ErrorNet: Learning Error Representations from Limited Data to Improve Vascular Segmentation

@article{Tajbakhsh2020ErrorNetLE,
  title={ErrorNet: Learning Error Representations from Limited Data to Improve Vascular Segmentation},
  author={Nima Tajbakhsh and Brian Lai and Shilpa P. Ananth and Xiaowei Ding},
  journal={2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)},
  year={2020},
  pages={1364-1368}
}
Deep convolutional neural networks have proved effective in segmenting lesions and anatomies in various medical imaging modalities. However, in the presence of small sample size and domain shift problems, these models often produce masks with non-intuitive segmentation mistakes. In this paper, we propose a segmentation framework called ErrorNet, which learns to correct these segmentation mistakes through the repeated process of injecting systematic segmentation errors to the segmentation result… Expand
DAPR-Net: Domain Adaptive Predicting-Refinement Network for Retinal Vessel Segmentation
TLDR
A novel domain adaptive predicting-refinement network called DAPR-Net is proposed to perform domain adaptive segmentation task on retinal vessel images to mitigate the gap between two domains and improves accuracy of segmentation results in dealing with domain shift. Expand
Progressive Adversarial Semantic Segmentation
TLDR
This work proposes a novel end - to-end medical image segmentation model, namely Progressive Adversarial Semantic Segmentation (PASS), which can make improved and consistent pixel-wise segmentation predictions without requiring any domain-specific data during training. Expand
Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
TLDR
This article provides a detailed review of the solutions above, summarizing both the technical novelties and empirical results, and compares the benefits and requirements of the surveyed methodologies and provides recommended solutions. Expand
UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
TLDR
UNet++ is proposed, a new neural architecture for semantic and instance segmentation by alleviating the unknown network depth with an efficient ensemble of U-Nets of varying depths and redesigning skip connections to aggregate features of varying semantic scales at the decoder sub-networks, leading to a highly flexible feature fusion scheme. Expand
The Unreasonable Effectiveness of Encoder-Decoder Networks for Retinal Vessel Segmentation
TLDR
It is shown that this encoder-decoder framework - called VLight - avoids overfitting to specific training images and generalizes well across different datasets, which makes it highly suitable for real-world applications where robustness, accuracy as well as low inference time on high-resolution fundus images is required. Expand
Mixed Supervision Learning for Whole Slide Image Classification
TLDR
A mixed supervision learning framework for super high-resolution images to effectively utilize their various labels and make use of coarse image-level labels to refine selfsupervised learning and generate high-quality pixel-level pseudo labels is proposed. Expand
Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning: Second MICCAI Workshop, DART 2020, and First MICCAI Workshop, DCL 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, October 4–8, 2020, Proceedings
TLDR
An auxiliary indicator function layer is designed to compress the network architecture via removing a decoding block, in which all individual responses are less than a given threshold α, that allows us to automatically identify and discard redundant decoding blocks without the loss of precision. Expand

References

SHOWING 1-10 OF 19 REFERENCES
Interactive segmentation of medical images through fully convolutional neural networks
TLDR
A deep learning (DL) based semi-automated segmentation approach that aims to be a "smart" interactive tool for region of interest delineation in medical images and demonstrates its use for segmenting multiple organs on computed tomography of the abdomen. Expand
Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation
TLDR
This article provides a detailed review of the solutions above, summarizing both the technical novelties and empirical results, and compares the benefits and requirements of the surveyed methodologies and provides recommended solutions. Expand
Anatomical Priors for Image Segmentation via Post-Processing with Denoising Autoencoders
TLDR
Post-DAE is proposed, a post-processing method based on denoising autoencoders (DAE) trained using only segmentation masks that can improve the quality of noisy and incorrect segmentation mask obtained with a variety of standard methods, by bringing them back to a feasible space, with almost no extra computational time. Expand
Intelligent Labeling Based on Fisher Information for Medical Image Segmentation Using Deep Learning
TLDR
A new active learning method based on Fisher information (FI) for CNNs for the first time is proposed and the results showed that FI-based AL outperformed the competing methods in improving the performance of the model after labeling a very small portion of target data set. Expand
SynSeg-Net: Synthetic Segmentation Without Target Modality Ground Truth
TLDR
An end-to-end synthetic segmentation network (SynSeg-Net) to train a segmentationNetwork for a target imaging modality without having manual labels is proposed and achieved comparable performance to the traditional segmentationnetwork using target modality labels in certain scenarios. Expand
UNet++: A Nested U-Net Architecture for Medical Image Segmentation
TLDR
This paper presents UNet++, a new, more powerful architecture for medical image segmentation where the encoder and decoder sub-networks are connected through a series of nested, dense skip pathways, and argues that the optimizer would deal with an easier learning task when the feature maps from the decoder and encoder networks are semantically similar. Expand
Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network
TLDR
This work proposes a generic cross-modality synthesis approach and shows that these goals can be achieved with an end-to-end 3D convolutional neural network (CNN) composed of mutually-beneficial generators and segmentors for image synthesis and segmentation tasks. Expand
Synergistic Image and Feature Adaptation: Towards Cross-Modality Domain Adaptation for Medical Image Segmentation
TLDR
This paper presents a novel unsupervised domain adaptation framework, called Synergistic Image and Feature Adaptation (SIFA), to effectively tackle the problem of domain shift, and extensively validated the method with a challenging application of cross-modality medical image segmentation of cardiac structures. Expand
Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
TLDR
An efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data, and improves on the state-of-the‐art for all three applications. Expand
Cost-Sensitive Active Learning for Intracranial Hemorrhage Detection
TLDR
This paper builds a cost-sensitive active learning system for the problem of intracranial hemorrhage detection and segmentation on head computed tomography (CT) and shows that the ensemble method compares favorably with the state-of-the-art, while running faster and using less memory. Expand
...
1
2
...