Computer-aided diagnosis of metabolic dysfunction-associated steatotic liver disease using paired liver–kidney texture features
- 1Department of Bioelectrics and Biomedical Engineering, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences
- 2Department of Radiology, School of Medicine, Isfahan University of Medical Sciences
- 3Gastroenterology and Hepatology Research Center, Isfahan University of Medical Sciences
Abstract
This study aims to introduce a computer-aided diagnosis tool that leverages texture analysis and machine learning techniques to support radiologists in diagnosing fatty liver through ultrasound imaging. In this method, regions of interest for further analysis are identified from the paired liver-kidney. Textural features are extracted from these regions using conventional methods (e.g., GLCM) and advanced techniques (e.g., ELBP, NASTA). A two-stage feature reduction process is applied, beginning with a statistical t-test, followed by dimensionality reduction methods including PCA, SBS, SFS, LDA, and ReliefF. Finally, three classifiers: RF, SVM, and KNN are employed in two sequential stages to classify healthy versus fatty livers and grade fat accumulation severity. Furthermore, we developed a graphical user interface. We analyzed 189 ultrasound images from 54 patients. The ReliefF–SVM model in the first stage and the LDA–SVM model in the second achieved the highest performance, with an overall accuracy of 0.945 ± 0.023, precision of 0.935 ± 0.033, sensitivity of 0.940 ± 0.034, and specificity of 0.931 ± 0.036. Results demonstrate that extracting textural features from the paired liver-kidney regions using advanced methods with conventional features, and applying a two-stage binary classification framework, can significantly enhance the diagnostic efficacy of fatty liver.
Related
- A rare diagnosis during evaluation for metabolic dysfunction associated steatotic liver disease: Glycogen storage disease type Ia presenting during adolescence in a male with severe obesity
- European Society for Pediatric Gastroenterology, Hepatology and Nutrition (ESPGHAN) steatotic liver disease special interest group position paper on screening, diagnosis and investigation of paediatric metabolic dysfunction‐associated steatotic liver disease
- Efficacy and safety of GLP-1 receptor agonists in patients with metabolic dysfunction-associated steatotic liver disease (MASLD) and metabolic dysfunction-associated steatohepatitis (MASH) : A systematic review and meta-analysis
- Efficacy of plant extracts for metabolic dysfunction-associated steatotic liver disease: a network meta-analysis
- Tirzepatide use in adolescents with metabolic dysfunction‐associated steatotic liver disease (MASLD): A case series
BibTeX
@article{abdolvahabi2026computeraided,
title = {{Computer-aided diagnosis of metabolic dysfunction-associated steatotic liver disease using paired liver–kidney texture features}},
author = {Zahra Abdolvahabi and Alireza Vard and Kimia Kazemi and Peyman Adibi},
journal = {Scientific Reports},
year = {2026},
month = aug,
doi = {10.1038/s41598-026-65413-8},
url = {https://doi.org/10.1038/s41598-026-65413-8},
note = {CC BY},
}
RIS
TY - JOUR
TI - Computer-aided diagnosis of metabolic dysfunction-associated steatotic liver disease using paired liver–kidney texture features
AU - Zahra Abdolvahabi
AU - Alireza Vard
AU - Kimia Kazemi
AU - Peyman Adibi
PY - 2026
DA - 2026/08/01
JO - Scientific Reports
DO - 10.1038/s41598-026-65413-8
UR - https://doi.org/10.1038/s41598-026-65413-8
AB - This study aims to introduce a computer-aided diagnosis tool that leverages texture analysis and machine learning techniques to support radiologists in diagnosing fatty liver through ultrasound imaging. In this method, regions of interest for further analysis are identified from the paired liver-kidney. Textural features are extracted from these regions using conventional methods (e.g., GLCM) and advanced techniques (e.g., ELBP, NASTA). A two-stage feature reduction process is applied, beginning with a statistical t-test, followed by dimensionality reduction methods including PCA, SBS, SFS, LDA, and ReliefF. Finally, three classifiers: RF, SVM, and KNN are employed in two sequential stages to classify healthy versus fatty livers and grade fat accumulation severity. Furthermore, we developed a graphical user interface. We analyzed 189 ultrasound images from 54 patients. The ReliefF–SVM model in the first stage and the LDA–SVM model in the second achieved the highest performance, with an overall accuracy of 0.945 ± 0.023, precision of 0.935 ± 0.033, sensitivity of 0.940 ± 0.034, and specificity of 0.931 ± 0.036. Results demonstrate that extracting textural features from the paired liver-kidney regions using advanced methods with conventional features, and applying a two-stage binary classification framework, can significantly enhance the diagnostic efficacy of fatty liver.
SN - 2045-2322
ER -