Leveraging deep learning and explainable AI for effective liver tumor classification from CT scan images
-
By
-
Meshal Alfarhood
-
Shatha Alotaibi
-
Aows Abuhaimed
-
Abdalrahman Alalwan
-
June 2, 2026
-
Objective:
To develop a comprehensive deep learning framework for non-invasive liver tumor classification with integrated explainability.
Key Findings:
- The EfficientNetV2 model achieved 96.97% accuracy.
- The framework integrates explainable AI methods to enhance interpretability and clinical trust.
Interpretation:
Limitations:
- The study does not address the scalability of the proposed methods across diverse datasets.
- Limited exploration of the integration of additional imaging modalities.
Conclusion:
The study presents a novel approach to liver tumor classification that combines high accuracy with interpretability.
