DESIGN OF A MULTIMODAL AI-BASED INTELLIGENT BLOOD CELL DIAGNOSTIC SYSTEM WITH EDGE-ENHANCED YOLOV8
Keywords:
Blood cell detection, YOLOv8, Multimodal AI, CMEM, Cloud-edge collaboration, System designAbstract
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.References
[1] Rajpurkar P, Chen E, Banerjee O, et al. AI in health and medicine. Nature Medicine, 2022, 28(1): 31-38.
[2] Aggarwal R, Sounderajah V, Martin G, et al. Diagnostic accuracy of deep learning in medical imaging: A systematic review and meta-analysis. NPJ Digital Medicine, 2021, 4: 65.
[3] Matek C, Kerkhoffs T, Marr C, et al. Highly accurate differentiation of bone marrow cell morphologies using deep neural networks on a large image data set. Blood, 2021, 138(20): 1917-1927.
[4] Kouzehkanan Z M, Sadeghian A, Hosseinzadeh M, et al. Raabin-WBC: A large free access dataset of white blood cells images. Medical & Biological Engineering & Computing, 2022, 60: 1427-1443.
[5] Terven J, Córdova-esparza D M, Romero-gonzález J A. A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS. Machine Learning and Knowledge Extraction, 2023, 5(4): 1680-1716.
[6] Van Der Velden B H M, Kuijf H J, Gilhuijs K G A, et al. Explainable artificial intelligence in deep learning-based medical image analysis. Medical Image Analysis, 2022, 79: 102470.
[7] Karargyris A, Umeton R, Sheller M J, et al. Federated benchmarking of medical artificial intelligence with MedPerf. Nature Machine Intelligence, 2023, 5: 799-810.
[8] Wen J, Zhang Z, Lan Y, et al. A survey on federated learning: Challenges and applications. International Journal of Machine Learning and Cybernetics, 2023, 14(2): 513-535.
[9] Gou J, Yu B, Maybank S J, et al. Knowledge distillation: A survey. International Journal of Computer Vision, 2021, 129(6): 1789-1819.
[10] Varoquaux G, Cheplygina V. Machine learning for medical imaging: Methodological failures and recommendations for the future. NPJ Digital Medicine, 2022, 5: 48.