当前位置: X-MOL 学术Med. Biol. Eng. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Automated measurement network for accurate segmentation and parameter modification in fetal head ultrasound images
Medical & Biological Engineering & Computing ( IF 3.2 ) Pub Date : 2020-09-25 , DOI: 10.1007/s11517-020-02242-5
Peixuan Li 1, 2, 3, 4, 5 , Huaici Zhao 1, 2, 4, 5 , Pengfei Liu 1, 2, 3, 4, 5 , Feidao Cao 1, 2, 3, 4, 5
Affiliation  

Measurement of anatomical structures from ultrasound images requires the expertise of experienced clinicians. Moreover, there are artificial factors that make an automatic measurement complicated. In this paper, we aim to present a novel end-to-end deep learning network to automatically measure the fetal head circumference (HC), biparietal diameter (BPD), and occipitofrontal diameter (OFD) length from 2D ultrasound images. Fully convolutional neural networks (FCNNs) have shown significant improvement in natural image segmentation. Therefore, to overcome the potential difficulties in automated segmentation, we present a novelty FCNN and add a regression branch for predicting OFD and BPD in parallel. In the segmentation branch, a feature pyramid inside our network is built from low-level feature layers for a variety of fetal head in ultrasound images, which is different from traditional feature pyramid building methods. In order to select the most useful scale and reduce scale noise, attention mechanism is taken for the feature’s filter. In the regression branch, for the accurate estimation of OFD and BPD length, a new region of interest (ROI) pooling layer is proposed to extract the elliptic feature map. We also evaluate the performance of our method on large dataset: HC18. Our experimental results show that our method can achieve better performance than the existing fetal head measurement methods.



中文翻译:

用于准确分割和修改胎头超声图像参数的自动化测量网络

从超声图像测量解剖结构需要经验丰富的临床医生的专业知识。此外,还有一些人为因素使自动测量变得复杂。在本文中,我们旨在提出一种新颖的端到端深度学习网络,以从 2D 超声图像中自动测量胎儿头围 (HC)、双顶径 (BPD) 和枕额径 (OFD) 长度。全卷积神经网络 (FCNN) 在自然图像分割方面表现出显着改进。因此,为了克服自动分割中的潜在困难,我们提出了一种新颖的 FCNN 并添加了一个回归分支来并行预测 OFD 和 BPD。在细分分支中,我们网络内部的特征金字塔是由超声图像中各种胎头的低级特征层构建的,这与传统的特征金字塔构建方法不同。为了选择最有用的尺度并减少尺度噪声,特征的过滤器采用了注意力机制。在回归分支中,为了准确估计OFD和BPD长度,提出了一个新的感兴趣区域(ROI)池化层来提取椭圆特征图。我们还评估了我们的方法在大型数据集 HC18 上的性能。我们的实验结果表明,我们的方法可以取得比现有胎头测量方法更好的性能。对特征的过滤器采用注意机制。在回归分支中,为了准确估计OFD和BPD长度,提出了一个新的感兴趣区域(ROI)池化层来提取椭圆特征图。我们还评估了我们的方法在大型数据集 HC18 上的性能。我们的实验结果表明,我们的方法可以取得比现有胎头测量方法更好的性能。对特征的过滤器采用注意机制。在回归分支中,为了准确估计OFD和BPD长度,提出了一个新的感兴趣区域(ROI)池化层来提取椭圆特征图。我们还评估了我们的方法在大型数据集 HC18 上的性能。我们的实验结果表明,我们的方法可以取得比现有胎头测量方法更好的性能。

更新日期:2020-10-14
down
wechat
bug