Graduate School of Health Sciences, Hokkaido University, Kita-12, Nishi-5, Kita-ku, Sapporo, 060-0812, Japan.
Department of Radiological Technology, Kurashiki Central Hospital, 1-1-1 Miwa, Kurashiki, Okayama, 710-8602, Japan.
Phys Eng Sci Med. 2022 Sep;45(3):835-845. doi: 10.1007/s13246-022-01153-z. Epub 2022 Jul 6.
Consistent cross-sectional imaging is desirable to accurately detect lesions and facilitate follow-up in head computed tomography (CT). However, manual reformation causes image variations among technologists and requires additional time. We therefore developed a system that reformats head CT images at the orbitomeatal (OM) line and evaluated the system performance using real-world clinical data. Retrospective data were obtained for 681 consecutive patients who underwent non-contrast head CT. The datasets were randomly divided into one of three sets for training, validation, or testing. Four landmarks (bilateral eyes and external auditory canal) were detected with the trained You Look Only Once (YOLO)v5 model, and the head CT images were reformatted at the OM line. The precision, recall, and mean average precision at the intersection over union threshold of 0.5 were computed in the validation sets. The reformation quality in testing sets was evaluated by three radiological technologists on a qualitative 4-point scale. The precision, recall, and mean average precision of the trained YOLOv5 model for all categories were 0.688, 0.949, and 0.827, respectively. In our environment, the mean implementation time was 23.5 ± 2.4 s for each case. The qualitative evaluation in the testing sets showed that post-processed images of automatic reformation had clinically useful quality with scores 3 and 4 in 86.8%, 91.2%, and 94.1% for observers 1, 2, and 3, respectively. Our system demonstrated acceptable quality in reformatting the head CT images at the OM line using an object detection algorithm and was highly time efficient.
理想情况下，应进行一致性的横截面成像，以准确检测病变并便于头部计算机断层扫描 (CT) 随访。然而，手动重建会导致技术人员之间的图像差异，并需要额外的时间。因此，我们开发了一种在眶耳线（OM）重建成像头部 CT 图像的系统，并使用真实临床数据评估了系统性能。回顾性地获得了 681 例连续行非对比头部 CT 的患者数据。数据集随机分为训练集、验证集或测试集。使用训练好的 You Look Only Once (YOLO)v5 模型检测到四个标志点（双侧眼睛和外耳道口），并在 OM 线处重建成像头部 CT 图像。在验证集中计算了精度、召回率和在交并比阈值为 0.5 时的平均精度。在测试集中，三位放射技术人员使用定性 4 分制评估重建成像质量。训练好的 YOLOv5 模型对所有类别的精度、召回率和平均精度分别为 0.688、0.949 和 0.827。在我们的环境中，每个病例的平均实施时间为 23.5 ± 2.4 秒。测试集中的定性评估显示，自动重建成像的后处理图像具有临床有用的质量，观察者 1、2 和 3 的评分分别为 3 分和 4 分，占 86.8%、91.2%和 94.1%。我们的系统使用目标检测算法在 OM 线重建成像头部 CT 图像的质量可接受，并且非常高效。
