Aligning deep learning and interpretable models for blood cell classification: A dual-model framework for explainability

Blood smear examination involves classifying cells by morphology under a microscope, a labour-intensive process prone to subjective variation. Recent deep learning models achieve strong performance in blood cell classification but remain as "black boxes", offering little clinical transparency. We propose a dual-model framework that pairs a deep YOLO (You Only Look Once) classifier with a shallow, interpretable explainer. YOLO performs classification and segmentation, while clinically informed features are extracted from segmented images to train the explainer on YOLO predictions. SHapley Additive exPlanations (SHAP) quantify feature importance, with discrepancies flagged as "other reasons" to enhance transparency. Evaluated on proprietary and public datasets (PBC, Raabin), YOLO achieved AUCs of 0.997, 0.994, and 1.000 respectively, with the explainer demonstrating strong alignment: Score-CAM activation maps agreed with SHAP-identified features. In a user study with 9 trained and qualified haematologists and laboratory medical technologists, predictions achieved 96.9% concurrence. This work shows that the coupling of deep learning with interpretable models improves the confidence of predictions while providing clinical meaningful insights.