.09847v1 fatcat:wsskwn6ypfaczd4beoamni3sjq

Cross Modality Microscopy Segmentation via Adversarial Adaptation [chapter]

Yue Guo, Qian Wang, Oleh Krupa, Jason Stein, Guorong Wu, Kira Bradford, Ashok Krishnamurthy
2019 Lecture Notes in Computer Science  
In this paper, we demonstrate an adversarial adaptation method to transfer deep network knowledge for microscopy segmentation from one imaging modality (e.g., confocal) to a new imaging modality (e.g.,  ...  Promising segmentation results show that the proposed transfer learning approach is an effective way to rapidly develop segmentation solutions for new imaging methods.  ...  First, we present an unsupervised solution for cross-modality microscopy segmentation, inspired by the adversarial adaptation method [17] .  ... 
doi:10.1007/978-3-030-17935-9_42 pmid:32154516 pmcid:PMC7062366 fatcat:bmdankxwvjeyhgl2oxjdebhrty

Scribble-based Domain Adaptation via Co-segmentation [article]

Reuben Dorent, Samuel Joutard, Jonathan Shapey, Sotirios Bisdas, Neil Kitchen, Robert Bradford, Shakeel Saeed, Marc Modat, Sebastien Ourselin, Tom Vercauteren
2020 arXiv   pre-print
To be able to generalise from one domain (e.g. one imaging modality) to another, domain adaptation has to be performed.  ...  This paper introduces a new formulation of domain adaptation based on structured learning and co-segmentation. Our method is easy to train, thanks to the introduction of a regularised loss.  ...  Fourthly, we evaluate our framework on a challenging problem, unpaired cross-modality domain adaptation.  ... 
arXiv:2007.03632v2 fatcat:4tm2qqlp45ckdlodc2jznjvary

CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation [article]

Reuben Dorent, Aaron Kujawa, Marina Ivory, Spyridon Bakas, Nicola Rieke, Samuel Joutard, Ben Glocker, Jorge Cardoso, Marc Modat, Kayhan Batmanghelich, Arseniy Belkov, Maria Baldeon Calisto (+28 others)
2022 arXiv   pre-print
CrossMoDA is the first large and multi-class benchmark for unsupervised cross-modality DA.  ...  To tackle these limitations, the Cross-Modality Domain Adaptation (crossMoDA) challenge was organised in conjunction with the 24th International Conference on Medical Image Computing and Computer Assisted  ...  Cross-MoDA is the first large and multi-class benchmark for unsupervised cross-modality Domain Adaptation.  ... 
arXiv:2201.02831v2 fatcat:qdd3rj62czdmxjwinmif7mkay4

Leveraging Motion Priors in Videos for Improving Human Segmentation [article]

Yu-Ting Chen, Wen-Yen Chang, Hai-Lun Lu, Tingfan Wu, Min Sun
2018 arXiv   pre-print
approach with domain adaptation approaches.  ...  Recently, a few domain adaptation and active learning approaches have been proposed to mitigate the performance drop.  ...  To demonstrate severe domain shift, we evaluate our method mainly on cross-modality (RGB to IR) domain adaptation for human segmentation.  ... 
arXiv:1807.11436v1 fatcat:jdiwvoqas5hkhohburdpw2wegu

Source-Relaxed Domain Adaptation for Image Segmentation [article]

Mathilde Bateson, Hoel Kervadec, Jose Dolz, Herve Lombaert, Ismail Ben Ayed
2020 arXiv   pre-print
Domain adaptation (DA) has drawn high interests for its capacity to adapt a model trained on labeled source data to perform well on unlabeled or weakly labeled target data from a different domain.  ...  We show the effectiveness of our prior-aware entropy minimization in adapting spine segmentation across different MRI modalities.  ...  for multi-modal magnetic resonance images.  ... 
arXiv:2005.03697v1 fatcat:37fikv6cgbc3ljdsfxstg27roq

Student Become Decathlon Master in Retinal Vessel Segmentation via Dual-teacher Multi-target Domain Adaptation [article]

Linkai Peng, Li Lin, Pujin Cheng, Huaqing He, Xiaoying Tang
2022 arXiv   pre-print
In this paper, we propose RVms, a novel unsupervised multi-target domain adaptation approach to segment retinal vessels (RVs) from multimodal and multicenter retinal images.  ...  Unsupervised domain adaptation has been proposed recently to tackle the so-called domain shift between training data and test data with different distributions.  ...  unsupervised multi-target domain adaptation in retinal vessel segmentation.  ... 
arXiv:2203.03631v2 fatcat:h4mzajxn75a27i65ybe6qjj4py
« Previous Showing results 1 — 15 out of 5,496 results