Deep patch-based priors under a fully convolutional encoder-decoder architecture for interstitial lung disease segmentation - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Deep patch-based priors under a fully convolutional encoder-decoder architecture for interstitial lung disease segmentation

(1, 2) , (1, 2) , (1, 2) , (3) , (4)
1
2
3
4

Abstract

Interstitial lung diseases (ILD) encompass a large spectrum of diseases sharing similarities in their physiopathology and computed tomography (CT) appearance. In this paper, we propose the adaption of a deep convolutional encoder-decoder (CED) that has shown high accuracy for image segmentation. Such architectures require annotation of the total region with pathological findings. This is difficult to acquire, due to uncertainty in the definition and extent of disease patterns and the need of significant human effort, especially for large datasets. Therefore, often current methods use patch-based implementations of convolutional neural networks, which however tend to produce spatially inhomogeneous segmen-tations due to their local contextual view. We exploit the advantages of both architectures by using the output of a patch-based classifier as a prior to a CED. Our method could advance the state-of-the-art in lung tissue segmentation using only a small number of newly annotated images.
Fichier principal
Vignette du fichier
Vakalopoulou_etal_ISBI18.pdf (341.14 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01721714 , version 1 (02-03-2018)

Identifiers

  • HAL Id : hal-01721714 , version 1

Cite

Maria Vakalopoulou, Guillaume Chassagnon, Nikos Paragios, Marie-Pierre Revel, Evangelia I. Zacharaki. Deep patch-based priors under a fully convolutional encoder-decoder architecture for interstitial lung disease segmentation. ISBI’18 - IEEE International Symposium on Biomedical Imaging, Apr 2018, Washington, D.C., United States. ⟨hal-01721714⟩
317 View
406 Download

Share

Gmail Facebook Twitter LinkedIn More