EUVIMEDEUVIMED entdecken
Crossref

Neural Network–Based Multi-Level Classification for Region-Oriented CT Lung Image Analysis: Neural Network–Based Classification

Jalaldeen Khan Mohamed, K Jayaprakasam, M Pandimadevi, M Vadivel, K Ashokkumar

International Journal of Medical Toxicology and Forensic Medicine · 11.03.2026

DOI: 10.22037/ijmtfm.v16.51398 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Medical Toxicology and Forensic Medicine, erschienen am 11.03.2026. Verfasst von Jalaldeen Khan Mohamed und 4 weiteren Autor:innen.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Lung cancer remains a leading cause of mortality worldwide, and computed tomography (CT) imaging plays a vital role in its diagnosis, follow-up, and medico-legal evaluation. However, manual interpretation of CT images is time-consuming and often affected by inter-observer variability, particularly in resource-limited settings.

Methods

This study proposes a region-oriented CT lung image analysis framework that integrates Fuzzy Possibilistic C-Means (FPCM) segmentation with a multi-level neural network classifier. After preprocessing, CT images are segmented to delineate lung parenchyma, nodules, and surrounding tissues. Intensity, texture, and shape-based features are then extracted, and a hierarchical neural network is employed to progressively classify lung regions, abnormalities, and suspicious cancer-related patterns.

Results

Experimental evaluation demonstrates that the proposed framework outperforms conventional clustering techniques and single-level classifiers. Improved performance is observed in terms of accuracy, sensitivity, specificity, and Dice similarity coefficient, along with a reduction in false positive detections across diverse CT lung images.

Conclusion

The proposed automated framework provides an accurate and cost-effective solution for CT lung image analysis. Its robustness and interpretability make it suitable for clinical diagnosis as well as medical toxicology and forensic applications, including deployment in resource-constrained environments.

Schlagwörter

lung cancerlung CTlung nodule detectionimage segmentationhierarchical classificationtexture featuresshape featuresautomated image analysisforensic toxicologyresource-limited settings

Zitieren

APA

Mohamed, J. K., Jayaprakasam, K., Pandimadevi, M., Vadivel, M., & Ashokkumar, K. (2026). Neural Network–Based Multi-Level Classification for Region-Oriented CT Lung Image Analysis: Neural Network–Based Classification. International Journal of Medical Toxicology and Forensic Medicine. https://doi.org/10.22037/ijmtfm.v16.51398

Vancouver

Mohamed JK, Jayaprakasam K, Pandimadevi M, Vadivel M, Ashokkumar K. Neural Network–Based Multi-Level Classification for Region-Oriented CT Lung Image Analysis: Neural Network–Based Classification. International Journal of Medical Toxicology and Forensic Medicine. 2026. doi:10.22037/ijmtfm.v16.51398

BibTeX
@article{Mohamed2026,
  author = {Mohamed, Jalaldeen Khan and Jayaprakasam, K and Pandimadevi, M and Vadivel, M and Ashokkumar, K},
  title = {Neural Network–Based Multi-Level Classification for Region-Oriented CT Lung Image Analysis: Neural Network–Based Classification},
  journal = {International Journal of Medical Toxicology and Forensic Medicine},
  year = {2026},
  doi = {10.22037/ijmtfm.v16.51398}
}
Kostenlos starten →