Abstract: In recent years, the breakthrough development of artificial intelligence technology has promoted a paradigm change in the interdisciplinary field of medicine and engineering, among which the object detection algorithm based on deep learning has shown significant advantages in medical image analysis. As a typical representative of the single-stage detection framework, the YOLO ( You Only Look Once ) series algorithms have demonstrated the unique advantages of high real-time, strong generalization ability and precise positioning in the field of medical image analysis through the "end-to-end" detection paradigm, and have gradually become the mainstream research methods for lesion detection, cell recognition and other tasks. Firstly, based on the dimension of algorithm architecture innovation, the core evolution path of 12 generations of basic algorithms from YOLO v1 to YOLO v11 was sorted out, and the improvement breakthroughs, advantages and limitations, and medical scene performance of each version of YOLO were compared and analyzed. Secondly, the classic open-source datasets in the field of medical object detection are summarized, and the commonly used evaluation indicators in object detection are expounded. At the same time, the literature research on the use of YOLO improved algorithm in the detection of cervical cells, blood cells, pulmonary nodules and diabetic retinopathy in 2D medical images was reviewed, and the different improved methods were comprehensively compared and analyzed. Finally, this paper summarizes the medical scenarios corresponding to different improvement ideas of YOLO, and discusses the challenges and future development directions in this field.

Key words: deep learning, object detection, YOLO, detection of cervical cells, detection of blood cells, detection of pulmonary nodules, detection of diabetic retinopathy

摘要： 近年来，人工智能技术的突破性发展推动了医工交叉领域的范式变革，其中基于深度学习的目标检测算法在医学图像分析中展现出显著优势。作为单阶段检测框架的典型代表，YOLO（You Only Look Once）系列算法通过“端到端”的检测范式，在医学影像分析领域展现出高实时性、强泛化能力和精准定位的独特优势，现逐渐成为病灶检测、细胞识别等任务的主流研究方法。针对YOLO改进算法在医学目标检测研究进行梳理，首先，基于算法架构创新维度，整理了从YOLO v1到YOLO v11共12代基础算法的核心演进路径，并深入对比分析各版本YOLO的改进突破、优势与局限性、医学场景表现；其次，归纳了医学目标检测领域中的经典开源数据集，阐述了目标检测中常用的评价指标；同时，重点综述了YOLO改进算法在2D医学图像的宫颈细胞检测、血细胞检测、肺结节检测和糖尿病视网膜病变检测的文献研究，并对不同改进方法进行综合对比分析；最后，总结YOLO不同改进思想相对应的医用场景，并讨论指出该领域面临的挑战与未来发展方向。

关键词: 深度学习, 目标检测, YOLO, 宫颈细胞检测, 血细胞检测, 肺结节检测, 糖尿病视网膜病变检测