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
-
Clinical Scorecard: Utilizing deep learning and interpretable AI for accurate classification of liver tumors in CT imaging
At a Glance
| Category | Detail |
|---|
| Condition | |
| Key Mechanisms | Deep learning frameworks for non-invasive tumor classification with explainability. |
| Target Population | |
| Care Setting | |
Key Highlights
- Liver cancer is the fifth most prevalent cancer in men and ninth in women.
- EfficientNetV2 model achieved 96.97% accuracy in liver tumor classification.
- Integration of explainable AI methods enhances interpretability and clinical trust.
- Conventional biopsy methods are invasive and time-consuming.
Guideline-Based Recommendations
Diagnosis
- Utilize automated deep learning frameworks for non-invasive liver tumor classification.
Management
- Incorporate explainable AI techniques to improve clinical decision-making.
Monitoring & Follow-up
- Regular evaluation of model performance and accuracy in clinical settings.
Risks
- Invasive biopsy procedures carry procedural risks and patient discomfort.
Patient & Prescribing Data
Automated classification may reduce the need for invasive diagnostic procedures.
Clinical Best Practices
- Adopt deep learning models to enhance diagnostic accuracy in liver cancer.
Related Resources & Content
