Department of Radiology, The Second Affiliated Hospital of Chongqing Medical University, Yuzhong, Chongqing, China.
Eur Radiol Exp. 2024 Sep 20;8(1):107. doi: 10.1186/s41747-024-00504-7.
To explore an artificial intelligence (AI) technology employing YOLOv8 for quality control (QC) on elbow joint radiographs.
From January 2022 to August 2023, 2643 consecutive elbow radiographs were collected and randomly assigned to the training, validation, and test sets in a 6:2:2 ratio. We proposed the anteroposterior (AP) and lateral (LAT) models to identify target detection boxes and key points on elbow radiographs using YOLOv8. These identifications were transformed into five quality standards: (1) AP elbow positioning coordinates (X and Y); (2) olecranon fossa positioning distance parameters (S and S); (3) key points of joint space (Y, Y, Y and Y); (4) LAT elbow positioning coordinates (X and Y); and (5) flexion angle. Models were trained and validated using 2,120 radiographs. A test set of 523 radiographs was used for assessing the agreement between AI and physician and to evaluate clinical efficiency of models.
The AP and LAT models demonstrated high precision, recall, and mean average precision for identifying boxes and points. AI and physicians showed high intraclass correlation coefficient (ICC) in evaluating: AP coordinates X (0.987) and Y (0.991); olecranon fossa parameters S (0.964) and S (0.951); key points Y (0.998), Y (0.997), Y (0.998) and Y (0.959); LAT coordinates X (0.994) and Y (0.986); and flexion angle (0.865). Compared to manual methods, using AI, QC time was reduced by 43% for AP images and 45% for LAT images (p < 0.001).
YOLOv8-based AI technology is feasible for QC of elbow radiography with high performance.
This study proposed and validated a YOLOv8-based AI model for automated quality control in elbow radiography, obtaining high efficiency in clinical settings.
QC of elbow joint radiography is important for detecting diseases. Models based on YOLOv8 are proposed and perform well in image QC. Models offer objective and efficient solutions for QC in elbow joint radiographs.
探索一种使用 YOLOv8 进行肘部关节 X 光片质量控制（QC）的人工智能（AI）技术。
2022 年 1 月至 2023 年 8 月，连续收集了 2643 例肘部 X 光片，并以 6:2:2 的比例随机分配到训练集、验证集和测试集中。我们提出了前后（AP）和侧位（LAT）模型，使用 YOLOv8 识别肘部 X 光片中的目标检测框和关键点。这些识别结果被转化为五个质量标准：（1）AP 肘部定位坐标（X 和 Y）；（2）鹰嘴窝定位距离参数（S 和 S）；（3）关节间隙关键点（Y、Y、Y 和 Y）；（4）LAT 肘部定位坐标（X 和 Y）；（5）弯曲角度。使用 2120 张 X 光片对模型进行训练和验证。使用 523 张 X 光片的测试集评估 AI 和医生之间的一致性，并评估模型的临床效率。
AP 和 LAT 模型在识别框和点方面表现出高精度、高召回率和平均准确率。AI 和医生在评估 AP 坐标 X（0.987）和 Y（0.991）、鹰嘴窝参数 S（0.964）和 S（0.951）、关键点 Y（0.998）、Y（0.997）、Y（0.998）和 Y（0.959）、LAT 坐标 X（0.994）和 Y（0.986）以及弯曲角度（0.865）方面具有较高的组内相关系数（ICC）。与手动方法相比，使用 AI 可将 AP 图像的 QC 时间减少 43%，LAT 图像的 QC 时间减少 45%（均 P<0.001）。
基于 YOLOv8 的 AI 技术在肘部 X 光片 QC 中具有高性能，是可行的。
本研究提出并验证了一种基于 YOLOv8 的 AI 模型，用于肘部 X 光片的自动质量控制，在临床环境中具有高效率。
肘部关节 X 光片的 QC 对于检测疾病很重要。基于 YOLOv8 的模型被提出并在图像 QC 中表现良好。这些模型为肘部关节 X 光片的 QC 提供了客观、高效的解决方案。
