Radiomics Analysis of Whole-Kidney Non-Contrast CT for Early Identification of Chronic Kidney Disease Stages 1–3

Background: The early stages of chronic kidney disease (CKD) are often undetectable on traditional non-contrast computed tomography (NCCT) images through visual assessment by radiologists. This study aims to evaluate the potential of radiomics-based quantitative features extracted from NCCT, combine...

Full description

Saved in:
Bibliographic Details
Main Authors: Guirong Zhang, Pan Zhang, Yuwei Xia, Feng Shi, Yuelang Zhang, Dun Ding
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/12/5/454
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327512311562240
author Guirong Zhang
Pan Zhang
Yuwei Xia
Feng Shi
Yuelang Zhang
Dun Ding
author_facet Guirong Zhang
Pan Zhang
Yuwei Xia
Feng Shi
Yuelang Zhang
Dun Ding
author_sort Guirong Zhang
collection DOAJ
description Background: The early stages of chronic kidney disease (CKD) are often undetectable on traditional non-contrast computed tomography (NCCT) images through visual assessment by radiologists. This study aims to evaluate the potential of radiomics-based quantitative features extracted from NCCT, combined with machine learning techniques, in differentiating CKD stages 1–3 from healthy controls. Methods: This retrospective study involved 1099 CKD patients (stages 1–3) and 1099 healthy participants who underwent NCCT. Bilateral kidney volumes of interest were automatically segmented using a deep learning-based segmentation approach (VB-net) on CT images. Radiomics models were constructed using the mean values of features extracted from both kidneys. Key features were selected through Relief, MRMR, and LASSO regression algorithms. A machine learning classifier was trained to differentiate CKD from healthy kidneys and compared with the radiologist assessments. Model performance was evaluated using the area under the curve (AUC) of receiver operating characteristic analysis. Results: In the training set, the AUCs for the Gaussian process (GP) classifier model and radiologist assessments were 0.849 and 0.570, respectively. In the testing set, the AUC values were 0.790 for the GP model and 0.575 for radiologist assessments. Conclusions: The NCCT-based radiomics model demonstrates significant clinical utility by enabling non-invasive, early diagnosis of CKD stages 1–3, outperforming radiologist assessments.
format Article
id doaj-art-c847fe7a3f324821bb1ab658d8c336a8
institution Kabale University
issn 2306-5354
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-c847fe7a3f324821bb1ab658d8c336a82025-08-20T03:47:50ZengMDPI AGBioengineering2306-53542025-04-0112545410.3390/bioengineering12050454Radiomics Analysis of Whole-Kidney Non-Contrast CT for Early Identification of Chronic Kidney Disease Stages 1–3Guirong Zhang0Pan Zhang1Yuwei Xia2Feng Shi3Yuelang Zhang4Dun Ding5Department of Radiology, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, ChinaDepartment of Radiology, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, ChinaDepartment of Research and Development, United Imaging Intelligence, Shanghai 200232, ChinaDepartment of Research and Development, United Imaging Intelligence, Shanghai 200232, ChinaDepartment of Radiology, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, ChinaDepartment of Radiology, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an 710004, ChinaBackground: The early stages of chronic kidney disease (CKD) are often undetectable on traditional non-contrast computed tomography (NCCT) images through visual assessment by radiologists. This study aims to evaluate the potential of radiomics-based quantitative features extracted from NCCT, combined with machine learning techniques, in differentiating CKD stages 1–3 from healthy controls. Methods: This retrospective study involved 1099 CKD patients (stages 1–3) and 1099 healthy participants who underwent NCCT. Bilateral kidney volumes of interest were automatically segmented using a deep learning-based segmentation approach (VB-net) on CT images. Radiomics models were constructed using the mean values of features extracted from both kidneys. Key features were selected through Relief, MRMR, and LASSO regression algorithms. A machine learning classifier was trained to differentiate CKD from healthy kidneys and compared with the radiologist assessments. Model performance was evaluated using the area under the curve (AUC) of receiver operating characteristic analysis. Results: In the training set, the AUCs for the Gaussian process (GP) classifier model and radiologist assessments were 0.849 and 0.570, respectively. In the testing set, the AUC values were 0.790 for the GP model and 0.575 for radiologist assessments. Conclusions: The NCCT-based radiomics model demonstrates significant clinical utility by enabling non-invasive, early diagnosis of CKD stages 1–3, outperforming radiologist assessments.https://www.mdpi.com/2306-5354/12/5/454chronic kidney diseaseradiomicsnon-contrast computed tomographyestimated glomerular filtration ratemachine learning
spellingShingle Guirong Zhang
Pan Zhang
Yuwei Xia
Feng Shi
Yuelang Zhang
Dun Ding
Radiomics Analysis of Whole-Kidney Non-Contrast CT for Early Identification of Chronic Kidney Disease Stages 1–3
Bioengineering
chronic kidney disease
radiomics
non-contrast computed tomography
estimated glomerular filtration rate
machine learning
title Radiomics Analysis of Whole-Kidney Non-Contrast CT for Early Identification of Chronic Kidney Disease Stages 1–3
title_full Radiomics Analysis of Whole-Kidney Non-Contrast CT for Early Identification of Chronic Kidney Disease Stages 1–3
title_fullStr Radiomics Analysis of Whole-Kidney Non-Contrast CT for Early Identification of Chronic Kidney Disease Stages 1–3
title_full_unstemmed Radiomics Analysis of Whole-Kidney Non-Contrast CT for Early Identification of Chronic Kidney Disease Stages 1–3
title_short Radiomics Analysis of Whole-Kidney Non-Contrast CT for Early Identification of Chronic Kidney Disease Stages 1–3
title_sort radiomics analysis of whole kidney non contrast ct for early identification of chronic kidney disease stages 1 3
topic chronic kidney disease
radiomics
non-contrast computed tomography
estimated glomerular filtration rate
machine learning
url https://www.mdpi.com/2306-5354/12/5/454
work_keys_str_mv AT guirongzhang radiomicsanalysisofwholekidneynoncontrastctforearlyidentificationofchronickidneydiseasestages13
AT panzhang radiomicsanalysisofwholekidneynoncontrastctforearlyidentificationofchronickidneydiseasestages13
AT yuweixia radiomicsanalysisofwholekidneynoncontrastctforearlyidentificationofchronickidneydiseasestages13
AT fengshi radiomicsanalysisofwholekidneynoncontrastctforearlyidentificationofchronickidneydiseasestages13
AT yuelangzhang radiomicsanalysisofwholekidneynoncontrastctforearlyidentificationofchronickidneydiseasestages13
AT dunding radiomicsanalysisofwholekidneynoncontrastctforearlyidentificationofchronickidneydiseasestages13