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.
Filters
A Strong Baseline for Domain Adaptation and Generalization in Medical Imaging
[article]
2019
arXiv
pre-print
Preserved Fulltext
This work provides a strong baseline for the problem of multi-source multi-target domain adaptation and generalization in medical imaging. ...
Using a diverse collection of ten chest X-ray datasets, we empirically demonstrate the benefits of training medical imaging deep learning models on varied patient populations for generalization to out-of-sample ...
In this preliminary work, we a simple solution suggested which quantitatively shows its promise as a strong baseline for better generalization. 2019) also discussed a similar issue of coping with data ...
arXiv:1904.01638v1
fatcat:anu6xvjtyjcgtp67jjmgdr7zgu
Edge-preserving Domain Adaptation for semantic segmentation of Medical Images
[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.
Unsupervised domain adaptation is proposed to adapt a model to new modalities using solely labeled source data and unlabeled target domain data. ...
Domain Adaptation is a technique to address the lack of massive amounts of labeled data in unseen environments. ...
CONCLUSIONS In this paper, we demonstrated a novel Edge-preserving Domain Adaptation for semantic segmentation of medical images. ...
arXiv:2111.09847v1
fatcat:67kiqjsajzgh7dxvkdbl4kfwge
Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionary
[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.
We present a novel approach to address this problem in medical image segmentation, which extracts and integrates the semantic shape prior information of segmentation that are invariant across domains and ...
However, such strong assumption may not always hold in practice, especially in medical field where the data sharing is highly concerned and sometimes prohibitive due to privacy issue. ...
Based on our experiments, such adaptation strategy only requires in average 56ms to process a 2D medical image and 0.91s for a medical volume data, hence can be performed efficiently. ...
arXiv:2206.14467v1
fatcat:zymtqn46frdpvavduqzi2xpsgm
Robust and Efficient Medical Imaging with Self-Supervision
[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
More importantly, our strategy leads to strong data-efficient generalization of medical imaging AI, matching strong supervised baselines using between 1% to 33% of retraining data across tasks. ...
REMEDIS exhibits significantly improved in-distribution performance with up to 11.5% relative improvement in diagnostic accuracy over a strong supervised baseline. ...
for Artificial Intelligence in Medicine and Imaging, MIT Laboratory for Computational Physiology and PhysioNet, NIH Clinical Center. ...
arXiv:2205.09723v2
fatcat:u5cthmwpdzckbdjm4eukrcddka
Mitigating domain shift in AI-based tuberculosis screening with unsupervised domain adaptation
[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.
We show that without domain adaptation, ResNet-50 has difficulty in generalizing between imaging distributions from a number of public Tuberculosis screening datasets with imagery from geographically distributed ...
In the context of medical imaging, this could lead to unintended biases such as the inability to generalize from one patient population to another. ...
ACKNOWLEDGMENT This work was supported in part by the NSF Center for Advanced Real-time Analytics Grant 1747724 and in part by Google Foundation. ...
arXiv:2111.04893v1
fatcat:3yknzikfmnaahgo5hr3wz6kyn4
Single-Domain Generalization in Medical Image Segmentation via Test-Time Adaptation from Shape Dictionary
2022
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
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.
We present a novel approach to address this problem in medical image segmentation, which extracts and integrates the semantic shape prior information of segmentation that are invariant across domains and ...
However, such strong assumption may not always hold in practice, especially in medical field where the data sharing is highly concerned and sometimes prohibitive due to privacy issue. ...
Based on our experiments, such adaptation strategy only requires in average 56ms to process a 2D medical image and 0.91s for a medical volume data, hence can be performed efficiently. ...
doi:10.1609/aaai.v36i2.20068
fatcat:667yb2jbkjdlvh652o7uniyap4
FixMatchSeg: Fixing FixMatch for Semi-Supervised Semantic Segmentation
[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
Supervised deep learning methods for semantic medical image segmentation are getting increasingly popular in the past few years.However, in resource constrained settings, getting large number of annotated ...
When there are few labels, we show that FixMatchSeg performs on par with strong supervised baselines. ...
Acknowledgment This research was supported in part through computational resources provided by the Supercomputer Center Kathmandu University, which was established with equipment donated by CERN. ...
arXiv:2208.00400v2
fatcat:7yqt7cg3s5bc3ml43yw72t7wdu
Online Reflective Learning for Robust Medical Image Segmentation
[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.
RefSeg runs in the testing phase and is general for segmentation models. ...
Extensive validation on three medical image segmentation tasks with a public cardiac MR dataset and two in-house large ultrasound datasets show that our RefSeg remarkably improves model robustness and ...
Though UDA obtains promising performance on cross-domain medical images and does not require annotations of target domains, obtaining adequate amount of target images in advance can be tough for clinical ...
arXiv:2207.00476v1
fatcat:nv6kyzwbufghbh4tshuoyrbite
Unsupervised domain adaptation for medical imaging segmentation with self-ensembling
[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.
Other Versions
Those models, however, when trained to reduce the empirical risk on a single domain, fail to generalize when applied to other domains, a very common scenario in medical imaging due to the variability of ...
In this work, we extend the method of unsupervised domain adaptation using self-ensembling for the semantic segmentation task and explore multiple facets of the method on a small and realistic publicly-available ...
Acknowledgments We are very thankful to Ryan Topfer for the sensible review and time dedicated to improve this article. ...
arXiv:1811.06042v2
fatcat:h5o2alpl4zaddmbezyzdi4pzy4
Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation
[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.
driving, medical imaging, etc.). ...
In this paper, we investigate open compound domain adaptation (OCDA), which deals with mixed and novel situations at the same time, for semantic segmentation. ...
[24] proposed a strong OCDA baseline for semantic segmentation. ...
arXiv:2110.04111v1
fatcat:udbcpkspyngvlasaywt5xzczpi
Mitigating domain shift in AI-based TB screening with unsupervised domain adaptation
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
We show that without domain adaptation, ResNet-50 has difficulty in generalizing between imaging distributions from a number of public TB screening datasets with imagery from geographically distributed ...
In the context of medical imaging, this could lead to unintended biases such as the inability to generalize from one patient population to another. ...
At UMBC, he was involved with the Vision and Image Processing Algorithms Research Group (VIPAR), where he worked on research related to the use of domain adaptation techniques to mitigate potential biases ...
doi:10.1109/access.2022.3168680
fatcat:v7sydft4rfavneyp3jf5xgruby
Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation
2020
Neural Information Processing 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 2021; you can also visit the original URL.
The file type is application/pdf.
driving, medical imaging, etc.). ...
In this paper, we investigate open compound domain adaptation (OCDA), which deals with mixed and novel situations at the same time, for semantic segmentation. ...
Recently, Liu et.al. [23] proposed a strong OCDA baseline for semantic segmentation. ...
dblp:conf/nips/ParkWSK20
fatcat:6ms5scfdpnfphnjdflgjqm2rxy
Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room
[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
Second, to address the domain shift and the lack of annotations, we propose a novel unsupervised domain adaptation method, called AdaptOR, to adapt a model from an in-the-wild labeled source domain to ...
on high- and low-resolution OR images in a self-training framework. ...
KM-ORPose is a strong baseline as it uses a complex multistage teacher model to generate accurate pseudo labels for the training. ...
arXiv:2108.11801v4
fatcat:4fxsoswfpvfejbcqmzvkdorpky
Improving Robustness of Deep Learning Based Knee MRI Segmentation: Mixup and Adversarial Domain Adaptation
[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.
Other Versions
We assessed the robustness of automatic segmentation by comparing mixup and UDA approaches to a strong baseline method at different OA severity stages and, additionally, in relation to anatomical locations ...
In this study, we investigated two modern regularization techniques -- mixup and adversarial unsupervised domain adaptation (UDA) -- to improve the robustness of DL-based knee cartilage segmentation to ...
, a branch of the Department of Health and Human Services, and conducted by the OAI Study Investigators. ...
arXiv:1908.04126v3
fatcat:5mo2m6r2iza5pcunx3kquwgvsy
PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training
[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 work, we present a novel framework for unsupervised domain adaptation based on the notion of target-domain consistency training. ...
Unsupervised domain adaptation is a promising technique for semantic segmentation and other computer vision tasks for which large-scale data annotation is costly and time-consuming. ...
Data labeling for semantic segmentation is notoriously laborious and expensive, especially in domains where experts are required (e.g. medical image segmentation). ...
arXiv:2105.08128v1
fatcat:ljgltkzxxjcivci24jjuokbw5u
« Previous
Showing results 1 — 15 out of 47,494 results