通过高斯过程集合识别子宫收缩
IDENTIFICATION OF UTERINE CONTRACTIONS BY AN ENSEMBLE OF GAUSSIAN PROCESSES.
作者信息
Yang Liu, Heiselman Cassandra, Quirk J Gerald, Djurić Petar M
机构信息
Department of Electrical and Computer Engineering, Stony Brook University, Stony Brook, NY 11794, USA.
Department of Obstetrics, Gynecology and Reproductive Medicine, Stony Brook, NY 11794, USA.
出版信息
Proc IEEE Int Conf Acoust Speech Signal Process. 2021 Jun;2021. doi: 10.1109/icassp39728.2021.9414041. Epub 2021 May 13.
Abstract
Identifying uterine contractions with the aid of machine learning methods is necessary vis-á-vis their use in combination with fetal heart rates and other clinical data for the assessment of a fetus wellbeing. In this paper, we study contraction identification by processing noisy signals due to uterine activities. We propose a complete four-step method where we address the imbalanced classification problem with an ensemble Gaussian process classifier, where the Gaussian process latent variable model is used as a decision-maker. The results of both simulation and real data show promising performance compared to existing methods.
摘要
借助机器学习方法识别子宫收缩对于将其与胎儿心率及其他临床数据相结合以评估胎儿健康状况而言是必要的。在本文中，我们通过处理由子宫活动产生的噪声信号来研究收缩识别。我们提出了一种完整的四步方法，其中我们使用集成高斯过程分类器来解决不平衡分类问题，高斯过程潜在变量模型用作决策器。与现有方法相比，模拟和实际数据的结果均显示出良好的性能。
相似文献
1
IDENTIFICATION OF UTERINE CONTRACTIONS BY AN ENSEMBLE OF GAUSSIAN PROCESSES.通过高斯过程集合识别子宫收缩
Proc IEEE Int Conf Acoust Speech Signal Process. 2021 Jun;2021. doi: 10.1109/icassp39728.2021.9414041. Epub 2021 May 13.
2
CLASS-IMBALANCED CLASSIFIERS USING ENSEMBLES OF GAUSSIAN PROCESSES AND GAUSSIAN PROCESS LATENT VARIABLE MODELS.使用高斯过程和高斯过程潜在变量模型集成的类不平衡分类器
Proc IEEE Int Conf Acoust Speech Signal Process. 2021 Jun;2021. doi: 10.1109/icassp39728.2021.9414754. Epub 2021 May 13.
3
BOOST ENSEMBLE LEARNING FOR CLASSIFICATION OF CTG SIGNALS.用于CTG信号分类的增强集成学习
Proc IEEE Int Conf Acoust Speech Signal Process. 2022 May;2022:1316-1320. doi: 10.1109/icassp43922.2022.9746503. Epub 2022 Apr 27.
4
Fetal movement during labor.
Am J Obstet Gynecol. 1991 Oct;165(4 Pt 1):1073-6. doi: 10.1016/0002-9378(91)90473-5.
5
Adaptive Fusion Based Method for Imbalanced Data Classification.基于自适应融合的不平衡数据分类方法
Front Neurorobot. 2022 Feb 28;16:827913. doi: 10.3389/fnbot.2022.827913. eCollection 2022.
6
Cardiotocography analysis by empirical dynamic modeling and Gaussian processes.基于经验动态建模和高斯过程的胎心监护分析
Front Bioeng Biotechnol. 2023 Jan 12;10:1057807. doi: 10.3389/fbioe.2022.1057807. eCollection 2022.
7
INFERENCE ABOUT CAUSALITY FROM CARDIOTOCOGRAPHY SIGNALS USING GAUSSIAN PROCESSES.利用高斯过程从心电图信号推断因果关系
Proc IEEE Int Conf Acoust Speech Signal Process. 2019 May;2019:2852-2856. doi: 10.1109/icassp.2019.8683052. Epub 2019 Apr 17.
8
Machine learning-based prediction of postpartum hemorrhage after vaginal delivery: combining bleeding high risk factors and uterine contraction curve.基于机器学习的阴道分娩后产后出血预测：结合出血高危因素和子宫收缩曲线。
Arch Gynecol Obstet. 2022 Oct;306(4):1015-1025. doi: 10.1007/s00404-021-06377-0. Epub 2022 Feb 16.
9
A Deep-Ensemble-Level-Based Interpretable Takagi-Sugeno-Kang Fuzzy Classifier for Imbalanced Data.基于深度集成层的可解释 Takagi-Sugeno-Kang 模糊分类器用于不平衡数据。
IEEE Trans Cybern. 2022 May;52(5):3805-3818. doi: 10.1109/TCYB.2020.3016972. Epub 2022 May 19.
10
Deep Generative Mixture Model for Robust Imbalance Classification.深度生成混合模型用于稳健的不平衡分类。
IEEE Trans Pattern Anal Mach Intell. 2023 Mar;45(3):2897-2912. doi: 10.1109/TPAMI.2022.3178914. Epub 2023 Feb 3.
引用本文的文献
1
Enhancing uterine contraction detection through novel EHG signal processing: a pilot study leveraging the relationship between slow and fast wave components to improve signal quality and noise resilience.通过新型EHG信号处理增强子宫收缩检测：一项利用慢波和快波成分之间的关系来提高信号质量和抗噪声能力的初步研究。
Front Physiol. 2025 May 27;16:1568919. doi: 10.3389/fphys.2025.1568919. eCollection 2025.
2
UNSUPERVISED CLUSTERING AND ANALYSIS OF CONTRACTION-DEPENDENT FETAL HEART RATE SEGMENTS.收缩依赖性胎儿心率段的无监督聚类与分析
Proc IEEE Int Conf Acoust Speech Signal Process. 2022 May;2022. doi: 10.1109/icassp43922.2022.9747598. Epub 2022 Apr 27.
本文引用的文献
1
Application of decision tree in determining the importance of surface electrohysterography signal characteristics for recognizing uterine contractions.决策树在确定表面电子宫图信号特征对识别子宫收缩的重要性方面的应用。
Biocybern Biomed Eng. 2019 Jul-Sep;39(3):806-813. doi: 10.1016/j.bbe.2019.06.008.
2
Evaluation of convolutional neural network for recognizing uterine contractions with electrohysterogram.基于电子宫收缩描记图的卷积神经网络识别子宫收缩的评估。
Comput Biol Med. 2019 Oct;113:103394. doi: 10.1016/j.compbiomed.2019.103394. Epub 2019 Aug 19.
3
Automated electrohysterographic detection of uterine contractions for monitoring of pregnancy: feasibility and prospects.自动电子宫收缩描记术检测用于妊娠监测的可行性和前景。
BMC Pregnancy Childbirth. 2018 May 8;18(1):136. doi: 10.1186/s12884-018-1778-1.
4
Detection rate of fetal distress using contraction-dependent fetal heart rate variability analysis.基于宫缩相关胎儿心率变异性分析的胎儿窘迫检出率。
Physiol Meas. 2018 Feb 28;39(2):025008. doi: 10.1088/1361-6579/aaa925.
5
Effect of uterine contractions on fetal heart rate in pregnancy: a prospective observational study.孕期子宫收缩对胎儿心率的影响：一项前瞻性观察研究。
Acta Obstet Gynecol Scand. 2016 Oct;95(10):1129-35. doi: 10.1111/aogs.12949.
6
Electrohysterographic detection of uterine contractions in term pregnancy.
Annu Int Conf IEEE Eng Med Biol Soc. 2015 Aug;2015:5851-4. doi: 10.1109/EMBC.2015.7319722.
7
Open access intrapartum CTG database.开放获取的产时电子胎心监护数据库
BMC Pregnancy Childbirth. 2014 Jan 13;14:16. doi: 10.1186/1471-2393-14-16.
8
Accuracy and reliability of fetal heart rate monitoring using maternal abdominal surface electrodes.使用母体腹部表面电极进行胎儿心率监测的准确性和可靠性。
Acta Obstet Gynecol Scand. 2012 Nov;91(11):1306-13. doi: 10.1111/j.1600-0412.2012.01533.x. Epub 2012 Oct 19.
9
Quantitative analysis of contraction patterns in electrical activity signal of pregnant uterus as an alternative to mechanical approach.作为机械方法的替代方案，对妊娠子宫电活动信号中的收缩模式进行定量分析。
Physiol Meas. 2005 Oct;26(5):753-67. doi: 10.1088/0967-3334/26/5/014. Epub 2005 Jul 1.
Zotero 插件