Filters








144 Hits in 5.5 sec

Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations [article]

Chen Qin, Bibo Shi, Rui Liao, Tommaso Mansi, Daniel Rueckert, Ali Kamen
2019 arXiv   pre-print
We propose a fully unsupervised multi-modal deformable image registration method (UMDIR), which does not require any ground truth deformation fields or any aligned multi-modal image pairs during training  ...  In this paper, we propose an unsupervised learning approach to reduce the multi-modal registration problem to a mono-modal one through image disentangling.  ...  (a) Multi-modal image registration via disentangled representations (Section 2.2). x and y are warped images from x and y.  ... 
arXiv:1903.09331v1 fatcat:qusif46r2ba7tnf3ykffmk34wy

Bayesian intrinsic groupwise registration via explicit hierarchical disentanglement [article]

Xin Wang, Xinzhe Luo, Xiahai Zhuang
2022 arXiv   pre-print
Here, the imaging process of multimodal medical images, including shape transition and appearance variation, is characterized by a disentangled variational auto-encoder.  ...  To this end, we propose a novel variational posterior and network architecture that facilitate joint learning of the common structural representation and the desired spatial correspondences.  ...  Except for z l , the channel number below each feature is specific to one modality. of submodules: 1) an encoder that extracts modality-invariant structural codes, 2) multi-level registration (Reg) modules  ... 
arXiv:2206.02377v1 fatcat:pd4nrseqqvfxxp2expntb6agmm

Unsupervised Multi-Modality Registration Network based on Spatially Encoded Gradient Information [article]

Wangbin Ding, Lei Li, Xiahai Zhuang, Liqin Huang
2021 arXiv   pre-print
In this work, we propose a multi-modality registration network (MMRegNet), which can perform registration between multi-modality images.  ...  Multi-modality medical images can provide relevant or complementary information for a target (organ, tumor or tissue).  ...  [16] disentangled a shape representation from multi-modality images via GAN, then a convenient mono-modality similarity metric could be applied on the shape representation for registration network training  ... 
arXiv:2105.07392v3 fatcat:cvujd7pknrewbntcs37njvdzhi

Unsupervised Multi-Modal Medical Image Registration via Discriminator-Free Image-to-Image Translation [article]

Zekang Chen, Jia Wei, Rui Li
2022 arXiv   pre-print
Multi-modal image registration is essential for the accurate alignment of these multi-modal images.  ...  In this paper, we propose a novel translation-based unsupervised deformable image registration approach to convert the multi-modal registration problem to a mono-modal one.  ...  In this work, we propose a novel translation-based unsupervised registration approach for aligning multi-modal images.  ... 
arXiv:2204.13656v1 fatcat:ukegvxqypzae5l4nepagexjn2u

Disentangle, align and fuse for multimodal and semi-supervised image segmentation [article]

Agisilaos Chartsias, Giorgos Papanastasiou, Chengjia Wang, Scott Semple, David E. Newby, Rohan Dharmakumar, Sotirios A. Tsaftaris
2020 arXiv   pre-print
) or no (unsupervised) annotations are available for this specific modality.  ...  Taking advantage of the common information shared between modalities (an organ's anatomy) is beneficial for multi-modality processing and learning.  ...  In medical imaging, disentangled representations have been used for semi-supervised cardiac segmentation [4, 5] , multi-task learning [5, 29] , lung nodule synthesis [24] , and multimodal registration  ... 
arXiv:1911.04417v4 fatcat:qxlay6fzz5fdlcpta2epygydf4

Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation [article]

Moab Arar, Yiftach Ginger, Dov Danon, Ilya Leizerson, Amit Bermano, Daniel Cohen-Or
2020 arXiv   pre-print
Compared to state-of-the-art multi-modal methods our presented method is unsupervised, requiring no pairs of aligned modalities for training, and can be adapted to any pair of modalities.  ...  Most multi-modal registration methods struggle computing the spatial correspondence between the images using prevalent cross-modality similarity measures.  ...  In this paper, we present an unsupervised method for multi-modal registration.  ... 
arXiv:2003.08073v1 fatcat:6qmuzqdttnezhm7sf3y2ro3iim

Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation

Moab Arar, Yiftach Ginger, Dov Danon, Amit H. Bermano, Daniel Cohen-Or
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Compared to state-of-the-art multi-modal methods our presented method is unsupervised, requiring no pairs of aligned modalities for training, and can be adapted to any pair of modalities.  ...  Most multi-modal registration methods struggle computing the spatial correspondence between the images using prevalent cross-modality similarity measures.  ...  In this paper, we present an unsupervised method for multi-modal registration.  ... 
doi:10.1109/cvpr42600.2020.01342 dblp:conf/cvpr/ArarGDBC20 fatcat:o6e5txywjzfrtmmhf3ik6m2sca

Table of contents

2021 IEEE Transactions on Medical Imaging  
Wu 2575 A Coarse-to-Fine Deformable Transformation Framework for Unsupervised Multi-Contrast MR Image Registration With Dual Consistency Constraint ...................................................  ...  Lu 2589 Noise-Powered Disentangled Representation for Unsupervised Speckle Reduction of Optical Coherence Tomography Images ............... Y. Huang, W. Xia, Z. Lu, Y. Liu, H. Chen, J. Zhou, L.  ... 
doi:10.1109/tmi.2021.3112022 fatcat:kcyeb3vh3zdafc746oq44zcjcu

Front Matter: Volume 12032

Ivana Išgum, Olivier Colliot
2022 Medical Imaging 2022: Image Processing  
Contents of non-linear gradient fields on diffusion MRI tensor estimation [12032-1] 04 Multi-scale sparse representation-based shadow inpainting for retinal OCT images [12032-2] 05 Measuring strain in  ...  image segmentation [12032-30] 0T Effective hyperparameter optimization with proxy data for multi-organ segmentation [12032-31] 0U Spatial label smoothing via aleatoric uncertainty for bleeding region  ... 
doi:10.1117/12.2638192 fatcat:ikfgnjefaba2tpiamxoftyi6sa

Learning Disentangled Representations in the Imaging Domain [article]

Xiao Liu, Pedro Sanchez, Spyridon Thermos, Alison Q. O'Neil, Sotirios A. Tsaftaris
2022 arXiv   pre-print
In this tutorial paper, we motivate the need for disentangled representations, revisit key concepts, and describe practical building blocks and criteria for learning such representations.  ...  Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision.  ...  We thank the participants of the DREAM tutorials for feedback.  ... 
arXiv:2108.12043v5 fatcat:cbpmp6pbajhjvjzovulswuj2wy

Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired images [article]

Adrià Casamitjana, Matteo Mancini, Juan Eugenio Iglesias
2021 arXiv   pre-print
We introduce a registration loss for weakly supervised image translation between domains that does not require perfectly aligned training data.  ...  Nonlinear inter-modality registration is often challenging due to the lack of objective functions that are good proxies for alignment.  ...  constraint; and (iii) we combine (i) and (ii) into an unsupervised SbR framework for inter-modality registration that does not require multiple encoders / decoders and therefore has low GPU memory requirements  ... 
arXiv:2107.14449v2 fatcat:hfrh3itv2fcbfgaycmwa22ensu

Image-to-Image Translation: Methods and Applications [article]

Yingxue Pang, Jianxin Lin, Tao Qin, Zhibo Chen
2021 arXiv   pre-print
Image-to-image translation (I2I) aims to transfer images from a source domain to a target domain while preserving the content representations.  ...  I2I has drawn increasing attention and made tremendous progress in recent years because of its wide range of applications in many computer vision and image processing problems, such as image synthesis,  ...  In addition, a large variety of multi-domain UI2I methods with a single-modal output have been proposed to obtain image representations in an unsupervised way.  ... 
arXiv:2101.08629v2 fatcat:i6pywjwnvnhp3i7cmgza2slnle

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 199-213 A Multi-Domain and Multi-Modal Representation Disentangler for Cross-Domain Image Manipulation and Classification.  ...  Li, J., +, TIP 2020 5817-5831 A Multi-Domain and Multi-Modal Representation Disentangler for Cross-Domain Image Manipulation and Classification.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Cross-Modality Multi-Atlas Segmentation Using Deep Neural Networks [article]

Wangbin Ding, Lei Li, Xiahai Zhuang, Liqin Huang
2020 arXiv   pre-print
This work presents a new MAS framework for cross-modality images, where both image registration and label fusion are achieved by DNNs.  ...  Both image registration and label fusion in the multi-atlas segmentation (MAS) rely on the intensity similarity between target and atlas images.  ...  Qin et al. designed an unsupervised registration network based on disentangled shape representations, and then converted the multi-modality registration into a mono-modality problem in the latent shape  ... 
arXiv:2008.08946v1 fatcat:taj5thg72ffgvfchyequzxjuke

Deep Learning Based Registration of Serial Whole-slide Histopathology Images in Different Stains [article]

Mousumi Roy, Fusheng Wang, George Teodoro, Ritu Aneja, Jun Kong, other paper in another context
2022 bioRxiv   pre-print
The synthetic IHC images and the real IHC images are then registered through a Fully Convolutional Network with multi-scale based deformable vector fields and a joint loss optimization for enhancing image  ...  We propose a novel translation based registration network CycGANReg-Net using deep learning for serial WSI images in different stains, which requires no prior deformation field information for deep model  ...  In another study, a mono-modal image registration with CycleGAN-produced synthetic images presents a comparable performance to the multi-modal deformable registration with paired image data of thoracic  ... 
doi:10.1101/2022.05.31.494254 fatcat:2frvqbo7ffaevjdjv46u55q2tm
« Previous Showing results 1 — 15 out of 144 results