EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fused-DCNN-U-Net with Hu-Driven YCBCR Transformation for Early Detection of Malignant Lung Nodules

B. Prashanthi

Journal of Intelligent Decision Making and Information Science · 10.10.2026 · 3 (16s) · 71-92

DOI: 10.17762/jidmis.v3.4884 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 10.10.2026. Verfasst von B. Prashanthi. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Lung cancer remains a leading cause of cancer-related mortality worldwide, highlighting the need for early and accurate diagnostic methods. This study proposes a hybrid deep learning framework for automated lung nodule segmentation and classification using computed tomography (CT) images. Unlike natural images, CT scans are inherently grayscale and represent tissue density through Hounsfield Units (HU). A novel HU-driven multi-channel transformation is introduced to enhance feature representation by mapping normalized HU values to an extended YCbCr space. In this formulation, the Y channel preserves intensity information, while the Cb and Cr channels act as auxiliary mathematical transforms that emphasize contrast and gradient variations, thereby enriching feature extraction. The proposed Fused-Dilated Convolution neural network named as Fused-DCNN-U-Net. It integrates dilated convolutional layers into a modified U-Net architecture for accurate segmentation, along with a parallel Convolutional neural network(CNN)-based classification head. The model is trained on a proprietary CT dataset and evaluated on the Barnard Institute of Radiology (BIR) Lung dataset. Experimental results demonstrate statistically significant improvements (p < 0.05) over grayscale baselines in terms of Dice coefficient, IoU, and classification accuracy, achieving 99.2% accuracy. Cross-dataset validation confirms robustness, while reduced false negatives indicate improved diagnostic reliability. The proposed framework offers a practical and efficient solution for early lung cancer detection and clinical decision support.

Zitieren

APA

Prashanthi, B. (2026). Fused-DCNN-U-Net with Hu-Driven YCBCR Transformation for Early Detection of Malignant Lung Nodules. Journal of Intelligent Decision Making and Information Science, 3(16s), 71-92. https://doi.org/10.17762/jidmis.v3.4884

Vancouver

Prashanthi B. Fused-DCNN-U-Net with Hu-Driven YCBCR Transformation for Early Detection of Malignant Lung Nodules. Journal of Intelligent Decision Making and Information Science. 2026;3(16s):71-92. doi:10.17762/jidmis.v3.4884

BibTeX
@article{Prashanthi2026,
  author = {Prashanthi, B.},
  title = {Fused-DCNN-U-Net with Hu-Driven YCBCR Transformation for Early Detection of Malignant Lung Nodules},
  journal = {Journal of Intelligent Decision Making and Information Science},
  year = {2026},
  volume = {3},
  number = {16s},
  pages = {71--92},
  doi = {10.17762/jidmis.v3.4884}
}
Kostenlos starten →