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

@article{Zhang2020GeneralizingDL,
  title={Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation},
  author={Ling Zhang and Xiaosong Wang and Dong Yang and Thomas Sanford and Stephanie A. Harmon and Baris Turkbey and Bradford J. Wood and Holger R. Roth and Andriy Myronenko and Daguang Xu and Ziyue Xu},
  journal={IEEE Transactions on Medical Imaging},
  year={2020},
  volume={39},
  pages={2531-2540}
}
Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, application of these models in clinically realistic environments can result in poor generalization and decreased accuracy, mainly due to the domain shift across different hospitals, scanner vendors, imaging protocols, and patient populations etc. Common transfer learning and domain adaptation techniques are proposed to address this bottleneck. However, these solutions require data (and… 
Causality-inspired Single-source Domain Generalization for Medical Image Segmentation
TLDR
This work investigates the single-source domain generalization problem: training a deep network that is robust to unseen domains, under the condition that training data is only available from one source domain, which is common in medical imaging applications.
Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains
TLDR
A novel shape-aware meta-learning scheme is presented to improve the model generalization in prostate MRI segmentation, and outperforms many state-of-the-art generalization methods consistently across all six settings of unseen domains.
Domain Generalizer: A Few-shot Meta Learning Framework for Domain Generalization in Medical Imaging
TLDR
The method learns a domain-agnostic feature representation to improve generalization of models to the unseen test distribution and employs few-shot learning, i.e. training the generalized model using very few examples from the unseen domain, to quickly adapt the model to new unseen data distribution.
Semi-supervised Meta-learning with Disentanglement for Domain-generalised Medical Image Segmentation
TLDR
This work proposes a novel semi-supervised meta-learning framework with disentanglement that explicitly model the representations related to domain shifts, and allows unlabeled data to be used to better approximate the true domain shifts for meta- learning.
Cooperative Training and Latent Space Data Augmentation for Robust Medical Image Segmentation
TLDR
A cooperative framework for training image segmentation models and a latent space augmentation method for generating hard examples that improves model generalization and robustness with limited data is presented.
Autoencoder based self-supervised test-time adaptation for medical image analysis
TLDR
This paper proposes a model that can adapt based on a single test subject during inference, which can achieve significant performance improvement and was validated on both retinal optical coherence tomography (OCT) image segmentation and magnetic resonance imaging (MRI) T1-weighted to T2- Weighted image synthesis.
U-shaped GAN for Semi-Supervised Learning and Unsupervised Domain Adaptation in High Resolution Chest Radiograph Segmentation
Deep learning has achieved considerable success in medical image segmentation. However, applying deep learning in clinical environments often involves two problems: (1) scarcity of annotated data as
Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization
TLDR
This paper proposes a novel dual-normalization module by leveraging the augmented source-similar and source-dissimilar images during generalizable segmentation to simulate the possible appearance change in unseen target domains.
Studying Robustness of Semantic Segmentation under Domain Shift in cardiac MRI
TLDR
This work builds upon a fixed U-Net architecture configured by the nnU-net framework to investigate various data augmentation techniques and batch normalization layers as an easy-to-customize pipeline component and provide general guidelines on how to improve domain generalizability abilities in existing deep learning methods.
Domain Composition and Attention for Unseen-Domain Generalizable Medical Image Segmentation
TLDR
Experimental results show that the proposed Domain Composition and Attention-based network (DCA-Net) can generalizes well on different and even unseen domains and it outperforms state-of-theart methods on the multi-domain prostate segmentation task.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 41 REFERENCES
Semantic-Aware Generative Adversarial Nets for Unsupervised Domain Adaptation in Chest X-ray Segmentation
TLDR
A novel unsupervised domain adaptation approach for segmentation tasks by designing semantic-aware generative adversarial networks (GANs) that transform the test image into the appearance of source domain, with the semantic structural information being well preserved.
Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
TLDR
A novel model framework for learning automatic X-ray image parsing from labeled CT scans is proposed and an added module leveraging the pre-trained DI2I to enforce segmentation consistency is introduced.
Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation
TLDR
This study trained a CNN on legacy MR images of brain and evaluated the performance of the domain-adapted network on the same task with images from a different domain, substantially outperforming a similar network trained on the the same set of examples from scratch.
Unsupervised domain adaptation in brain lesion segmentation with adversarial networks
TLDR
This work investigates unsupervised domain adaptation using adversarial neural networks to train a segmentation method which is more robust to differences in the input data, and which does not require any annotations on the test domain.
A Lifelong Learning Approach to Brain MR Segmentation Across Scanners and Protocols
TLDR
This work proposes a single CNN with shared convolutional filters and domain-specific batch normalization layers, which can be tuned to new domains with only a few (\({\approx 4) labelled images), which largely closes the gap to the benchmark, which is training a dedicated CNN for each scanner.
V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
TLDR
This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.
Generalizing Deep Models for Ultrasound Image Segmentation
TLDR
This paper proposes a self-play training strategy to effectively pre-train all the adversarial modules in their framework to capture the appearance and structure distributions of source corpus to stabilize the online adversarial appearance conversion.
GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks
TLDR
The feasibility of introducing GAN derived synthetic data to the training datasets in two brain segmentation tasks is demonstrated, leading to improvements in Dice Similarity Coefficient of between 1 and 5 percentage points under different conditions, with the strongest effects seen fewer than ten training image stacks are available.
Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
TLDR
An automated searching approach is proposed for the optimal training strategy with reinforcement learning for 3D medical image segmentation, and it can achieve comparable accuracy to other manually-tuned state-of-the-art segmentation approaches.
Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images
Automatic and accurate Gleason grading of histopathology tissue slides is crucial for prostate cancer diagnosis, treatment, and prognosis. Usually, histopathology tissue slides from different
...
1
2
3
4
5
...