一种针对智能手机拍摄的带有二进制背景网格的CTG纸质报告的有效数字化方法。
An effective digitization method for CTG paper report with binary background grids taken by smartphone.
作者信息
Zhao Zhidong, Liu Zhikang, Si Yingsong, Zhang Yu, Ye Haihui
机构信息
School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou 310018, China.
School of Electronics and Information Engineering, Hangzhou Dianzi University, Hangzhou 310018, China.
出版信息
Comput Methods Programs Biomed. 2021 Mar;200:105872. doi: 10.1016/j.cmpb.2020.105872. Epub 2020 Nov 30.
BACKGROUND AND OBJECTIVE
Cardiotocography (CTG) is the most popular prenatal diagnostic examination, which includes continuous monitoring of foetal heart rate (FHR, bpm) and uterine contraction (UC, mmHg) signals. Compared with CTG paper reports, digitized reports have better storage, transmission and retrieval capabilities, in addition to being able to assess foetal health. However, most of the existing digitization methods extract signals from paper reports with colour background grids, and they cannot extract signals completely from paper reports with binary background grids, which are widely used in clinical CTG monitoring. Moreover, the existing digitization algorithms often neglect the image distortion caused by the imaging equipment.
METHODS
To overcome the above drawbacks, a digitization method for CTG paper reports with binary background grids taken by smartphones is proposed in this paper. In the stage of removing the grid background, a region merger based on super-pixels and an improved binary line mask removal are designed. Then, signal extraction is performed separately according to the different states of the image column. Through a projection map used to synchronize the signal, the distortion effect of the mobile phone is removed.
RESULTS
The experimental results show that the average correlation coefficient (ρ) between the recovery signal obtained by the proposed method and the reference signal is 0.9855±0.0108 for FHR and 0.9866 ± 0.1020 for UC, and the root mean square errors (RMSE) of FHR and UC processed by the proposed method are 1.0366 ± 0.4953 and 2.0355 ± 1.0246, and the mean absolute errors (MAE) of FHR and UC processed by the proposed method are 0.8735 ± 0.0684 and 1.4991 ± 0.2837, which are higher than those of the existing digitization methods. Compared with clinical signals, no significant difference is found in the feature of digitization CTG.
CONCLUSION
The proposed digitization method is a promising useful tool to realize the electronization of CTG signal.
背景与目的
胎心监护（CTG）是最常用的产前诊断检查，包括对胎儿心率（FHR，次/分钟）和子宫收缩（UC，毫米汞柱）信号的持续监测。与CTG纸质报告相比，数字化报告除了能够评估胎儿健康状况外，还具有更好的存储、传输和检索能力。然而，现有的大多数数字化方法是从带有彩色背景网格的纸质报告中提取信号，无法从临床CTG监测中广泛使用的带有二进制背景网格的纸质报告中完全提取信号。此外，现有的数字化算法往往忽略了成像设备引起的图像失真。
方法
为克服上述缺点，本文提出了一种针对智能手机拍摄的带有二进制背景网格的CTG纸质报告的数字化方法。在去除网格背景阶段，设计了基于超像素的区域合并和改进的二进制线条掩码去除方法。然后，根据图像列的不同状态分别进行信号提取。通过用于同步信号的投影图，消除了手机的失真影响。
结果
实验结果表明，所提方法获得的恢复信号与参考信号之间，FHR的平均相关系数（ρ）为0.9855±0.0108，UC的平均相关系数为0.9866±0.1020；所提方法处理的FHR和UC的均方根误差（RMSE）分别为1.0366±0.4953和2.0355±1.0246，平均绝对误差（MAE）分别为0.8735±0.0684和1.4991±0.2837，均高于现有数字化方法。与临床信号相比，数字化CTG的特征无显著差异。
结论
所提数字化方法是实现CTG信号电子化的一种很有前景的有用工具。
Zotero 插件