In this work, the related risk factors and perinatal outcomes of pregnant women with gestational diabetes mellitus (GDM) were analyzed based on color Doppler ultrasound (CDU) diagnosis. Backpropagation (BP) algorithm-based CDU imaging algorithm (BPC) was constructed in this study and applied in CDU images of 80 pregnant women with GDM. Besides, amplitude and phase estimation (APES) and low-complexity adaptive beam (LCA) algorithms were introduced for comparison with BPC in turn. It was found that Dice similarity coefficient (96.44%), sensitivity (95.45%), and specificity (91.56%) of BPC were greater than those of APES (83.97%, 85.84%, 78.45%) and LCA (84.74%, 86.29%, 82.35%), while its running time (6.44 ± 1.39 s) was shorter than that of APES (11.87 ± 2.41 s) and LCA (13.76 ± 1.54 s) (). Pregnant women in the experimental group (group B) were older than those in the control group (group A) (). The pulsatility index (PI) and renal artery resistance index (RI) of fetuses in group B (0.95 ± 0.15) were higher than those of group A (0.57 ± 0.24) (). In addition, pregnancy age, family history of hypertension, and abortion history were positively correlated with GDM (). In conclusion, BPC could not only improve diagnosis accuracy in fetuses’ CDU images but also shorten calculation time. Pregnancy age, family history of hypertension, and abortion history were the related risk factors for GDM in pregnant women.

中文翻译：

---

基于反向传播神经网络算法的彩色多普勒超声检测妊娠期糖尿病和围产期结局

在这项工作中，基于彩色多普勒超声（CDU）诊断分析妊娠期糖尿病（GDM）孕妇的相关危险因素和围产期结局。本研究构建了基于反向传播 (BP) 算法的 CDU 成像算法 (BPC)，并将其应用于 80 名 GDM 孕妇的 CDU 图像。此外，依次引入幅度和相位估计（APES）和低复杂度自适应波束（LCA）算法与BPC进行比较。发现BPC的Dice相似系数（96.44%）、敏感性（95.45%）和特异性（91.56%）均大于APES（83.97%、85.84%、78.45%）和LCA（84.74%、86.29%） , 82.35%), 而其运行时间 (6.44 ± 1.39 s) 短于 APES (11.87 ± 2.41 s) 和 LCA (13.76 ± 1.54 s) (）。实验组（B组）孕妇年龄大于对照组（A组）（）。B组胎儿搏动指数（PI）和肾动脉阻力指数（RI）（0.95±0.15）高于A组（0.57±0.24）（）。此外，孕龄、高血压家族史、流产史与GDM呈正相关。）。总之，BPC不仅可以提高胎儿CDU图像的诊断准确性，还可以缩短计算时间。孕龄、高血压家族史和流产史是孕妇发生GDM的相关危险因素。