shadjee/WBC_UGDC: WBC_UGDE
Abstract
This project implements a Deep Ensemble of CNN models (MobileNetV3, EfficientNet-B0, ShuffleNetV2) integrated with Monte Carlo Dropout and Conformal Prediction (ICP) to achieve accurate, reliable, and interpretable white blood cell subtype classification. The framework provides uncertainty quantification, calibrated predictions, and Grad-CAM-based visual explanations, enabling trustworthy AI deployment in clinical hematology diagnostics. README.md
Fields of Study & Subjects
Digital Imaging for Blood Diseases
Advanced Neural Network Applications
Cell Image Analysis Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 4 March 2026
- Language
- EN