Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing 100084, China.
Biomed Res Int. 2022 Aug 31;2022:8504149. doi: 10.1155/2022/8504149. eCollection 2022.
Often more than one category of lesions in patients' gastrointestinal tracts need to be found in the endoscopic examination. Therefore, there is a need to establish an efficient synchronous real-time computer-aided detection (CADe) system for multicategory lesion detection. This paper proposes to build a system with a multiclass detection model based on the YOLOv5 to detect multicategory lesions synchronously in real-time. Two joint detection CADe systems using multiple single-class detection models with the same structure in parallel or series are established for comparison. A retrospective dataset containing 31117 images from 3747 patients is used in this study. To train the model, various online data augmentation methods and multiple loss functions are used. The proposed CADe system can synchronously detect cancers, gastrointestinal stromal tumours, polyps, and ulcers from different quality input images with 98% precision, 89% recall, and 90.2% mAP. The detection speed is 47 frames per second with a 0.04 s latency on a PC workstation. Compared to the two joint detection CADe systems, the proposed system is more accurate with faster speed and lower latency. Two extra experiments indicated that the lesion detection model based on YOLOv5x could provide better performance than other common YOLO structures and that different accuracy metrics and lesion categories have different requirements for the number of training images. The proposed synchronous real-time CADe system with the multiclass detection model can detect multicategory lesions with high accuracy and speed and low latency on limited hardware. It expands the clinical application of CADe in endoscopy and uses expensive labelled medical images more efficiently than multiple single-category lesion models for joint detection.
在胃肠内窥镜检查中，经常需要发现患者胃肠道中的不止一类病变。因此，需要建立一种有效的多类别病变同步实时计算机辅助检测（CADe）系统。本文提出了一种基于 YOLOv5 的多类别检测模型的系统，用于实时同步检测多类别病变。建立了两个使用相同结构的多类别检测模型的联合检测 CADe 系统，用于并行或串行联合检测。该研究使用了包含 3747 名患者的 31117 张图像的回顾性数据集。为了训练模型，使用了各种在线数据增强方法和多个损失函数。所提出的 CADe 系统可以从不同质量的输入图像中同步检测癌症、胃肠道间质瘤、息肉和溃疡，精度为 98%，召回率为 89%，mAP 为 90.2%。在 PC 工作站上，检测速度为 47 帧/秒，延迟为 0.04 秒。与两个联合检测 CADe 系统相比，该系统具有更高的准确性、更快的速度和更低的延迟。另外两个实验表明，基于 YOLOv5x 的病变检测模型可以提供比其他常见的 YOLO 结构更好的性能，并且不同的准确性指标和病变类别对训练图像的数量有不同的要求。该系统可以在有限的硬件上实现多类别病变的高精度、高速度和低延迟实时同步检测。它扩展了 CADe 在内窥镜检查中的临床应用，并且比多个单类别病变模型的联合检测更有效地利用了昂贵的有标签的医学图像。
