A Novel Context-Aware Feature Pyramid Networks With Kolmogorov-Arnold Modeling and XAI Framework for Robust Lung Cancer Detection
The present work describes a new method for detecting lung cancer based on a Kolmogorov-Arnold Network (KAN) combined with a Context-Aware Feature Pyramid Network (FPN), denoted KAFPN and supported by XAI tools, including Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive ex...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11005971/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The present work describes a new method for detecting lung cancer based on a Kolmogorov-Arnold Network (KAN) combined with a Context-Aware Feature Pyramid Network (FPN), denoted KAFPN and supported by XAI tools, including Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) for explanation purposes. The model is compiled based on an extended corpus containing 25,000 histopathological images from 15,000 lung tissue samples. The proposed KAFPN model outperformed the traditional models, such as Base CNN, Inception V3, VGG16, ResNet50, EfficientNet-B7, ResNet-101, and DenseNet-121, based on testing and validation accuracy of 99.63% and 99.60%, respectively. The integration of LIME and SHAP facilitated an advanced level of interpretability by providing detailed visual explanations of the model’s predictive decisions, delineating the image regions that most significantly impacted the decision-making process. The proposed KAFPN framework is well-suited for image segmentation and object detection because it has multiple-scale feature responses. Stringent data augmentation and correct division of data sets make the model robust and efficient for real-world applications. |
|---|---|
| ISSN: | 2169-3536 |