Advanced Multi-Architecture Deep Learning Framework for BIRADS-Based Mammographic Image Retrieval: Comprehensive Performance Analysis with Super-Ensemble Optimization
By: MD Shaikh Rahman , Feiroz Humayara , Syed Maudud E Rabbi and more
Potential Business Impact:
Finds breast cancer images faster and more accurately.
Content-based mammographic image retrieval systems require exact BIRADS categorical matching across five distinct classes, presenting significantly greater complexity than binary classification tasks commonly addressed in literature. Current medical image retrieval studies suffer from methodological limitations including inadequate sample sizes, improper data splitting, and insufficient statistical validation that hinder clinical translation. We developed a comprehensive evaluation framework systematically comparing CNN architectures (DenseNet121, ResNet50, VGG16) with advanced training strategies including sophisticated fine-tuning, metric learning, and super-ensemble optimization. Our evaluation employed rigorous stratified data splitting (50%/20%/30% train/validation/test), 602 test queries, and systematic validation using bootstrap confidence intervals with 1,000 samples. Advanced fine-tuning with differential learning rates achieved substantial improvements: DenseNet121 (34.79% precision@10, 19.64% improvement) and ResNet50 (34.54%, 19.58% improvement). Super-ensemble optimization combining complementary architectures achieved 36.33% precision@10 (95% CI: [34.78%, 37.88%]), representing 24.93% improvement over baseline and providing 3.6 relevant cases per query. Statistical analysis revealed significant performance differences between optimization strategies (p<0.001) with large effect sizes (Cohen's d>0.8), while maintaining practical search efficiency (2.8milliseconds). Performance significantly exceeds realistic expectations for 5-class medical retrieval tasks, where literature suggests 20-25% precision@10 represents achievable performance for exact BIRADS matching. Our framework establishes new performance benchmarks while providing evidence-based architecture selection guidelines for clinical deployment in diagnostic support and quality assurance applications.
Similar Papers
From ACR O-RADS 2022 to Explainable Deep Learning: Comparative Performance of Expert Radiologists, Convolutional Neural Networks, Vision Transformers, and Fusion Models in Ovarian Masses
CV and Pattern Recognition
Helps doctors find risky cysts better with AI.
Automated Multi-label Classification of Eleven Retinal Diseases: A Benchmark of Modern Architectures and a Meta-Ensemble on a Large Synthetic Dataset
CV and Pattern Recognition
Helps AI learn to spot eye diseases from pictures.
Multi-Attention Stacked Ensemble for Lung Cancer Detection in CT Scans
Image and Video Processing
Helps doctors find lung cancer faster and better.