Corpus ID: 67855292

SPDA: Superpixel-based Data Augmentation for Biomedical Image Segmentation

@inproceedings{Zhang2019SPDASD,
  title={SPDA: Superpixel-based Data Augmentation for Biomedical Image Segmentation},
  author={Yizhe Zhang and Lin Yang and Hao Zheng and Peixian Liang and Colleen A Mangold and Raquel G. Loreto and David P. Hughes and Danny Ziyi Chen},
  booktitle={MIDL},
  year={2019}
}
Supervised training a deep neural network aims to "teach" the network to mimic human visual perception that is represented by image-and-label pairs in the training data. Superpixelized (SP) images are visually perceivable to humans, but a conventionally trained deep learning model often performs poorly when working on SP images. To better mimic human visual perception, we think it is desirable for the deep learning model to be able to perceive not only raw images but also SP images. In this… Expand
SEEK: A Framework of Superpixel Learning with CNN Features for Unsupervised Segmentation
TLDR
This work iteratively enable the CNN architecture to learn the target generated by a graph-based segmentation method, while simultaneously preventing the network from falling into the pit of over-segmentation. Expand
Challenges and Recent Solutions for Image Segmentation in the Era of Deep Learning
  • E. Goceri
  • Computer Science
  • 2019 Ninth International Conference on Image Processing Theory, Tools and Applications (IPTA)
  • 2019
TLDR
The challenges that are mostly related to architecture and training of deep neural networks are explained and the state-of-the-art solutions applied in the literature are presented to help researchers to design proper network architectures according to their problems. Expand
Feature Preserving Smoothing Provides Simple and Effective Data Augmentation for Medical Image Segmentation
TLDR
Experiments on multiple medical image segmentation tasks confirm that, especially when limited training data is available or a domain shift is involved, feature preserving smoothing can indeed serve as a simple and effective augmentation technique. Expand
Investigating the Performance of Generative Adversarial Networks for Prostate Tissue Detection and Segmentation
TLDR
Conditional GAN, cycleGAN and U-Net models and their performances were studied for the detection and segmentation of prostate tissue in 3D multi-parametric MRI scans and the cGAN model outperformed the U- net and cycleGAN predictions owing to the inclusion of paired image supervision. Expand
Hermite transform-based superpixel for texture image segmentation
TLDR
The proposed algorithm adds texture information to the common superpixel representation with the Hermite Transform, which extracts local texture features in terms of Gaussian derivatives, and generates superpixels preserving boundary adherence, smoothness, regularity, and compactness. Expand

References

SHOWING 1-10 OF 26 REFERENCES
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Gland Instance Segmentation Using Deep Multichannel Neural Networks
  • Yan Xu, Yang Li, +4 authors E. Chang
  • Computer Science, Medicine
  • IEEE Transactions on Biomedical Engineering
  • 2017
TLDR
An algorithm that automatically exploits and fuses complex multichannel information—regional, location, and boundary cues—in gland histology images and is able to meet multifarious requirements by altering channels is proposed. Expand
Gland Instance Segmentation by Deep Multichannel Neural Networks
TLDR
A new image instance segmentation method that segments individual glands (instances) in colon histology images, alleviates heavy feature design due to the use of convolutional neural networks and is able to meet multifarious requirement by altering channels. Expand
Gland Instance Segmentation by Deep Multichannel Side Supervision
TLDR
The proposed system, deep multichannel side supervision (DMCS), alleviates heavy feature design due to the use of convolutional neural networks guided by side supervision in gland histology images. Expand
Improving Data Augmentation for Medical Image Segmentation
TLDR
It is shown that the recently-proposed ‘mixup’ algorithm increases performance in segmentation tasks, and a theoretical suggestion is offered for the efficacy of this technique. Expand
ImageNet classification with deep convolutional neural networks
TLDR
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images
TLDR
An auto‐context version of the VoxResNet is proposed by combining the low‐level image appearance features, implicit shape information, and high‐level context together for further improving the segmentation performance, and achieved the best performance in the 2013 MICCAI MRBrainS challenge. Expand
Deep Contextual Networks for Neuronal Structure Segmentation
TLDR
A deep contextual network is proposed here by leveraging multi-level contextual information from the deep hierarchical structure to achieve better segmentation performance and can potentially facilitate the automatic connectome analysis from EM images with less human intervention effort. Expand
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
TLDR
A method to allow a neural net to learn augmentations that best improve the classifier, which is called neural augmentation is proposed, and the successes and shortcomings of this method are discussed. Expand
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
TLDR
The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training. Expand
...
1
2
3
...