☆ 4.7 Article

Causality-Inspired Single-Source Domain Generalization for Medical Image Segmentation

IEEE TRANSACTIONS ON MEDICAL IMAGING (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

Test-time adaptable neural networks for robust medical image segmentation

Neerav Karani et al.

Summary: In this study, a method to address the mismatch between training and test images in medical image segmentation is proposed. The segmentation network consists of a shallow image normalization CNN and a deep CNN, with a denoising autoencoder used to model an implicit prior. Experimental results demonstrate the performance improvement achieved by test-time adaptation.

MEDICAL IMAGE ANALYSIS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

CHAOS Challenge- combined (CT-MR) healthy abdominal organ segmentation

A. Emre Kavur et al.

Summary: Abdominal organ segmentation has long been a comprehensive research field, with recent developments in deep learning introducing new state-of-the-art segmentation systems. However, the effects of DL model properties and parameters on performance are still difficult to interpret, and multi-tasking DL models often perform worse compared to organ-specific ones.

MEDICAL IMAGE ANALYSIS (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Learning to Diversify for Single Domain Generalization

Zijian Wang et al.

Summary: This paper focuses on Single Domain Generalization (Single-DG), proposing a style-complement module to enhance model generalization by synthesizing images from distributions complementary to the source domain. The proposed method optimizes mutual information between generated and source samples, achieving superior performance compared to state-of-the-art single-DG methods.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Engineering, Biomedical

GENERALIZE ULTRASOUND IMAGE SEGMENTATION VIA INSTANT AND PLUG & PLAY STYLE TRANSFER

Zhendong Liu et al.

Summary: This paper proposed a robust segmentation method for unknown appearance shifts by embedding hierarchical style transfer units and adopting Dynamic Instance Normalization, which can achieve precise and dynamic style transfer in a fast and lightweight manner. Extensive experiments on a large dataset from three vendors demonstrate that the proposed method enhances the robustness of deep segmentation models.

2021 IEEE 18TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Limitations of Post-Hoc Feature Alignment for Robustness

Collin Burns et al.

Summary: Feature alignment is a method for improving robustness to distribution shift by matching feature activation distributions between training and test data. However, research has found that this approach is only significantly helpful in certain specific distribution shift scenarios, and can even degrade performance in other cases.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation

Chen Chen et al.

Summary: This paper introduces a cooperative framework and a latent space augmentation method to improve the generalization and robustness of image segmentation models. By training on a limited dataset, it can enhance segmentation performance between different sites and increase robustness against various imaging artifacts.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT III (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Domain Composition and Attention for Unseen-Domain Generalizable Medical Image Segmentation

Ran Gu et al.

Summary: The study introduces a Domain Composition and Attention-based network (DCA-Net) to address domain generalization in medical image analysis. By using domain composition method, domain preceptor, and domain attention module, the model achieves the ability to generalize across different domains effectively.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT III (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Semi-supervised Meta-learning with Disentanglement for Domain-Generalised Medical Image Segmentation

Xiao Liu et al.

Summary: The study introduces a novel semi-supervised meta-learning framework that disentangles representations related to domain shifts, allowing unlabeled data to approximate true domain shifts better for meta-learning. This approach achieves improved generalization performance on various segmentation tasks and outperforms state-of-the-art methods on two public benchmarks.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT II (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation

Ling Zhang et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2020)

Add to Collection

Article Multidisciplinary Sciences

Causality matters in medical imaging

Daniel C. Castro et al.

NATURE COMMUNICATIONS (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Shortcut learning in deep neural networks

Robert Geirhos et al.

NATURE MACHINE INTELLIGENCE (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning

Takeru Miyato et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Data Efficient Unsupervised Domain Adaptation For Cross-modality Image Segmentation

Cheng Ouyang et al.

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT II (2019)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Multimodal MR Synthesis via Modality-Invariant Latent Representation

Agisilaos Chartsias et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2018)

Add to Collection

Article Medicine, General & Internal

Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study

John R. Zech et al.

PLOS MEDICINE (2018)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Unsupervised Domain Adaptation in Brain Lesion Segmentation with Adversarial Networks

Konstantinos Kamnitsas et al.

INFORMATION PROCESSING IN MEDICAL IMAGING (IPMI 2017) (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

Xun Huang et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?

Raja Giryes et al.

IEEE TRANSACTIONS ON SIGNAL PROCESSING (2016)

Add to Collection

Review Biology

Computer-Aided Detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: A review

Guillaume Lemaitre et al.

COMPUTERS IN BIOLOGY AND MEDICINE (2015)

Add to Collection

Article Computer Science, Artificial Intelligence

Evaluation of prostate segmentation algorithms for MRI: The PROMISE12 challenge

Geert Litjens et al.

MEDICAL IMAGE ANALYSIS (2014)

Add to Collection

Article Computer Science, Artificial Intelligence

A theory of learning from different domains

Shai Ben-David et al.

MACHINE LEARNING (2010)

Add to Collection

Article Computer Science, Artificial Intelligence

Efficient graph-based image segmentation

PF Felzenszwalb et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2004)

Add to Collection

© Peeref 2019-2024. All rights reserved.