A New Ensemble Learning Framework for 3D Biomedical Image Segmentation

@inproceedings{Zheng2018ANE,
  title={A New Ensemble Learning Framework for 3D Biomedical Image Segmentation},
  author={Hao Zheng and Yizhe Zhang and Lin Yang and Peixian Liang and Zhuo Zhao and Chaoli Wang and Danny Ziyi Chen},
  booktitle={AAAI Conference on Artificial Intelligence},
  year={2018}
}
3D image segmentation plays an important role in biomedical image analysis. Many 2D and 3D deep learning models have achieved state-of-the-art segmentation performance on 3D biomedical image datasets. Yet, 2D and 3D models have their own strengths and weaknesses, and by unifying them together, one may be able to achieve more accurate results. In this paper, we propose a new ensemble learning framework for 3D biomedical image segmentation that combines the merits of 2D and 3D models. First, we… 
View PDF on arXiv
56 Citations
Highly Influential Citations
2
Background Citations
15
Methods Citations
20

Figures and Tables from this paper

56 Citations

Division and Fusion: Rethink Convolutional Kernels for 3D Medical Image Segmentation

This paper proposes a general solution, Division-Fusion (DF)-CNN for free performance improvement on any available 3D medical image segmentation approach, and extensively evaluated the DF mechanism on prostate ultrasound volume segmentation.

Neural Style Transfer Improves 3D Cardiovascular MR Image Segmentation on Inconsistent Data

StyleSegor, an efficient and easy-to-use strategy to alleviate the inconsistency in medical images generated by different machines and hospitals, and is corroborated to be an accurate tool for 3D whole heart segmentation especially on highly inconsistent data.

An Annotation Sparsification Strategy for 3D Medical Image Segmentation via Representative Selection and Self-Training

A new DL framework for reducing annotation effort and bridging the gap between full annotation and sparse annotation in 3D medical image segmentation is proposed, which achieves this by selecting representative slices in3D images that minimize data redundancy and save annotation effort.

3D Dense Separated Convolution Module for Volumetric Image Analysis

A novel 3D Dense Separated Convolution (3D-DSC) module is proposed to replace the original 3D convolutional kernels and demonstrated the superiority of 3D- DSC on volumetric image classification and segmentation, which are two challenging tasks often encountered in biomedical image computing.

3D Dense Separated Convolution Module for Volumetric Medical Image Analysis

A novel 3D Dense Separated Convolution module is proposed to replace the original 3D convolutional kernels and demonstrates the superiority of 3D-DSC on volumetric medical image classification and segmentation, which are two challenging tasks often encountered in biomedical image computing.

Fusing 2D and 3D convolutional neural networks for the segmentation of aorta and coronary arteries from CT images

Reinventing 2D Convolutions for 3D Medical Images

This study proposes ACS (axial-coronal-sagittal) convolutions to perform natively 3D representation learning, while utilizing the pretrained weights from 2D counterparts, to bridge the gap between 2D and 3D convolution by reinventing the 2D convolutions.

Reinventing 2D Convolutions for 3D Images

This study proposes ACS (axial-coronal-sagittal) convolutions to perform natively 3D representation learning, while utilizing the pretrained weights on 2D datasets, to bridge the gap between 2D and 3D convolution by reinventing the 2D convolutions.

Ensemble of deep learning models with surrogate-based optimization for medical image segmentation

This paper proposes an ensemble framework of DNNs for the problem of medical image segmentation and introduces an effective combining strategy for individual segmentation models based on swarm intelligence, which is a family of optimization algorithms inspired by biological processes.

CMC-Net: 3D calf muscle compartment segmentation with sparse annotation

...

References

SHOWING 1-10 OF 31 REFERENCES

Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation

This paper proposes a new DL framework for 3D image segmentation, based on a fully convolutional network (FCN) and a recurrent neural network (RNN), which are responsible for exploiting the intra-slice and inter-slice contexts, respectively.

Bridging the Gap Between 2D and 3D Organ Segmentation with Volumetric Fusion Net

An alternative framework is presented, which trains 2D networks on different viewpoints for segmentation, and builds a 3D Volumetric Fusion Net (VFN) to fuse the 2D segmentation results, which is relatively shallow and contains much fewer parameters than most 3D networks.

3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes

A novel 3D deeply supervised network (3D DSN) is presented which takes advantage of a fully convolutional architecture which performs efficient end-to-end learning and inference and introduces a deep supervision mechanism during the learning process to combat potential optimization difficulties.

Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation

A deep active learning framework that combines fully convolutional network (FCN) and active learning to significantly reduce annotation effort by making judicious suggestions on the most effective annotation areas is presented.

Bridging the Gap Between 2D and 3D Organ Segmentation

An alternative framework is presented, which trains 2D networks on different viewpoints for segmentation, and builds a 3D Volumetric Fusion Net (VFN) to fuse the 2D segmentation results, which is relatively shallow and contains much fewer parameters than most 3D networks.

VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images

Automatic 3D Cardiovascular MR Segmentation with Densely-Connected Volumetric ConvNets

A novel densely-connected volumetric convolutional neural network to automatically segment the cardiac and vascular structures from 3D cardiac MR images, referred as DenseVoxNet, and it is shown that this network can achieve better performance than other 3D ConvNets but with fewer parameters.

Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Prediction

This work adopts a recursively trained architecture in which a first network generates a preliminary boundary map that is provided as input along with the original image to a second network that generates a final boundary map, and uses a much deeper network than previously employed for boundary detection.

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

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.

DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation

An efficient deep contour-aware network (DCAN) to solve this challenging problem under a unified multi-task learning framework and can be efficient when applied to large-scale histopathological data without resorting to additional steps to generate contours based on low-level cues for post-separating.