DESIGN OF A MULTIMODAL AI-BASED INTELLIGENT BLOOD CELL DIAGNOSTIC SYSTEM WITH EDGE-ENHANCED YOLOV8

This study presents a practical design for an intelligent blood cell diagnostic system that integrates microscopic images, clinical text, and an edge-enhanced YOLOv8 detector. The scheme addresses the low efficiency, subjective variation, and limited specialist resources associated with manual blood-smear review. A standardized multimodal dataset is organized around normal and abnormal red blood cells, white blood cells, and platelets. The detection backbone is strengthened with a cell morphology feature enhancement module, weighted bidirectional feature fusion, and a combined localization and classification loss to improve recognition under cell overlap, uneven staining, and blurred boundaries. A PySide6 interface, FastAPI service, SQLite database, and cloud-edge collaborative workflow support image, batch, video, and camera-based analysis. The available training curves, bounding-box distribution, detection visualization, and recall-confidence results are used as feasibility evidence without adding unsupported experimental claims. The resulting design provides a modular route for efficient blood cell screening and can be transferred to bacterial examination, urinary sediment analysis, and sperm quality assessment through dataset and output-layer adaptation.