Adaptive dual-window enhancement and multi-scale texture prior fusion for robust kidney CT classification
PLOS One · 2025
DOI: 10.1371/journal.pone.0335585 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Ping Xia und 5 weiteren Autor:innen. Beteiligte Einrichtung: The First Affiliated Hospital of Soochow University, Suzhou, China. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Kidney, Kidney Diseases, Image Processing, Computer-Assisted. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Province Leading Talents Cultivation Project for Traditional Chinese Medicine, Jiangsu Province Sixth Phase 333 High-Level Talents Project, the Jiangsu Provincial Medical Innovation Center, the 2024 Suzhou Science and Education Driven Healthcare Enhancement Project.
Abstract (Originalsprache)
Accurate classification of kidney diseases is of great importance for clinical diagnosis and treatment. However, traditional CT images suffer from insufficient contrast, blurred tissue boundaries, and complex texture variations, which limit the performance of automated analysis. This paper proposes a novel kidney CT classification framework that combines Adaptive Dual-Window Enhancement (ADWE) with Multi-Scale Texture Prior Fusion (MTPF). The ADWE module dynamically adjusts window width and window level to generate complementary views, effectively enhancing the contrast of both soft tissues and high-density structures; the MTPF module incorporates edge, local binary pattern (LBP), and Gabor texture priors to achieve fine-grained structural modeling. Experimental results demonstrate that in the binary classification task, the proposed method achieves an accuracy of 0.9802, F1-score of 0.9786, and AUC of 0.9989, all outperforming mainstream deep learning and domain-specific medical models. In the four-class classification task, it achieves an accuracy of 0.8821, F1-score of 0.8438, and AUC of 0.9801, representing an improvement of approximately 3%–5% compared with the ConvNeXtV2 baseline. Moreover, under noise intensity σ = 0.1 , the method still maintains an accuracy of 0.8510 and an AUC of 0.9634, showing remarkable robustness. These results validate the effectiveness and clinical potential of the proposed method for automated kidney CT classification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- The First Affiliated Hospital of Soochow University, Suzhou, China.
- Suzhou Traditional Chinese Medicine Hospital affiliated to Nanjing University of Chinese Medicine, Suzhou, China.
- Affiliated Hospital of Nanjing University of Chinese Medicine, Nanjing, China.
ORCID-Profile: Ming-Gang Wei
Förderung
- Jiangsu Province Leading Talents Cultivation Project for Traditional Chinese Medicine
- Jiangsu Province Sixth Phase 333 High-Level Talents Project, the Jiangsu Provincial Medical Innovation Center
- the 2024 Suzhou Science and Education Driven Healthcare Enhancement Project
- the 2024 Research Projects of the Jiangsu Association of Traditional Chinese Medicine
Zitieren
APA
Xia, P., Li, Y., Yao, X., Jiang, Y., He, W., & Wei, M. G. (2025). Adaptive dual-window enhancement and multi-scale texture prior fusion for robust kidney CT classification. PLOS One. https://doi.org/10.1371/journal.pone.0335585
Vancouver
Xia P, Li Y, Yao X, Jiang Y, He W, Wei MG. Adaptive dual-window enhancement and multi-scale texture prior fusion for robust kidney CT classification. PLOS One. 2025. doi:10.1371/journal.pone.0335585
BibTeX
@article{Xia2025,
author = {Xia, Ping and Li, Yilin and Yao, Xin and Jiang, Yunjia and He, WeiMing and Wei, Ming-Gang},
title = {Adaptive dual-window enhancement and multi-scale texture prior fusion for robust kidney CT classification},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0335585}
}
EUVIMED