Random 2.5D U-net for Fully 3D Segmentation

2019-10-23 · Christoph Angermann, Markus Haltmeier

Convolutional neural networks are state-of-the-art for various segmentation tasks. While for 2D images these networks are also computationally efficient, 3D convolutions have huge storage requirements and therefore, end-to-end training is limited by GPU memory and data size. To overcome this issue, we introduce a network structure for volumetric data without 3D convolution layers. The main idea is to include projections from different directions to transform the volumetric data to a sequence of images, where each image contains information of the full data. We then apply 2D convolutions to these projection images and lift them again to volumetric data using a trainable reconstruction algorithm. The proposed architecture can be applied end-to-end to very large data volumes without cropping or sliding-window techniques. For a tested sparse binary segmentation task, it outperforms already known standard approaches and is more resistant to generation of artefacts.

📄 PDF Abstract BibTeX arXiv:1910.10398

Code (0)

등록된 구현이 없습니다.

Tasks

GPUSegmentation

Methods 이 논문이 사용한 방법론

3D Convolution A 3D Convolution is a type of convolution where the kernel slides in 3 dimensions as opposed to 2 dimensions with 2D…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Forming A Random Field via Stochastic Cliques: From Random Graphs to Fully Connected Random Fields

2015-06-30 · Mohammad Javad Shafiee, Alexander Wong, Paul Fieguth

Random fields have remained a topic of great interest over past decades for the purpose of structured inference, especially for problems such as image segmentation. The local nodal interactions commonly used in such mode…

Image Segmentation Semantic Segmentation

MRI Brain Tumor Segmentation using Random Forests and Fully Convolutional Networks

2019-09-13 · Mohammadreza Soltaninejad, Lei Zhang, Tryphon Lambrou, Guang Yang 외

In this paper, we propose a novel learning based method for automated segmentation of brain tumor in multimodal MRI images, which incorporates two sets of machine -learned and hand crafted features. Fully convolutional n…

Brain Tumor Segmentation Segmentation Tumor Segmentation

Incorporating Depth into both CNN and CRF for Indoor Semantic Segmentation

2017-05-21 · Jindong Jiang, Zhijun Zhang, Yongqian Huang, Lunan Zheng

To improve segmentation performance, a novel neural network architecture (termed DFCN-DCRF) is proposed, which combines an RGB-D fully convolutional neural network (DFCN) with a depth-sensitive fully-connected conditiona…

Semantic Segmentation

Discriminative Parameter Estimation for Random Walks Segmentation

2013-08-30 · Pierre-Yves Baudin, Danny Goodman, Puneet Kumar, Noura Azzabou 외

The Random Walks (RW) algorithm is one of the most e - cient and easy-to-use probabilistic segmentation methods. By combining contrast terms with prior terms, it provides accurate segmentations of medical images in a ful…

parameter estimation Segmentation

Discriminative Parameter Estimation for Random Walks Segmentation: Technical Report

2013-06-05 · Pierre-Yves Baudin, Danny Goodman, Puneet Kumar, Noura Azzabou 외