A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation

Multi-organ segmentation of X-ray images is of fundamental importance for computer aided diagnosis systems. However, the most advanced semantic segmentation methods rely on deep learning and require a huge amount of labeled images, which are rarely available due to both the high cost of human resour...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Giorgio Ciano, Paolo Andreini, Tommaso Mazzierli, Monica Bianchini, Franco Scarselli
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep learning convolutional neural networks semantic segmentation generative adversarial networks chest X-ray image augmentation Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/1b5d1880254149c885f696e5bbd61d1d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1b5d1880254149c885f696e5bbd61d1d
record_format	dspace
spelling	oai:doaj.org-article:1b5d1880254149c885f696e5bbd61d1d2021-11-25T18:16:57ZA Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation10.3390/math92228962227-7390https://doaj.org/article/1b5d1880254149c885f696e5bbd61d1d2021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/22/2896https://doaj.org/toc/2227-7390Multi-organ segmentation of X-ray images is of fundamental importance for computer aided diagnosis systems. However, the most advanced semantic segmentation methods rely on deep learning and require a huge amount of labeled images, which are rarely available due to both the high cost of human resources and the time required for labeling. In this paper, we present a novel multi-stage generation algorithm based on Generative Adversarial Networks (GANs) that can produce synthetic images along with their semantic labels and can be used for data augmentation. The main feature of the method is that, unlike other approaches, generation occurs in several stages, which simplifies the procedure and allows it to be used on very small datasets. The method was evaluated on the segmentation of chest radiographic images, showing promising results. The multi-stage approach achieves state-of-the-art and, when very few images are used to train the GANs, outperforms the corresponding single-stage approach.Giorgio CianoPaolo AndreiniTommaso MazzierliMonica BianchiniFranco ScarselliMDPI AGarticledeep learningconvolutional neural networkssemantic segmentationgenerative adversarial networkschest X-rayimage augmentationMathematicsQA1-939ENMathematics, Vol 9, Iss 2896, p 2896 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep learning convolutional neural networks semantic segmentation generative adversarial networks chest X-ray image augmentation Mathematics QA1-939
spellingShingle	deep learning convolutional neural networks semantic segmentation generative adversarial networks chest X-ray image augmentation Mathematics QA1-939 Giorgio Ciano Paolo Andreini Tommaso Mazzierli Monica Bianchini Franco Scarselli A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation
description	Multi-organ segmentation of X-ray images is of fundamental importance for computer aided diagnosis systems. However, the most advanced semantic segmentation methods rely on deep learning and require a huge amount of labeled images, which are rarely available due to both the high cost of human resources and the time required for labeling. In this paper, we present a novel multi-stage generation algorithm based on Generative Adversarial Networks (GANs) that can produce synthetic images along with their semantic labels and can be used for data augmentation. The main feature of the method is that, unlike other approaches, generation occurs in several stages, which simplifies the procedure and allows it to be used on very small datasets. The method was evaluated on the segmentation of chest radiographic images, showing promising results. The multi-stage approach achieves state-of-the-art and, when very few images are used to train the GANs, outperforms the corresponding single-stage approach.
format	article
author	Giorgio Ciano Paolo Andreini Tommaso Mazzierli Monica Bianchini Franco Scarselli
author_facet	Giorgio Ciano Paolo Andreini Tommaso Mazzierli Monica Bianchini Franco Scarselli
author_sort	Giorgio Ciano
title	A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation
title_short	A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation
title_full	A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation
title_fullStr	A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation
title_full_unstemmed	A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation
title_sort	multi-stage gan for multi-organ chest x-ray image generation and segmentation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/1b5d1880254149c885f696e5bbd61d1d
work_keys_str_mv	AT giorgiociano amultistageganformultiorganchestxrayimagegenerationandsegmentation AT paoloandreini amultistageganformultiorganchestxrayimagegenerationandsegmentation AT tommasomazzierli amultistageganformultiorganchestxrayimagegenerationandsegmentation AT monicabianchini amultistageganformultiorganchestxrayimagegenerationandsegmentation AT francoscarselli amultistageganformultiorganchestxrayimagegenerationandsegmentation AT giorgiociano multistageganformultiorganchestxrayimagegenerationandsegmentation AT paoloandreini multistageganformultiorganchestxrayimagegenerationandsegmentation AT tommasomazzierli multistageganformultiorganchestxrayimagegenerationandsegmentation AT monicabianchini multistageganformultiorganchestxrayimagegenerationandsegmentation AT francoscarselli multistageganformultiorganchestxrayimagegenerationandsegmentation
_version_	1718411366247694336

A Multi-Stage GAN for Multi-Organ Chest X-ray Image Generation and Segmentation

Ejemplares similares