To develop a robust computer-aided diagnostic system for the accurate detection of Acute Lymphoblastic Leukemia (ALL) using an ensemble of deep learning models optimized with the Fast Osprey Algorithm.
Key Findings:
The FOO-Ensemble framework achieved an accuracy of 97.76%, precision of 98.13%, recall of 97.71%, and F1-score of 97.83%.
The ensemble approach reduced inference time compared to standalone models.
The proposed system demonstrated resilience, scalability, and exceptional generalization capabilities.
Interpretation:
The study highlights the effectiveness of combining deep learning ensembles with bio-inspired optimization techniques for reliable detection of ALL, potentially improving diagnostic processes in clinical settings.
Limitations:
The study may be limited by the quality and diversity of the datasets used for training and validation.
Further validation in real-world clinical settings is necessary to confirm the findings.
Conclusion:
The FOO-Ensemble framework presents a scalable and reliable CAD model for assisting hematopathologists in diagnosing ALL, which could lead to improved patient outcomes.
