College of Mathematics and Informatics, South China Agricultural University, Guangzhou, 510642, China.
Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area, Shenzhen Polytechnic University, Shenzhen, 518055, China.
Sci Rep. 2024 Nov 19;14(1):28658. doi: 10.1038/s41598-024-79969-w.
Accurate and efficient detection and segmentation of the urine formed element plays a vital role in the clinical diagnosis and treatment of many diseases, such as urinary system diseases, kidney diseases, and other diseases. However, artificial microscopy is subjective, and time- consuming. The mainstream detection and instance segmentation algorithms lack adequate accuracy and speed for the urine formed element due to small and dense targets. Therefore, this study proposes a quick one-stage urine formed element instance segmentation model based on YOLOv5n. The approach first employs a backbone architecture to extract features named shallow graphical features and semantic features from urine cells. Next, the neck network combines shallow graphical features with different deep semantic features, obtaining multi-scale, and multi-level features. Finally, according to these multi-level features, the head network of YOLOv5n integrates a small FCN network into the YOLOv5 detector. It obtains the location, classification, and segmentation results of the targets. To validate the superiority of this approach in terms of speed and accuracy, a special urine formed element dataset including 500 images was created. Experimental results show that the YOLOv5n method achieves a Mean Average Precision (mAP) at intersection over the union threshold of 0.5 (mAP50) with 91.8%, and Frames Per Second (FPS) of 63.3. Compared to Mask R-CNN and YOLOv8, its FPS increased by 62.6 and 60.9, respectively, resulting in nearly a hundred-fold speedup, and its mAP50 also increased by 3.6 and 1.4% points in accuracy, respectively. Additionally, the YOLOv5n obtains a superior balance of accuracy and speed in comparisons with SOLOv2, BoxInst, and ConvNeXt V2. This study developed a new automated analysis of urinary particles based on deep learning, and this method is expected to be used for the automated analysis and detection of the urine formed element. The experimental results also demonstrate that YOLOv5n can achieve more accurate and faster instance segmentation of urine formed element, providing technical support for clinical disease diagnosis.
准确、高效地检测和分割尿液形成元素在许多疾病的临床诊断和治疗中起着至关重要的作用，如泌尿系统疾病、肾脏疾病等。然而，人工显微镜检查具有主观性和耗时性。主流的检测和实例分割算法由于目标小而密集，缺乏足够的准确性和速度。因此，本研究提出了一种基于 YOLOv5n 的快速尿液形成元素实例分割模型。该方法首先使用骨干架构从尿液细胞中提取特征，称为浅层图形特征和语义特征。然后，颈部网络将浅层图形特征与不同的深层语义特征相结合，获得多尺度、多层次的特征。最后，根据这些多层次的特征，YOLOv5n 的头部网络将一个小型 FCN 网络集成到 YOLOv5 探测器中。它得到目标的位置、分类和分割结果。为了验证该方法在速度和准确性方面的优越性，创建了一个包含 500 张图像的特殊尿液形成元素数据集。实验结果表明，YOLOv5n 方法在交并比阈值为 0.5 时的平均精度（mAP）为 91.8%，帧率（FPS）为 63.3。与 Mask R-CNN 和 YOLOv8 相比，其 FPS 分别提高了 62.6%和 60.9%，速度提高了近百倍，精度也分别提高了 3.6%和 1.4%。此外，YOLOv5n 在与 SOLOv2、BoxInst 和 ConvNeXt V2 的比较中，在准确性和速度之间取得了更好的平衡。本研究基于深度学习开发了一种新的尿液颗粒自动分析方法，该方法有望用于尿液形成元素的自动分析和检测。实验结果还表明，YOLOv5n 可以实现更准确、更快的尿液形成元素实例分割，为临床疾病诊断提供技术支持。
