Cargando…

Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods

Medical image super-resolution (SR) has mainly been developed for a single image in the literature. However, there is a growing demand for high-resolution, thin-slice medical images. We hypothesized that fusing the two planes of a computed tomography (CT) study and applying the SR model to the third...

Descripción completa

Detalles Bibliográficos
Autores principales: Chao, Heng-Sheng, Wu, Yu-Hong, Siana, Linda, Chen, Yuh-Min
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9689374/
https://www.ncbi.nlm.nih.gov/pubmed/36359568
http://dx.doi.org/10.3390/diagnostics12112725
_version_ 1784836517534892032
author Chao, Heng-Sheng
Wu, Yu-Hong
Siana, Linda
Chen, Yuh-Min
author_facet Chao, Heng-Sheng
Wu, Yu-Hong
Siana, Linda
Chen, Yuh-Min
author_sort Chao, Heng-Sheng
collection PubMed
description Medical image super-resolution (SR) has mainly been developed for a single image in the literature. However, there is a growing demand for high-resolution, thin-slice medical images. We hypothesized that fusing the two planes of a computed tomography (CT) study and applying the SR model to the third plane could yield high-quality thin-slice SR images. From the same CT study, we collected axial planes of 1 mm and 5 mm in thickness and coronal planes of 5 mm in thickness. Four SR algorithms were then used for SR reconstruction. Quantitative measurements were performed for image quality testing. We also tested the effects of different regions of interest (ROIs). Based on quantitative comparisons, the image quality obtained when the SR models were applied to the sagittal plane was better than that when applying the models to the other planes. The results were statistically significant according to the Wilcoxon signed-rank test. The overall effect of the enhanced deep residual network (EDSR) model was superior to those of the other three resolution-enhancement methods. A maximal ROI containing minimal blank areas was the most appropriate for quantitative measurements. Fusing two series of thick-slice CT images and applying SR models to the third plane can yield high-resolution thin-slice CT images. EDSR provides superior SR performance across all ROI conditions.
format Online
Article
Text
id pubmed-9689374
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96893742022-11-25 Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods Chao, Heng-Sheng Wu, Yu-Hong Siana, Linda Chen, Yuh-Min Diagnostics (Basel) Article Medical image super-resolution (SR) has mainly been developed for a single image in the literature. However, there is a growing demand for high-resolution, thin-slice medical images. We hypothesized that fusing the two planes of a computed tomography (CT) study and applying the SR model to the third plane could yield high-quality thin-slice SR images. From the same CT study, we collected axial planes of 1 mm and 5 mm in thickness and coronal planes of 5 mm in thickness. Four SR algorithms were then used for SR reconstruction. Quantitative measurements were performed for image quality testing. We also tested the effects of different regions of interest (ROIs). Based on quantitative comparisons, the image quality obtained when the SR models were applied to the sagittal plane was better than that when applying the models to the other planes. The results were statistically significant according to the Wilcoxon signed-rank test. The overall effect of the enhanced deep residual network (EDSR) model was superior to those of the other three resolution-enhancement methods. A maximal ROI containing minimal blank areas was the most appropriate for quantitative measurements. Fusing two series of thick-slice CT images and applying SR models to the third plane can yield high-resolution thin-slice CT images. EDSR provides superior SR performance across all ROI conditions. MDPI 2022-11-08 /pmc/articles/PMC9689374/ /pubmed/36359568 http://dx.doi.org/10.3390/diagnostics12112725 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chao, Heng-Sheng
Wu, Yu-Hong
Siana, Linda
Chen, Yuh-Min
Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods
title Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods
title_full Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods
title_fullStr Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods
title_full_unstemmed Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods
title_short Generating High-Resolution CT Slices from Two Image Series Using Deep-Learning-Based Resolution Enhancement Methods
title_sort generating high-resolution ct slices from two image series using deep-learning-based resolution enhancement methods
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9689374/
https://www.ncbi.nlm.nih.gov/pubmed/36359568
http://dx.doi.org/10.3390/diagnostics12112725
work_keys_str_mv AT chaohengsheng generatinghighresolutionctslicesfromtwoimageseriesusingdeeplearningbasedresolutionenhancementmethods
AT wuyuhong generatinghighresolutionctslicesfromtwoimageseriesusingdeeplearningbasedresolutionenhancementmethods
AT sianalinda generatinghighresolutionctslicesfromtwoimageseriesusingdeeplearningbasedresolutionenhancementmethods
AT chenyuhmin generatinghighresolutionctslicesfromtwoimageseriesusingdeeplearningbasedresolutionenhancementmethods