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
Representation Disentanglement for Multi-task Learning with application to Fetal Ultrasound
[article]
2019
arXiv
pre-print
Preserved Fulltext
In this paper we propose a novel representation disentanglement method to extract semantically meaningful and generalizable features for different tasks within a multi-task learning framework. ...
We aim to use the disentangled representations to generalize the applicability of deep neural networks. ...
Contribution: In this paper, we propose a novel, end-to-end trainable representation disentanglement model that can learn distinct and generalizable features through a multi-task architecture with adversarial ...
arXiv:1908.07885v1
fatcat:qrrvtyht2rcqrkgplgjctdmaya
Mutual Information-based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging
[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 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2011.00739v1 fatcat:z3w5ydvzdzbf7ivqhoacg5y56q
We extensively evaluate the proposed method on fetal ultrasound datasets for two different image classification tasks where domain features are respectively defined by shadow artifacts and image acquisition ...
This problem occurs frequently in medical imaging applications when attempts are made to deploy and improve deep learning models across different image acquisition devices, across acquisition parameters ...
To use disentangled representations for identifying images with unseen entangled features in real applications, Meng et al. ...
arXiv:2011.00739v2
fatcat:zlk6gah6oveljkmtfrnc52godi
Learning Cross-domain Generalizable Features by Representation Disentanglement
[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.
We demonstrate our method on handwritten digits datasets and a fetal ultrasound dataset for image classification tasks. ...
To address this problem, we propose Mutual-Information-based Disentangled Neural Networks (MIDNet) to extract generalizable features that enable transferring knowledge to unseen categorical features in ...
To use disentangled representations for identifying images with unseen entangled features in real applications, Meng et al. ...
arXiv:2003.00321v1
fatcat:z27lkqt7fzh7tbafcethalp6c4
Learning Disentangled Representations in the Imaging Domain
[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 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2108.12043v4 fatcat:rckcevnvw5apdnslkr76a65ztuOther Versions
Disentangled representation learning has been proposed as an approach to learning general representations even in the absence of, or with limited, supervision. ...
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. ...
We thank the participants of the DREAM tutorials for feedback. ...
arXiv:2108.12043v5
fatcat:cbpmp6pbajhjvjzovulswuj2wy
Recent Advances in Variational Autoen-coders with Representation Learning for Biomedical Informatics: A Survey
2020
IEEE Access
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.
This has allowed for efficient extraction of relevant biomedical information from learned features for biological data sets, referred to as unsupervised feature representation learning. ...
We discuss challenges and future opportunities for biomedical research with respect to VAEs. ...
The goal of representation learning is to be useful for downstream tasks. ...
doi:10.1109/access.2020.3048309
fatcat:ka5k7nfia5c5ra4npsvuxp6h3q
A Survey of Cross-Modality Brain Image Synthesis
[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
A realistic solution is to explore either an unsupervised learning or a semi-supervised learning to synthesize the absent neuroimaging data. ...
In this paper, we tend to approach multi-modality brain image synthesis task from different perspectives, which include the level of supervision, the range of modality synthesis, and the synthesis-based ...
Ultrasound to MRI Ultrasound is a most common method to detect abnormalities in the fetal brain and growth restriction. ...
arXiv:2202.06997v2
fatcat:kqxte2xrcrcpjfkkhwrcxdjqsu
Transparency of Deep Neural Networks for Medical Image Analysis: A Review of Interpretability Methods
[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.
In this narrative review, we utilized systematic keyword searches and domain expertise to identify nine different types of interpretability methods that have been used for understanding deep learning models ...
Artificial Intelligence has emerged as a useful aid in numerous clinical applications for diagnosis and treatment decisions. ...
This method was validated for standard plane classification for fetal ultrasound imaging. ...
arXiv:2111.02398v1
fatcat:glrfdkbcqrbqto2nrl7dnlg3gq
Self-supervised learning methods and applications in medical imaging analysis: A survey
[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
Self-supervised learning is a recent training paradigm that enables learning robust representations without the need for human annotation which can be considered as an effective solution for the scarcity ...
This article reviews the state-of-the-art research directions in self-supervised learning approaches for image data with concentration on their applications in the field of medical imaging analysis. ...
Jiao et al. [2020] proposed temporal order correction and spatio-temporal transformation prediction pretext tasks to learn good representation from fetal ultrasound videos. ...
arXiv:2109.08685v2
fatcat:iu2zanqqrnaflawcxndb6xszgu
A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis
[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.
Deep-learning (DL) algorithms are becoming the standard for processing ultrasound (US) fetal images. ...
This paper ends with a critical summary of the current state of the art on DL algorithms for fetal US image analysis and a discussion on current challenges that have to be tackled by researchers working ...
With these questions in mind, we outlined a set of keywords for our survey, including: classification, detection, segmentation, fetal, ultrasound, deep learning combined together with terms related to ...
arXiv:2201.12260v1
fatcat:hewsv3i3vfbzjjt3sakunb2g2a
Deep Learning for Cardiac Image Segmentation: A Review
2020
Frontiers in Cardiovascular Medicine
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.
Deep learning has become the most widely used approach for cardiac image segmentation in recent years. ...
In addition, a summary of publicly available cardiac image datasets and code repositories are included to provide a base for encouraging reproducible research. ...
ACKNOWLEDGMENTS We would like to thank our colleagues: Karl Hahn, Qingjie Meng, James Batten, and Jonathan Passerat-Palmbach who provided the insight and expertise that greatly assisted the work, and also ...
doi:10.3389/fcvm.2020.00025
pmid:32195270
pmcid:PMC7066212
fatcat:iw7xpnltn5cgbn5ullq2ldy3nq
Single Independent Component Recovery and Applications
[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.
Our goal is to recover the hidden component. For this purpose, we propose an autoencoder equipped with a discriminator. ...
Latent variable discovery is a central problem in data analysis with a broad range of applications in applied science. ...
In a similar fashion to the ICA case, the task of learning of disentangled representations in the general case was proved to be non-identifiable [41] . ...
arXiv:2110.05887v1
fatcat:xsqczumbpvasdgafcuo55yhgwq
AI and Medical Imaging Informatics: Current Challenges and Future Directions
2020
IEEE journal of biomedical and health informatics
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 both radiology and digital pathology applications. ...
The clinical benefits of in-silico modelling advances linked with evolving 3D reconstruction and visualization applications are further documented. ...
Still, ultrasound remains one of the most used imaging techniques employed extensively for real-time cardiac and fetal imaging [11] . ...
doi:10.1109/jbhi.2020.2991043
pmid:32609615
pmcid:PMC8580417
fatcat:dcaefxwwqjfwla5asin34x2hxm
Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directions
2019
IEEE Access
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.
promising directions for the Medical Imaging Community to fully harness deep learning in the future. ...
This technology has recently attracted so much interest of the Medical Imaging Community that it led to a specialized conference in "Medical Imaging with Deep Learning" in the year 2018. ...
For automatic classification of ultrasound abdominal images, Xu et al. [269] proposed a multi-task learning framework based on CNN. ...
doi:10.1109/access.2019.2929365
fatcat:arimcbjaxrd3zcsjyzd7abjgd4
Going Deep in Medical Image Analysis: Concepts, Methods, Challenges and Future Directions
[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 2020; you can also visit the original URL.
The file type is application/pdf.
provide promising directions for the Medical Imaging community to fully harness Deep Learning in the future. ...
This technology has recently attracted so much interest of the Medical Imaging community that it led to a specialized conference in 'Medical Imaging with Deep Learning' in the year 2018. ...
For automatic classification of ultrasound abdominal images, Xu et al. [262] proposed a multi-task learning framework based on CNN. ...
arXiv:1902.05655v1
fatcat:mjplenjrprgavmy5ssniji4cam
Graph Convolutional Networks for Multi-modality Medical Imaging: Methods, Architectures, and Clinical Applications
[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
Yet daunting challenges remain for designing the important image-to-graph transformation for multi-modality medical imaging and gaining insights into model interpretation and enhanced clinical decision ...
To foster cross-disciplinary research, we present GCNs technical advancements, emerging medical applications, identify common challenges in the use of image-based GCNs and their extensions in model interpretation ...
Fundus images ultrasound Optic disc and cup images segmentation and fetal head segmentation Wu et al. ...
arXiv:2202.08916v3
fatcat:zskcqvgjpnb6vdklmyy5rozswq
« Previous
Showing results 1 — 15 out of 94 results