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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |