Dual-Path Convolutional Neural Network with Squeeze-and-Excitation Attention for Lung and Colon Histopathology Classification
Guardado en:
| Udgivet i: | Journal of Imaging vol. 11, no. 12 (2025), p. 448-465 |
|---|---|
| Hovedforfatter: | |
| Udgivet: |
MDPI AG
|
| Fag: | |
| Online adgang: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3286310264 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2313-433X | ||
| 024 | 7 | |a 10.3390/jimaging11120448 |2 doi | |
| 035 | |a 3286310264 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 100 | 1 | |a AlShehri Helala | |
| 245 | 1 | |a Dual-Path Convolutional Neural Network with Squeeze-and-Excitation Attention for Lung and Colon Histopathology Classification | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Lung and colon cancers remain among the leading causes of cancer-related mortality worldwide, underscoring the need for rapid and accurate histopathological diagnosis. Manual examination of biopsy slides is often time-consuming and prone to inter-observer variability, which highlights the importance of developing reliable and explainable automated diagnostic systems. This study presents DPCSE-Net, a lightweight dual-path convolutional neural network enhanced with a squeeze-and-excitation (SE) attention mechanism for lung and colon cancer classification. The dual-path structure captures both fine-grained cellular textures and global contextual information through multiscale feature extraction, while the SE attention module adaptively recalibrates channel responses to emphasize discriminative features. To enhance transparency and interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM), attention heatmaps, and Integrated Gradients are employed to visualize class-specific activation patterns and verify that the model’s focus aligns with diagnostically relevant tissue regions. Evaluated on the publicly available LC25000 dataset, DPCSE-Net achieved state-of-the-art performance with 99.88% accuracy and F1-score, while maintaining low computational complexity. Ablation experiments confirmed the contribution of the dual-path design and SE module, and qualitative analyses demonstrated the model’s strong interpretability. These results establish DPCSE-Net as an accurate, efficient, and explainable framework for computer-aided histopathological diagnosis, supporting the broader goals of explainable AI in computer vision. | |
| 653 | |a Qualitative analysis | ||
| 653 | |a Excitation | ||
| 653 | |a Classification | ||
| 653 | |a Lungs | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Artificial neural networks | ||
| 653 | |a Neural networks | ||
| 653 | |a Ablation | ||
| 653 | |a Diagnostic systems | ||
| 653 | |a Computer vision | ||
| 653 | |a Modules | ||
| 653 | |a Colorectal cancer | ||
| 653 | |a Cellular structure | ||
| 653 | |a Explainable artificial intelligence | ||
| 773 | 0 | |t Journal of Imaging |g vol. 11, no. 12 (2025), p. 448-465 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3286310264/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3286310264/fulltextwithgraphics/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3286310264/fulltextPDF/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |