An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images

Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt

Standard

An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images. / Chen, Shuai; Bruijne, Marleen de.

2018.

Publikation: Konferencebidrag › Paper › Forskning › fagfællebedømt

Harvard

Chen, S & Bruijne, MD 2018, 'An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images'. <http://arxiv.org/pdf/1811.03549v1>

APA

Chen, S., & Bruijne, M. D. (2018). An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images. http://arxiv.org/pdf/1811.03549v1

Vancouver

Chen S, Bruijne MD. An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images. 2018.

Author

Chen, Shuai ; Bruijne, Marleen de. / An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images. 4 s.

Bibtex

@conference{e8951d5631ba499987a8e3660b25013c,
title = "An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images",
abstract = " Fully-connected Conditional Random Field (CRF) is often used as post-processing to refine voxel classification results by encouraging spatial coherence. In this paper, we propose a new end-to-end training method called Posterior-CRF. In contrast with previous approaches which use the original image intensity in the CRF, our approach applies 3D, fully connected CRF to the posterior probabilities from a CNN and optimizes both CNN and CRF together. The experiments on white matter hyperintensities segmentation demonstrate that our method outperforms CNN, post-processing CRF and different end-to-end training CRF approaches. ",
keywords = "cs.CV",
author = "Shuai Chen and Bruijne, {Marleen de}",
year = "2018",
month = nov,
day = "8",
language = "English",

}

RIS

TY - CONF

T1 - An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images

AU - Chen, Shuai

AU - Bruijne, Marleen de

PY - 2018/11/8

Y1 - 2018/11/8

N2 - Fully-connected Conditional Random Field (CRF) is often used as post-processing to refine voxel classification results by encouraging spatial coherence. In this paper, we propose a new end-to-end training method called Posterior-CRF. In contrast with previous approaches which use the original image intensity in the CRF, our approach applies 3D, fully connected CRF to the posterior probabilities from a CNN and optimizes both CNN and CRF together. The experiments on white matter hyperintensities segmentation demonstrate that our method outperforms CNN, post-processing CRF and different end-to-end training CRF approaches.

AB - Fully-connected Conditional Random Field (CRF) is often used as post-processing to refine voxel classification results by encouraging spatial coherence. In this paper, we propose a new end-to-end training method called Posterior-CRF. In contrast with previous approaches which use the original image intensity in the CRF, our approach applies 3D, fully connected CRF to the posterior probabilities from a CNN and optimizes both CNN and CRF together. The experiments on white matter hyperintensities segmentation demonstrate that our method outperforms CNN, post-processing CRF and different end-to-end training CRF approaches.

KW - cs.CV

UR - https://sites.google.com/view/med-nips-2018/abstracts

M3 - Paper

ER -

ID: 216262545