A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Multimodal Self-Supervised Learning for Medical Image Analysis
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
Our results also highlight the benefits of exploiting synthetic images for self-supervised pretraining. ...
In addition, we also propose to utilize cross-modal generation techniques for multimodal data augmentation used for training self-supervised tasks. ...
Self-supervision in the medical context. ...
arXiv:1912.05396v2
fatcat:klwchysg4ney3phlmlawyrzxvi
Learning the retinal anatomy from scarce annotated data using self-supervised multimodal reconstruction
2020
Applied Soft Computing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
For that purpose, a neural network is pre-trained using the self-supervised multimodal reconstruction of fluorescein angiography from retinography. ...
Deep learning is becoming the reference paradigm for approaching many computer vision problems. ...
A rich source of information that has still not been exploited for self-supervised transfer learning is the unlabelled multimodal data in medical imaging. ...
doi:10.1016/j.asoc.2020.106210
fatcat:7zr5xxza6rgald67fkcnve557y
Self-Supervised Multimodal Domino: in Search of Biomarkers for Alzheimer's Disease
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper, we unify recent work on multimodal self-supervised learning under a single framework. ...
This observation motivated the design of powerful multimodal self-supervised representation-learning algorithms. ...
., different MRI modalities [1] , [2] in medical imaging, LiDAR, and video for self-driving cars [3] , and confounder-influenced data [4] . ...
arXiv:2012.13623v4
fatcat:ndgnj5pakvgkfpoq55bvfz2zli
Self-supervised multimodal reconstruction of retinal images over paired datasets
2020
Expert systems with applications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This work proposes a novel self-supervised multimodal reconstruction task that takes advantage of this unlabeled multimodal data for learning about the domain without human supervision. ...
These results indicate that the proposed self-supervised task provides relevant cues for image analysis tasks in the same domain. ...
Proposed work The proposed self-supervised multimodal reconstruction paradigm naturally fits medical image applications, given the extensive use of multimodal visual data in many clinical specialties. ...
doi:10.1016/j.eswa.2020.113674
fatcat:2x7q6ag4xjf73oukbinjwhvvga
Tasting the cake: evaluating self-supervised generalization on out-of-distribution multimodal MRI data
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Self-supervised learning has enabled significant improvements on natural image benchmarks. However, there is less work in the medical imaging domain in this area. ...
Our results highlight the need for out-of-distribution generalization standards and benchmarks to adopt the self-supervised methods in the medical imaging community. ...
CONCLUSIONSSelf-supervised medical imaging models are only now beginning to be developed, and we hope that our analysis will facilitate robust and fair self-supervised models. ...
arXiv:2103.15914v3
fatcat:rre34oatsjhcjmpk2xw7ftjcua
Unsupervised MRI Super-Resolution Using Deep External Learning and Guided Residual Dense Network with Multimodal Image Priors
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
These techniques have also been applied to medical image super-resolution (SR). Compared with natural images, medical images have several unique characteristics. ...
Deep learning techniques have led to state-of-the-art single image super-resolution (SISR) with natural images. ...
The authors would like to thank Enago (www.enago.jp) for the English language review. ...
arXiv:2008.11921v2
fatcat:uls762ztunclbln3xa5xeelv2u
Learning Retinal Patterns from Multimodal Images
2018
Proceedings (MDPI)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
The self-supervised training of a reconstruction task between paired multimodal images can be used to learn about the image contents without using any label. ...
In this work, we propose the use of complementary medical image modalities as an alternative to reduce the required annotated data. ...
We train a neural network to predict the angiography from a retinography of the same patient and demonstrate that the network learns about relevant structures of the eye with this self-supervised training ...
doi:10.3390/proceedings2181195
fatcat:sv2ba5vq5vavplnl6s4ihwp2ou
MMBERT: Multimodal BERT Pretraining for Improved Medical VQA
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To overcome these limitations, we propose a solution inspired by self-supervised pretraining of Transformer-style architectures for NLP, Vision and Language tasks. ...
Our method involves learning richer medical image and text semantic representations using Masked Language Modeling (MLM) with image features as the pretext task on a large medical image+caption dataset ...
Since the annotations on medical images require the help of an expert, it is difficult to crowdsource and annotation cost is high. This motivates the usage of self-supervised pretraining methods. ...
arXiv:2104.01394v1
fatcat:nfgvcaftzjgslec2fuujidsm5e
Front Matter: Volume 12032
2022
Medical Imaging 2022: Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
2D KV/MV image [12032-124] 3K Size- [12032-105] 31 Bridging the domain gap for medical image segmentation with multimodal MIND features [12032-106] 32 Benefits of auxiliary information in deep learning-based ...
for deep learning segmentation in medical imaging [12032-25] 10 Unsupervised domain adaptation for segmentation with black-box source model [12032-26] 11 Do I know this? ...
doi:10.1117/12.2638192
fatcat:ikfgnjefaba2tpiamxoftyi6sa
Deep Learning in Medical Image Registration: A Survey
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Since the beginning of the recent deep learning renaissance, the medical imaging research community has developed deep learning based approaches and achieved the state-of-the-art in many applications, ...
The rapid adoption of deep learning for image registration applications over the past few years necessitates a comprehensive summary and outlook, which is the main scope of this survey. ...
Weakly-supervised convolutional neural networks for multimodal image registration. Medical image analysis, 49:1-13. 53. Ikeda, K., Ino, F., and Hagihara, K. (2014). ...
arXiv:1903.02026v1
fatcat:6ulnzrbj6rb55eydtkgygg5r6u
Medical Image Registration Using Deep Neural Networks: A Comprehensive Review
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, a comprehensive review on the state-of-the-art literature known as medical image registration using deep neural networks is presented. ...
to challenge with many medical applications, where the registration is not an exception. ...
Image Processing, and Ultrasound Systems for Assisted Diagnosis and Navigation 1 Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support Image Analysis for Moving ...
arXiv:2002.03401v1
fatcat:u4utrifr2rg3bf6x6fgohyfmpy
2020 Index IEEE Transactions on Artificial Intelligence Vol. 1
2020
IEEE Transactions on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
., +, TAI Oct.
2020 181-191
Image motion analysis
Self-Supervised Pose Adaptation for Cross-Domain Image Animation. ...
., +, TAI Aug. 2020 62-73 Self-Supervised Pose Adaptation for Cross-Domain Image Animation. ...
doi:10.1109/tai.2021.3089904
fatcat:53o6433ljne3lblvr5fuy66lou
Brain MR Multimodal Medical Image Registration Based on Image Segmentation and Symmetric Self-similarity
2020
KSII Transactions on Internet and Information Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
More particularly, we propose two novel symmetric self-similarity constraint operators to constrain the segmented medical images and convert each modal medical image into a unified modal for multimodal ...
In this paper, a multimodal medical image registration method based on image segmentation and symmetric self-similarity is proposed. ...
The unsupervised piece of self-supervised learning based on similarity measures is currently a research hotspot. ...
doi:10.3837/tiis.2020.03.014
fatcat:bvaxau4x6fbcxki2avgdncexsi
A Review of Self-supervised Learning Methods in the Field of Medical Image Analysis
2021
International Journal of Image Graphics and Signal Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
So, more and more researchers are trying to utilize SSL methods for medical image analysis, to meet the challenge of assembling large medical datasets. ...
review the application of self-supervised learning in the medical field. ...
Acknowledgment This research has been partially supported by China Scholarship Council (CSC), and Special thanks should go to my supervisor professor Sergii Stirenko, for his instructive advice and useful ...
doi:10.5815/ijigsp.2021.04.03
fatcat:ff7ybaplqncthgswf3zy7cbeza
Enhancing Retinal Blood Vessel Segmentation through Self-Supervised Pre-Training
2020
Proceedings (MDPI)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this work, we present a novel application of self-supervised multimodal pre-training to enhance the retinal vasculature segmentation. ...
Table 1 . 1 Best AUC-ROC and AUC-PR values of the different networks trained from scratch (FS) and using self-supervised multimodal pretraining (SSMP) for the STARE dataset. ...
This motivates the proposal of self-supervised multimodal pre-training (SSMP) to learn the relevant patterns from unlabeled data and reduce the required amount of annotated data [1] [2] [3] . ...
doi:10.3390/proceedings2020054044
fatcat:crkjipbjcfe33cmg6y3jcqzrmy
« Previous
Showing results 1 — 15 out of 6,497 results