Tanaka Rie, Nozaki Shiho, Goshima Futa, Shiraishi Junji
Kanazawa University, College of Medical, Pharmaceutical and Health Sciences, Kanazawa, Japan.
Kanazawa University, Graduate School of Health Sciences, Kanazawa, Japan.
J Med Imaging (Bellingham). 2022 Jan;9(1):015501. doi: 10.1117/1.JMI.9.1.015501. Epub 2022 Jan 18.
The necessity of image retakes is initially determined on a preview monitor equipped with an operating system; therefore, some image blurring is only noticed later, on a high-resolution monitor. The purpose of this study is to investigate blur detection performance on radiographs via a deep learning approach compared with human observers. A total of 99 radiographs (blurry 57, nonblurry 42) were independently observed and rated by six observers using preview and diagnostic liquid crystal displays (LCDs). The deep convolution neural network (DCNN) was trained and tested using ninefold cross-validation. The average areas under the ROC curves (AUCs) were calculated for each observer with LCDs and by stand-alone DCNN for each test session and then statistically tested using a 95% confidence interval. The average AUCs were 0.955 for stand-alone DCNN and 0.827 and 0.947 for human observers using preview and diagnostic LCDs, respectively. The DCNN revealed a high performance for image motion blur on digital radiographs (sensitivity 94.8%, specificity 96.8%, and accuracy 95.6%), along with the capability to detect a slight motion blur that was overlooked by human observers with a preview LCD. There were no cases of motion blur overlooked by the stand-alone DCNN, of which some were incorrectly recognized as nonblurry by human observers. The deep learning-based approach was capable of distinguishing slight motion blur that was unnoticeable on a preview LCD, and thus, is expected to aid the human visual system for detecting blurred images in the initial review of digital radiographs.
图像重拍的必要性最初是在配备操作系统的预览监视器上确定的；因此，一些图像模糊只是在后来在高分辨率监视器上才被注意到。本研究的目的是通过深度学习方法与人类观察者相比，研究X线照片上的模糊检测性能。共有99张X线照片（模糊的57张，不模糊的42张）由6名观察者使用预览和诊断液晶显示器（LCD）独立观察并评级。使用九折交叉验证对深度卷积神经网络（DCNN）进行训练和测试。计算每个观察者使用LCD以及每个测试会话中独立DCNN的ROC曲线下平均面积（AUC），然后使用95%置信区间进行统计测试。独立DCNN的平均AUC为0.955，使用预览和诊断LCD的人类观察者的平均AUC分别为0.827和0.947。DCNN在数字X线照片上显示出对图像运动模糊的高性能（灵敏度94.8%，特异性96.8%，准确性95.6%），同时能够检测到人类观察者使用预览LCD时忽略的轻微运动模糊。独立DCNN没有遗漏运动模糊的情况，其中一些被人类观察者错误地识别为不模糊。基于深度学习的方法能够区分在预览LCD上不易察觉的轻微运动模糊，因此，有望在数字X线照片的初步审查中辅助人类视觉系统检测模糊图像。
