Department of Pharmacy, The Third Affiliated Hospital of Southern Medical University, Guangzhou, 510000, China.
BMC Med Inform Decis Mak. 2021 Nov 22;21(1):324. doi: 10.1186/s12911-021-01691-8.
The correct identification of pills is very important to ensure the safe administration of drugs to patients. Here, we use three current mainstream object detection models, namely RetinaNet, Single Shot Multi-Box Detector (SSD), and You Only Look Once v3(YOLO v3), to identify pills and compare the associated performance.
In this paper, we introduce the basic principles of three object detection models. We trained each algorithm on a pill image dataset and analyzed the performance of the three models to determine the best pill recognition model. The models were then used to detect difficult samples and we compared the results.
The mean average precision (MAP) of RetinaNet reached 82.89%, but the frames per second (FPS) is only one third of YOLO v3, which makes it difficult to achieve real-time performance. SSD does not perform as well on the indicators of MAP and FPS. Although the MAP of YOLO v3 is slightly lower than the others (80.69%), it has a significant advantage in terms of detection speed. YOLO v3 also performed better when tasked with hard sample detection, and therefore the model is more suitable for deployment in hospital equipment.
Our study reveals that object detection can be applied for real-time pill identification in a hospital pharmacy, and YOLO v3 exhibits an advantage in detection speed while maintaining a satisfactory MAP.
正确识别药丸对于确保患者安全用药非常重要。在这里，我们使用了三种当前主流的目标检测模型，即 RetinaNet、Single Shot Multi-Box Detector（SSD）和 You Only Look Once v3（YOLO v3）来识别药丸，并比较相关性能。
在本文中，我们介绍了三种目标检测模型的基本原理。我们在药丸图像数据集上训练了每个算法，并分析了三种模型的性能，以确定最佳的药丸识别模型。然后，我们使用这些模型来检测困难样本，并比较结果。
RetinaNet 的平均准确率（MAP）达到了 82.89%，但每秒帧数（FPS）仅为 YOLO v3 的三分之一，这使得它难以实现实时性能。SSD 在 MAP 和 FPS 等指标上的表现也不是很好。虽然 YOLO v3 的 MAP 略低于其他模型（80.69%），但它在检测速度方面具有显著优势。YOLO v3 在进行困难样本检测时表现也更好，因此该模型更适合部署在医院设备中。
我们的研究表明，目标检测可用于医院药房的实时药丸识别，而 YOLO v3 在保持满意的 MAP 的同时，在检测速度方面具有优势。
