Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features

Abstract Robust machine learning models based on radiomic features might allow for accurate diagnosis, prognosis, and medical decision-making. Unfortunately, the lack of standardized radiomic feature extraction has hampered their clinical use. Since the radiomic features tend to be affected by low v...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Erick Costa de Farias, Christian di Noia, Changhee Han, Evis Sala, Mauro Castelli, Leonardo Rundo
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/1c283f93bd5f4101bb799f12bc7956e8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:1c283f93bd5f4101bb799f12bc7956e8
record_format	dspace
spelling	oai:doaj.org-article:1c283f93bd5f4101bb799f12bc7956e82021-11-08T10:53:24ZImpact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features10.1038/s41598-021-00898-z2045-2322https://doaj.org/article/1c283f93bd5f4101bb799f12bc7956e82021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-00898-zhttps://doaj.org/toc/2045-2322Abstract Robust machine learning models based on radiomic features might allow for accurate diagnosis, prognosis, and medical decision-making. Unfortunately, the lack of standardized radiomic feature extraction has hampered their clinical use. Since the radiomic features tend to be affected by low voxel statistics in regions of interest, increasing the sample size would improve their robustness in clinical studies. Therefore, we propose a Generative Adversarial Network (GAN)-based lesion-focused framework for Computed Tomography (CT) image Super-Resolution (SR); for the lesion (i.e., cancer) patch-focused training, we incorporate Spatial Pyramid Pooling (SPP) into GAN-Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE). At $$2\times $$ 2 × SR, the proposed model achieved better perceptual quality with less blurring than the other considered state-of-the-art SR methods, while producing comparable results at $$4\times $$ 4 × SR. We also evaluated the robustness of our model’s radiomic feature in terms of quantization on a different lung cancer CT dataset using Principal Component Analysis (PCA). Intriguingly, the most important radiomic features in our PCA-based analysis were the most robust features extracted on the GAN-super-resolved images. These achievements pave the way for the application of GAN-based image Super-Resolution techniques for studies of radiomics for robust biomarker discovery.Erick Costa de FariasChristian di NoiaChanghee HanEvis SalaMauro CastelliLeonardo RundoNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Erick Costa de Farias Christian di Noia Changhee Han Evis Sala Mauro Castelli Leonardo Rundo Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features
description	Abstract Robust machine learning models based on radiomic features might allow for accurate diagnosis, prognosis, and medical decision-making. Unfortunately, the lack of standardized radiomic feature extraction has hampered their clinical use. Since the radiomic features tend to be affected by low voxel statistics in regions of interest, increasing the sample size would improve their robustness in clinical studies. Therefore, we propose a Generative Adversarial Network (GAN)-based lesion-focused framework for Computed Tomography (CT) image Super-Resolution (SR); for the lesion (i.e., cancer) patch-focused training, we incorporate Spatial Pyramid Pooling (SPP) into GAN-Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE). At $$2\times $$ 2 × SR, the proposed model achieved better perceptual quality with less blurring than the other considered state-of-the-art SR methods, while producing comparable results at $$4\times $$ 4 × SR. We also evaluated the robustness of our model’s radiomic feature in terms of quantization on a different lung cancer CT dataset using Principal Component Analysis (PCA). Intriguingly, the most important radiomic features in our PCA-based analysis were the most robust features extracted on the GAN-super-resolved images. These achievements pave the way for the application of GAN-based image Super-Resolution techniques for studies of radiomics for robust biomarker discovery.
format	article
author	Erick Costa de Farias Christian di Noia Changhee Han Evis Sala Mauro Castelli Leonardo Rundo
author_facet	Erick Costa de Farias Christian di Noia Changhee Han Evis Sala Mauro Castelli Leonardo Rundo
author_sort	Erick Costa de Farias
title	Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features
title_short	Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features
title_full	Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features
title_fullStr	Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features
title_full_unstemmed	Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features
title_sort	impact of gan-based lesion-focused medical image super-resolution on the robustness of radiomic features
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/1c283f93bd5f4101bb799f12bc7956e8
work_keys_str_mv	AT erickcostadefarias impactofganbasedlesionfocusedmedicalimagesuperresolutionontherobustnessofradiomicfeatures AT christiandinoia impactofganbasedlesionfocusedmedicalimagesuperresolutionontherobustnessofradiomicfeatures AT changheehan impactofganbasedlesionfocusedmedicalimagesuperresolutionontherobustnessofradiomicfeatures AT evissala impactofganbasedlesionfocusedmedicalimagesuperresolutionontherobustnessofradiomicfeatures AT maurocastelli impactofganbasedlesionfocusedmedicalimagesuperresolutionontherobustnessofradiomicfeatures AT leonardorundo impactofganbasedlesionfocusedmedicalimagesuperresolutionontherobustnessofradiomicfeatures
_version_	1718442501387321344

Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features

Ejemplares similares