Dense121GAN: transfer learning-enhanced conditional generative adversarial network with DenseNet121 for reliable and efficient segmentation in medical and industrial imaging.
- 1Department of Software Engineering, Istinye University, Istanbul, Turkey.
Abstract
Accurate image segmentation in medical and industrial domains remains challenging due to small object sizes, complex textures, and diverse defect morphologies. To address these limitations, we propose Dense121GAN, a conditional generative adversarial network (cGAN) that integrates a pre-trained DenseNet121 as a frozen encoder. The proposed architecture promotes effective feature reuse and stable information flow through residual skip connections. By leveraging transfer learning, Dense121GAN captures rich hierarchical representations and improves training stability, particularly in data-constrained settings. Extensive experiments were conducted using five-fold cross-validation across 16 heterogeneous datasets. Dense121GAN consistently outperformed UNet and ResNet-based generative adversarial networks (GANs) across multiple evaluation metrics, including Intersection over Union (IoU), Dice coefficient (Dice), Matthews Correlation Coefficient (MCC), Cohen's Kappa, Structural Similarity Index Measure (SSIM), coefficient of determination (R ²), and Symmetric Mean Absolute Percentage Error (SMAPE). The model also demonstrated stable training behavior and mitigated common GAN failure modes such as mode collapse. In addition, Dense121GAN achieved faster convergence compared to the evaluated baseline architectures. These results highlight the effectiveness, robustness, and computational efficiency of Dense121GAN. The proposed framework provides a practical and versatile solution for both clinical diagnostic and industrial inspection applications.
Related
- Multi-tissue segmentation of knee MRI based on U-Net and conditional generative adversarial networks
- FCVGAN: A Novel Generative Framework Integrating Fuzzy C-Means Clustering with Conditional VAE-GAN for Polyp Segmentation
- A conditional generative adversarial network with dual-context aggregation and color enhancement for digital mural creation
- Conditional Generative Adversarial Network for the simulation of seabird trajectories based on environmental data
- Hi-cGAN: Prediction of Hi-C interaction matrices with conditional generative adversarial networks
BibTeX
@article{davud2026dense121gan,
title = {{Dense121GAN: transfer learning-enhanced conditional generative adversarial network with DenseNet121 for reliable and efficient segmentation in medical and industrial imaging.}},
author = {Muhammed Davud},
journal = {PeerJ. Computer science},
year = {2026},
month = jul,
doi = {10.7717/peerj-cs.4020},
url = {https://europepmc.org/article/MED/42899234},
note = {CC BY},
}
RIS
TY - JOUR
TI - Dense121GAN: transfer learning-enhanced conditional generative adversarial network with DenseNet121 for reliable and efficient segmentation in medical and industrial imaging.
AU - Muhammed Davud
PY - 2026
DA - 2026/07/07
JO - PeerJ. Computer science
DO - 10.7717/peerj-cs.4020
UR - https://europepmc.org/article/MED/42899234
AB - Accurate image segmentation in medical and industrial domains remains challenging due to small object sizes, complex textures, and diverse defect morphologies. To address these limitations, we propose Dense121GAN, a conditional generative adversarial network (cGAN) that integrates a pre-trained DenseNet121 as a frozen encoder. The proposed architecture promotes effective feature reuse and stable information flow through residual skip connections. By leveraging transfer learning, Dense121GAN captures rich hierarchical representations and improves training stability, particularly in data-constrained settings. Extensive experiments were conducted using five-fold cross-validation across 16 heterogeneous datasets. Dense121GAN consistently outperformed UNet and ResNet-based generative adversarial networks (GANs) across multiple evaluation metrics, including Intersection over Union (IoU), Dice coefficient (Dice), Matthews Correlation Coefficient (MCC), Cohen's Kappa, Structural Similarity Index Measure (SSIM), coefficient of determination (R ²), and Symmetric Mean Absolute Percentage Error (SMAPE). The model also demonstrated stable training behavior and mitigated common GAN failure modes such as mode collapse. In addition, Dense121GAN achieved faster convergence compared to the evaluated baseline architectures. These results highlight the effectiveness, robustness, and computational efficiency of Dense121GAN. The proposed framework provides a practical and versatile solution for both clinical diagnostic and industrial inspection applications.
SN - 2167-9843
SN - 2376-5992
ER -