Integrative Approaches for Breast Cancer Diagnosis through Feature Fusion and Deep Learning Techniques
-
By
-
Varun Malik
-
Tahani Alsubait
-
Mudassir Khan
-
Upasana Lakhina
-
Alaa Menshawi
-
Stuti Mehla
-
Loveleena Mukhija
-
Meteb Altaf
-
Leila Jamel
-
July 21, 2026
Clinical Scorecard: Integrative Approaches for Breast Cancer Diagnosis through Feature Fusion and Deep Learning Techniques
At a Glance
| Category | Detail |
|---|
| Condition | Breast Cancer |
| Key Mechanisms | Multimodal feature fusion using attention-based transformers and lightweight convolutional neural networks. |
| Target Population | Women diagnosed with breast cancer. |
| Care Setting | Clinical diagnostic environments utilizing imaging data. |
Key Highlights
- Proposed model achieves high accuracy (up to 99.438%) on multimodal datasets.
- Utilizes attention-based transformers for effective feature extraction.
- Incorporates modified mantissa search and American zebra optimization algorithms for feature selection.
- Lightweight convolutional neural network ensures real-time application in resource-limited settings.
- Addresses limitations of traditional single-modal imaging systems.
Guideline-Based Recommendations
Diagnosis
- Employ multimodal imaging data for improved breast cancer diagnosis.
Management
- Utilize optimized feature selection and lightweight models for efficient classification.
Monitoring & Follow-up
- Regularly validate model performance on benchmark datasets.
Risks
- Consider the limitations of individual imaging modalities when interpreting results.
Patient & Prescribing Data
Women with varying breast tissue densities and histopathological findings.
Multimodal approaches enhance diagnostic sensitivity and specificity.
Clinical Best Practices
- Integrate multiple imaging modalities for comprehensive assessment.
- Utilize AI and deep learning techniques to support clinical decision-making.
- Focus on feature extraction and selection to improve diagnostic accuracy.
Related Resources & Content
