2021 Recognition of Fetal Facial Ultrasound Standard Plane Based on Texture Feature Fusion

基于纹理特征融合的胎儿面部超声标准平面识别

摘要

简介

挑战

传统手工的图像识别和分类步骤

摘要

在产前超声诊断过程中，胎儿面部超声标准平面（FFUSP）的准确识别对于准确的面部畸形检测和疾病筛查，如唇腭裂检测和唐氏综合征筛查检查至关重要。

因此，在本研究中，我们提出了一种自动识别和分类的纹理特征融合方法（LH-SVM）。

首先提取图像的纹理特征，包括局部二进制模式（LBP）和定向梯度直方图（HOG），然后进行特征融合，最后采用支持向量机（SVM）进行预测分类。

在我们的研究中，我们使用妊娠20~24周的胎儿面部超声图像作为实验数据，共获得943张标准平面图像（眼轴平面221个，正中矢状面298个，鼻唇冠状面424个，350个非标准平面，OAP、MSP、NCP、N-SP）。基于这一数据集，我们进行了5倍交叉验证。最终测试结果表明，该方法对FFUSP分类的准确率为94.67%，平均准确率为94.27%，平均召回率为93.88%，平均F1得分为94.08%。实验结果表明，纹理特征融合方法能够有效地预测FFUSP和分类，为临床研究自动检测FFUSP的方法提供了必要的依据。

图1：FFUSP(a)OAP图像，其中CL代表晶状体，EB代表眼球；(b) MSP，FB代表额骨，NB代表鼻骨，AN代表鼻尖，LJ代表下颌骨；(c)NCP，AN代表鼻尖，NC代表鼻柱，Nos代表鼻孔，UL代表上唇，LL代表下唇，MD代表下颌骨

FFUSP由三个基本平面组成（图1）：眼轴向平面（OAP）、中位矢状面（MSP）和鼻唇冠状面（NCP）。

简介

虽然胎儿面部部位较普通图像发育较晚，但FFUSP是观察胎儿面部轮廓和筛选各种胎儿唇裂的良好平面。

FFUSP显示许多唇和面部异常。

因此，超声医生可以根据FFUSP图像评估胎儿的面部轮廓，并通过测量相关参数[8,9]来筛查和诊断鼻、唇、眼等面部结构异常。

针对胎儿的标准临床平面制定了适用的规范，应用[4,12,13]改进了胎儿异常的产前诊断，为胎儿异常产前筛查的标准化培训和质量控制奠定了基础。

挑战

1.小类间的差异和大类内差异获得的各种平面[14,15]

2.超声图像的成像原理使超声图像具有高噪声和低对比度的[16,17]

3.由于不同的操作人员、不同的扫描角度和尺度所引起的噪声或阴影，超声图像特征难以区分[18]

传统手工的图像识别和分类步骤

[19–22]

1.特征提取

2.特征编码

3.特征分类

References

[1] American Institute of Ultrasound in Medicine, “AIUM prac

tice guideline for the performance of obstetric ultrasound

examinations,” Journal of Ultrasound in Medicine, vol. 29,

no. 1, pp. 157–166, 2010.

[2] C. Baumgartner, K. Kamnitsas, J. Matthew et al., “SonoNet:

real-time detection and localisation of fetal standard scan

planes in freehand ultrasound,” IEEE Transactions on Medical

Imaging, vol. 36, no. 11, pp. 2204–2215, 2017.

[3] R. Qu, G. Xu, C. Ding, W. Jia, and M. Sun, “Standard plane

identifification in fetal brain ultrasound scans using a difffferen

tial convolutional neural network,” IEEE Access, vol. 8,

pp. 83821–83830, 2020.

[4] H. Shun-Li, “Standardized analysis of ultrasound screening

section in mid pregnancy fetus,” World Latest Medicine Infor

mation, vol. 18, no. 70, pp. 33-34, 2018.

[5] A. Namburete, R. V. Stebbing, B. Kemp, M. Yaqub, A. T. Papa

georghiou, and J. Alison Noble, “Learning-based prediction of

gestational age from ultrasound images of the fetal brain,”

Medical Image Analysis, vol. 21, no. 1, pp. 72–86, 2015.

[6] B. Rahmatullah, A. Papageorghiou, and J. A. Noble, “Auto

mated selection of standardized planes from ultrasound vol

ume,” in Machine Learning in Medical Imaging, K. Suzuki, F.

Wang, D. Shen, and P. Yan, Eds., vol. 7009 of Lecture Notes

in Computer Science, pp. 35–42, Springer, Berlin, Heidelberg,

2011.

[7] M. Yaqub, B. Kelly, A. T. Papageorghiou, and J. A. Noble, “A

deep learning solution for automatic fetal neurosonographic

diagnostic plane verifification using clinical standard con

straints,” Ultrasound in Medicine and Biology, vol. 43, no. 12,

pp. 2925–2933, 2017.

[8] S. Li and H. Wen, “Fetal anatomic ultrasound sections and

their values in the second trimester of pregnancy,” Chinese

Journal of Medical Ultrasound (Electronic Edition), vol. 7,

no. 3, pp. 366–381, 2010.

[9] L. I. Shengli and W. E. N. Huaxuan, “Fetal anatomic ultra

sound sections and their values in the second trimester of

Computational and Mathematical Methods in Medicinepregnancy (continued)[J],” Chinese Journal of Medical Ultra

sound (Electronic Edition), vol. 7, no. 4, pp. 617–643, 2010.

[10] R. Deter, J. Li, W. Lee, S. Liu, and R. Romero, “Quantitative

assessment of gestational sac shape: the gestational sac shape

score,” Ultrasound in Obstetrics and Gynecology, vol. 29,

no. 5, pp. 574–582, 2007.

[11] L. Zhang, S. Chen, C. T. Chin, T. Wang, and S. Li, “Intelligent

scanning: automated standard plane selection and biometric

measurement of early gestational sac in routine ultrasound

examination,” Medical Physics, vol. 39, no. 8, pp. 5015–5027,

2012.

[12] L. Salomon, Z. Alfifirevic, V. Berghella et al., “Practice guide

lines for performance of the routine mid-trimester fetal ultra

sound scan,” Ultrasound in Obstetrics & Gynecology, vol. 37,

no. 1, pp. 116–126, 2011.

[13] American Institute of Ultrasound in Medicine, “AIUM prac

tice guideline for the performance of obstetric ultrasound

examinations,” Journal of Ultrasound in Medicine, vol. 32,

no. 6, pp. 1083–1101, 2013.

[14] M. Yaqub, B. Kelly, and A. T. Papageorghiou,“Guided random

forests for identifification of key fetal anatomy and image cate

gorization in ultrasound scans,” in Medical Image Computing

and Computer-Assisted Intervention – MICCAI 2015. MICCAI

2015, N. Navab, J. Hornegger, W. Wells, and A. Frangi, Eds.,

vol. 9351 of Lecture Notes in Computer Science, pp. 687–

694, Springer, Cham, 2015.

[15] C. F. Baumgartner, K. Kamnitsas, J. Matthew, S. Smith,

B. Kainz, and D. Rueckert, “Real-time standard scan plane

detection and localisation in fetal ultrasound using fully con

volutional neural networks,” in Medical Image Computing

and Computer-Assisted Intervention – MICCAI 2016. MICCAI

2016, S. Ourselin, L. Joskowicz, M. Sabuncu, G. Unal, and W.

Wells, Eds., vol. 9901 of Lecture Notes in Computer Science,

pp. 203–211, Springer, Cham, 2016.

[16] B. Rahmatullah, A. T. Papageorghiou, and J. A. Noble, “Inte

gration of local and global features for anatomical object detec

tion in ultrasound,” in Medical Image Computing and

Computer-Assisted Intervention – MICCAI 2012. MICCAI

2012, vol. 7512 of Lecture Notes in Computer Science,

pp. 402–409, Springer, Berlin, Heidelberg, 2012.

[17] M. Maraci, R. Napolitano, A. T. Papageorghiou, and J. A.

Noble, “P22.03: searching for structures of interest in an ultra

sound video sequence with an application for detection of

breech,” Ultrasound in Obstetrics & Gynecology, vol. 44,

no. S1, pp. 315–315, 2014.

[18] J. Torrents-Barrena, G. Piella, N. Masoller et al., “Segmenta

tion and classifification in MRI and US fetal imaging: recent

trends and future prospects,” Medical Image Analysis, vol. 51,

pp. 61–88, 2019.

[19] X. Zhu, H. I. Suk, L. Wang, S. W. Lee, D. Shen, and Alzheimer’s

Disease Neuroimaging Initiative, “A novel relational regulari

zation feature selection method for joint regression and classi-

fification in AD diagnosis,” Medical Image Analysis, vol. 38,

pp. 205–214, 2017.

[20] K. Chatfifield, V. Lempitsky, A. Vedaldi, and A. Zisserman,

“The devil is in the details: an evaluation of recent feature

encoding methods,” in Procedings of the British Machine

Vision Conference 2011, pp. 76.1–76.12, Dundee, UK, 2011.

[21] S. Maji, A. C. Berg, and J. Malik, “Classifification using intersec

tion kernel support vector machines is effiffifficient,” in 2008 IEEE

Conference on Computer Vision and Pattern Recognition,

pp. 1–8, Anchorage, AK, USA, 2008.

[22] S. Fekri-Ershad, “Texture image analysis and texture classififica

tion methods-a review,” International Online Journal of Image

Processing and Pattern Recognition, vol. 2, no. 1, pp. 1–29,

2019.

[23] X. Liu, P. Annangi, M. Gupta et al., “Learning-based scan

plane identifification from fetal head ultrasound images,” in

Medical Imaging 2012: Ultrasonic Imaging, Tomography, and

Therapy, San Diego, CA, USA, 2012.

[24] D. Ni, T. Li, and X. Yang, “Selective search and sequential

detection for standard plane localization in ultrasound,” in

Abdominal Imaging. Computation and Clinical Applications.

ABD-MICCAI 2013, H. Yoshida, S. Warfifield, and M. W. Van

nier, Eds., vol. 8198 of Lecture Notes in Computer Science,

pp. 203–211, Springer, Berlin, 2013.

[25] B. Lei, L. Zhuo, S. Chen, S. Li, D. Ni, and T. Wang, “Automatic

recognition of fetal standard plane in ultrasound image,” in

2014 IEEE 11th International Symposium on Biomedical Imag

ing (ISBI), pp. 85–88, Beijing, China, 2014.

[26] B. Lei, E. L. Tan, S. Chen et al., “Automatic recognition of fetal

facial standard plane in ultrasound image via fifisher vector,”

PLoS One, vol. 10, no. 5, article e0121838, 2015.

[27] S. Liu, L. Zhuo, and N. Dong, “Automatic alignment of the ref

erence standard planes of fetal face from three-dimensional

ultrasound image,” Journal of Biomedical Engineering

Research, vol. 35, no. 4, pp. 229–233, 2016.

[28] C. Bridge, “Automated annotation and quantitative descrip

tion of ultrasound videos of the fetal heart,” Medical Image

Analysis, vol. 36, pp. 147–161, 2017.

[29] S. Fekri-Ershad and F. Tajeripour, “Impulse-noise resistant

color-texture classifification approach using hybrid color local

binary patterns and Kullback–Leibler divergence,” The Com

puter Journal, vol. 60, no. 11, pp. 1633–1648, 2017.

[30] S. Fekri-Ershad, “Bark texture classifification using improved

local ternary patterns and multilayer neural network,”

Expert Systems with Applications, vol. 158, article 113509,

2020.

[31] H. Chen, D. Ni, X. Yang, S. Li, and P. A. Heng, “Fetal abdom

inal standard plane localization through representation learn

ing with knowledge transfer,” in Machine Learning in Medical

Imaging. MLMI 2014, G. Wu, D. Zhang, and L. Zhou, Eds.,

vol. 8679 of Lecture Notes in Computer Science, pp. 125–

132, 2014.

[32] H. Chen, Q. Dou, D. Ni et al., “Automatic fetal ultrasound

standard plane detection using knowledge transferred recur

rent neural networks,” in Medical Image Computing and

Computer-Assisted Intervention – MICCAI 2015. MICCAI

2015, N. Navab, J. Hornegger, W. Wells, and A. Frangi, Eds.,

vol. 9349 of Lecture Notes in Computer Science, pp. 507–

514, Springer, Cham, 2015.

[33] H. Chen, D. Ni, J. Qin et al., “Standard plane localization in

fetal ultrasound via domain transferred deep neural networks,”

IEEE Journal of Biomedical and Health Informatics, vol. 19,

no. 5, pp. 1627–1636, 2015.

[34] H. Chen, L. Wu, Q. Dou et al., “Ultrasound standard plane

detection using a composite neural network framework,” IEEE

Transactions on Cybernetics, vol. 47, no. 6, pp. 1576–1586,

2017.

[35] Z. Yu, E. L. Tan, D. Ni et al., “A deep convolutional neural

network-based framework for automatic fetal facial standard

plane recognition,” IEEE Journal of Biomedical and Health

Informatics, vol. 22, no. 3, pp. 874–885, 2018.

Computational and Mathematical Methods in Medicine[36] H. P. Kim, S. M. Lee, J.-Y. Kwon, Y. Park, K. C. Kim, and J. K.

Seo, “Automatic evaluation of fetal head biometry from ultra

sound images using machine learning,” Physiological Measure

ment, vol. 40, no. 6, article 065009, 2019.

[37] J. Jang, Y. Park, B. Kim, S. M. Lee, J. Y. Kwon, and J. K. Seo,

“Automatic estimation of fetal abdominal circumference from

ultrasound images,” IEEE Journal of Biomedical and Health

Informatics, vol. 22, no. 5, pp. 1512–1520, 2018.

[38] P. Sridar, A. Kumar, C. Li et al., “Automatic measurement of

thalamic diameter in 2-D fetal ultrasound brain images using

shape prior constrained regularized level sets,” IEEE Journal

of Biomedical and Health Informatics, vol. 21, no. 4,

pp. 1069–1078, 2017.

[39] Z. Lin, S. Li, D. Ni et al., “Multi-task learning for quality assess

ment of fetal head ultrasound images,” Medical Image Analy

sis, vol. 58, article 101548, 2019.

[40] Y. Y. Xing, F. Yang, Y. J. Tang, and L. Y. Zhang, “Ultrasound

fetal head edge detection using fusion UNet ++,” Journal of

Image and Graphics, vol. 25, no. 2, pp. 366–377, 2020.

[41] T. Ojala, M. Pietikainen, and D. Harwood, “A comparative

study of texture measures with classifification based on featured

distributions,” Pattern Recoonition, vol. 29, no. 1, pp. 51–59,

1996.

[42] n. Dalal and b. Triggs, “Histograms of oriented gradients for

human detection,” in 2005 IEEE Computer Society Conference

on Computer Vision and Pattern Recognition (CVPR'05),

pp. 886–893, San Diego, CA, USA, 2005.

[43] C.-C. Chang and C.-J. Lin, “LIBSVM,” ACM Transactions on

Intelligent Systems and Technology, vol. 2, no. 3, pp. 1–27,

2011.

[44] T. OJALA, M. PIETIKAINEN, and T. MAENPAA, “Multire

solution gray-scale and rotation invariant texture classifification

with local binary patterns,” IEEE Transactions on Pattern

Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971–

987, 2002.

[45] R. Min, D. A. Stanley, Z. Yuan, A. Bonner, and Z. Zhang, “A

deep non-linear feature mapping for large-margin kNN classi-

fification,” in 2009 Ninth IEEE International Conference on

Data Mining, pp. 357–366, Miami Beach, FL, USA, 2009.

[46] I. Rish, “An empirical study of the naive Bayes classififier [J],”

Journal of Universal Computer Science, vol. 1, no. 2, p. 127,

2001

胎儿面部超声切面识别相关推荐

微表情如何用计算机分析计算,面部微表情识别若干关键技术之计算机研究
面部微表情识别若干关键技术之计算机研究论文价格:免费论文用途:其他编辑:vicky 点击次数:188 论文字数:31584 论文编号:sb2019053109223726543 日期:2019- ...
【论文知识点笔记】具有定量特征融合的粒子群优化模糊 CNN 用于超声图像质量识别
Particle Swarm Optimized Fuzzy CNN with Quantitative Feature Fusion for Ultrasound Image Quality Ide ...
左室短轴切面_3D图解心脏解剖与心脏超声切面
原标题:3D图解心脏解剖与心脏超声切面我们可以把二维超声理解成一个切片的刀,它可以对心脏进行不同角度切片,观察他们解剖形态声窗: 就是探头放在胸壁的哪个位置,一般有5大声窗(其中第5个为病理性声窗 ...
python图像人类检测_Python 超简单实现人类面部情绪的识别
还记得我们之前写过一篇文章<手把手教你人脸识别自动开机>吗?里面用OpenCV对人脸进行简单的识别,让计算机训练认识到某个特定人物后识别对象.今天来做点高级的,识别出人脸的情绪. 本文分为 ...
左室短轴切面_【图】短轴超声切面 - 心脏解剖学 - 天山医学院
在标准左心室长轴切面基础上,将探头顺时针旋转90°,恰与左心室长轴垂直,可获得主动脉短轴切面(short axis section of aorta).沿该切面解剖心脏,中央为主动脉口横断面,可见主动 ...
【效果展示】面部追踪+情绪识别
1.使用yolov5(目标检测网络)作为脸部定位模块首先标注出人脸,达到去冗余的效果 2.使用先前博客中提到的多模态迁移视觉网络作为情绪识别模块,对yolov5检测为人脸的框内图像进行判别,达到更为精 ...
胎儿超声标准切面图与详解
为了进一步了解胎儿超声的各个标准切面和方便查看学习,简单整理了下一些标准切面详解和测量方法. 目录正常胎儿妊娠中期超声检查标准切面胎儿超声标准切面详解产科超声标准切面胎儿标准测量切面讲解早孕 ...
python dlib实现面部标志识别
要使用Python.OpenCV.dlib实现面部标志的识别需要俩步: 究竟什么是面部标志以及它们是如何工作的. 如何使用dlib,OpenCV, Python从图像中检测和提取面部标志 (1)从图像 ...
关于动物识别论文的阅读笔记——青鳉鱼的个体识别和“面部反转效应”
论文简介论文中文翻译:<青鳉鱼的个体识别和"面部反转效应"> 论文名称:<Individual recognition and the 'face invers ...

胎儿面部超声切面识别

摘要

简介

挑战

传统手工的图像识别和分类步骤

相关工作

References

胎儿面部超声切面识别相关推荐

最新文章

热门文章