15,703 Hits in 4.2 sec

Domain Adaptation for Medical Image Segmentation: A Meta-Learning Method

Penghao Zhang, Jiayue Li, Yining Wang, Judong Pan
2021 Journal of Imaging  
Inspired by these two categories of approaches, we propose an optimization-based meta-learning method for segmentation tasks.  ...  from in medical image segmentation.  ...  Data Availability Statement: The proposed algorithm was tested on the Medical Segmentation Decathlon, see (accessed on 8 February 2020).  ... 
doi:10.3390/jimaging7020031 pmid:34460630 fatcat:pigepk5mm5gtvcnyttpvtapdha

Domain and Content Adaptive Convolution for Domain Generalization in Medical Image Segmentation [article]

Shishuai Hu, Zehui Liao, Jianpeng Zhang, Yong Xia
2021 arXiv   pre-print
In this paper, we propose a multi-source domain generalization model, namely domain and content adaptive convolution (DCAC), for medical image segmentation.  ...  The domain gap caused mainly by variable medical image quality renders a major obstacle on the path between training a segmentation model in the lab and applying the trained model to unseen clinical data  ...  Related Work DG in Medical Image Segmentation DG methods designed for medical image segmentation can be roughly categorized into augmentation-based, meta-learningbased, and domain-invariant feature learning  ... 
arXiv:2109.05676v1 fatcat:tqufa3orfbdxtjeo7762ij6kyy

Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns [article]

Hongwei Li, Timo Loehr, Anjany Sekuboyina, Jianguo Zhang, Benedikt Wiestler, Bjoern Menze
2020 arXiv   pre-print
In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen  ...  In this paper, we propose an unsupervised domain adaptation framework for boosting image segmentation performance across multiple domains without using any manual annotations from the new target domains  ...  RELATED WORK Our work is related to unsupervised domain adaptation, cross-domain image segmentation and continual learning. Unsupervised domain adaptation.  ... 
arXiv:2001.09313v3 fatcat:hyjylq4z6rdcxlkzoz4cmthn6i

A Review on Community Detection in Large Complex Networks from Conventional to Deep Learning Methods: A Call for the Use of Parallel Meta-Heuristic Algorithms

Mohammed Al-Andoli, Shing Chiang Tan, Wooi Ping Cheah, Sin Yin Tan
2021 IEEE Access  
Recently, in [80] , the authors developed a new learning method for CD in CNs.  ...  [98] also adapted GA to optimize deep CNNs for classification in multi-unmanned aerial vehicles. GA obtains the scenario states and path segments to train CNNs.  ... 
doi:10.1109/access.2021.3095335 fatcat:4zggvxofqvbcjbwylk7swc3c34

Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation [article]

Xiao Liu, Spyridon Thermos, Alison O'Neil, Sotirios A. Tsaftaris
2021 arXiv   pre-print
However, the current fully supervised meta-learning approaches are not scalable for medical image segmentation, where large effort is required to create pixel-wise annotations.  ...  Disentangling the representations and combining them to reconstruct the input image allows unlabeled data to be used to better approximate the true domain shifts for meta-learning.  ...  [20, 22] , where [20] extends [22] to medical image segmentation. 1 These approaches do not scale in medical image segmentation as pixel-wise annotation is time-consuming, laborious, and requires  ... 
arXiv:2106.13292v3 fatcat:pkmydr54ifd6tbssmtw7jepg4m

Learning to Segment Medical Images from Few-Shot Sparse Labels [article]

Pedro H. T. Gama, Hugo Oliveira, Jefersson A. dos Santos
2021 arXiv   pre-print
In this paper, we propose a novel approach for few-shot semantic segmentation with sparse labeled images.  ...  We investigate the effectiveness of our method, which is based on the Model-Agnostic Meta-Learning (MAML) algorithm, in the medical scenario, where the use of sparse labeling and few-shot can alleviate  ...  For instance, domain adaptation can be used to transfer knowledge from related medical imaging datasets to improve segmentation performance in unseen target tasks.  ... 
arXiv:2108.05476v2 fatcat:k25eyyqm7bgszfo4ihkszqkisq

Enhancing Pseudo Label Quality for Semi-Supervised Domain-Generalized Medical Image Segmentation [article]

Huifeng Yao, Xiaowei Hu, Xiaomeng Li
2022 arXiv   pre-print
This paper presents a novel confidence-aware cross pseudo supervision algorithm for semi-supervised domain generalized medical image segmentation.  ...  Generalizing the medical image segmentation algorithms to unseen domains is an important research topic for computer-aided diagnosis and surgery.  ...  Acknowledgments This work was supported by a research grant from Shenzhen Municipal Central Government Guides Local Science and Technology Development Special Funded Projects (2021Szvup139) and a research  ... 
arXiv:2201.08657v2 fatcat:cehwtd6imrad3es4a27huu6hny

Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation [article]

Neerav Karani, Ertunc Erdil, Krishna Chaitanya, Ender Konukoglu
2020 arXiv   pre-print
Now, at test time, we adapt the image normalization sub-network for each test image, guided by an implicit prior on the predicted segmentation labels.  ...  In medical image segmentation, this premise is violated when there is a mismatch between training and test images in terms of their acquisition details, such as the scanner model or the protocol.  ...  Clinical Research Priority Program Grant on Artificial Intelligence in Oncological Imaging Network from University of Zurich. We also thank NVIDIA corporation for their GPU donation.  ... 
arXiv:2004.04668v3 fatcat:lxh3hsoeifhffmx6pgwtrdwwkq

Few-Shot Microscopy Image Cell Segmentation [article]

Youssef Dawoud, Julia Hornauer, Gustavo Carneiro, Vasileios Belagiannis
2020 arXiv   pre-print
We pose this problem as meta-learning where the goal is to learn a generic and adaptable few-shot learning model from the available source domain data sets and cell segmentation tasks.  ...  each domain denotes not only different image appearance but also a different type of cell segmentation problem.  ...  G.C. acknowledges the support by the Alexander von Humboldt-Stiftung for the renewed research stay sponsorship.  ... 
arXiv:2007.01671v1 fatcat:p4ob756fgza6fhyergfgcidfjm

Diagnostic Performance of Generative Adversarial Network-Based Deep Learning Methods for Alzheimer's Disease: A Systematic Review and Meta-Analysis

Changxing Qu, Yinxi Zou, Yingqiao Ma, Qin Chen, Jiawei Luo, Huiyong Fan, Zhiyun Jia, Qiyong Gong, Taolin Chen
2022 Frontiers in Aging Neuroscience  
This study provided a systematic review on the application of the GAN-based deep learning method in the diagnosis of AD and conducted a meta-analysis to evaluate its diagnostic performance.  ...  For the AD vs. cognitively normal (CN) classification, the GAN-based deep learning method exhibited better performance than the non-GAN method, with significantly higher accuracy (OR 1.425, 95% CI: 1.150  ...  As one of the most important AI techniques, deep learning performs well in image processing for image detection, classification, and segmentation (Lee et al., 2017; Suzuki, 2017) .  ... 
doi:10.3389/fnagi.2022.841696 pmid:35527734 pmcid:PMC9068970 fatcat:lscirxiptjgnbcqwgrxdtm6dq4

Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation [article]

Shuhao Fu, Yongyi Lu, Yan Wang, Yuyin Zhou, Wei Shen, Elliot Fishman, Alan Yuille
2020 arXiv   pre-print
model to standardize medical images from different domain to a certain spatial resolution; 2) Adapting the spatial relationship for a test image by test-time jigsaw puzzle training.  ...  In this paper, we present a novel unsupervised domain adaptation (UDA) method, named Domain Adaptive Relational Reasoning (DARR), to generalize 3D multi-organ segmentation models to medical data collected  ...  Acknowledgement We especially Chen Wei for her valuable discussions and ideas. This work was supported by the Lustgarten Foundation for Pancreatic Cancer Research.  ... 
arXiv:2005.09120v2 fatcat:uaoaehddgffhlh3btpresyrb5y

MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting [article]

Yiren Jian, Chongyang Gao
2021 arXiv   pre-print
Training a deep neural model for semantic segmentation requires collecting a large amount of pixel-level labeled data.  ...  The experiments show that our method with only one single meta module can outperform a complicated combination of an adversarial feature alignment, a reconstruction loss, plus a hierarchical heuristic  ...  Conclusion In this paper, we propose MetaPix, a meta learning method for learning an adaptive weight map for source task in domain transfer learning of semantic segmentation.  ... 
arXiv:2110.01777v1 fatcat:pg66ldabcfcjnlrkhf7rbwt4wu

Causality-inspired Single-source Domain Generalization for Medical Image Segmentation [article]

Cheng Ouyang, Chen Chen, Surui Li, Zeju Li, Chen Qin, Wenjia Bai, Daniel Rueckert
2021 arXiv   pre-print
source domain, which is common in medical imaging applications.  ...  We tackle this problem in the context of cross-domain medical image segmentation. Under this scenario, domain shifts are mainly caused by different acquisition processes.  ...  ., “nnu-net: Self- Domain robustness has been a challenge for deep learning adapting framework for u-net-based medical image segmentation,” arXiv based medical image computing  ... 
arXiv:2111.12525v4 fatcat:e4ht2fhmijherf6jxo3fgmbgkm

Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains [article]

Quande Liu, Qi Dou, Pheng-Ann Heng
2020 arXiv   pre-print
Model generalization capacity at domain shift (e.g., various imaging protocols and scanners) is crucial for deep learning methods in real-world clinical deployment.  ...  We present a novel shape-aware meta-learning scheme to improve the model generalization in prostate MRI segmentation.  ...  We present a novel shape-aware meta-learning (SAML) scheme for domain generalization on medical image segmentation.  ... 
arXiv:2007.02035v1 fatcat:znalvflcqze27ishmhepojgufu

Meta-learning with implicit gradients in a few-shot setting for medical image segmentation [article]

Rabindra Khadga, Debesh Jha, Steven Hicks, Vajira Thambawita, Michael A. Riegler, Sharib Ali, Pål Halvorsen
2022 arXiv   pre-print
To this end, we propose to exploit an optimization-based implicit model agnostic meta-learning (iMAML) algorithm under few-shot settings for medical image segmentation.  ...  Therefore, a more general application of any trained model is quite limited for medical imaging for clinical practice.  ...  In the work proposed by Ouyang et al. (2020) , few-shot segmentation with a self-supervised method has been used to eliminate the need for having annotated medical images.  ... 
arXiv:2106.03223v2 fatcat:tl5tx5dr4batrfedsj4ou3arma
« Previous Showing results 1 — 15 out of 15,703 results