Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 6
Encontrada(s) 1 página(s)

RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

A deep sift convolutional neural networks for total brain volume estimation from 3D ultrasound images

  • Jafrasteh, Bahram
  • Lubián López, Simón
  • Benavente Fernández, Isabel
Preterm infants are a highly vulnerable population. The total brain volume (TBV) of these infants can be accurately estimated by brain ultrasound (US) imaging which enables a longitudinal study of early brain growth during Neonatal Intensive Care (NICU) admission. Automatic estimation of TBV from 3D images increases the diagnosis speed and evades the necessity for an expert to manually segment 3D images, which is a sophisticated and time consuming task. We develop a deep-learning approach to estimate TBV from 3D ultrasound images. It benefits from deep convolutional neural networks (CNN) with dilated residual connections and an additional layer, inspired by the fuzzy c-Means (FCM), to further separate the features into different regions, i.e. sift layer. Therefore, we call this method deep-sift convolutional neural networks (DSCNN). The proposed method is validated against three state-of-the-art methods including AlexNet-3D, ResNet-3D, and VGG-3D, for TBV estimation using two datasets acquired from two different ultrasound devices. The results highlight a strong correlation between the predictions and the observed TBV values. The regression activation maps are used to interpret DSCNN, allowing TBV estimation by exploring those pixels that are more consistent and plausible from an anatomical standpoint. Therefore, it can be used for direct estimation of TBV from 3D images without needing further image segmentation.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Assessment of the perception of vertical subjectivity in children born preterm

  • Riera Tur, Laura
  • Lubián Gutiérrez, Manuel
  • Benavente Fernández, Isabel
  • Lubián López, Simón Pedro
  • Martín‑Mateos, Antonio J.
  • Lechuga Sancho, Alfonso María
Children born preterm have increased rates of paediatric mortality and morbidity. Prematurity has been associated with impaired visual perception and visuo-motor integration. The alteration of the perception of verticality translates into alterations of the vestibular system at central and/or peripheral level, which may manifest itself in symptoms such as imbalance, dizziness or even vertigo. The aim of this study was to compare subjective visual vertical (SVV) test scores in children born preterm with those of children born at term at ages between 7 and 10. One hundred ten children with no neurodevelopmental disorder of 7 to 10 years of age were studied using a mobile application on a smartphone attached to a wall by means of a rotating plate. The SVV test was compared between two groups: a group of 55 preterm children (53 very preterm children born under 32 weeks of gestational age and 2 preterm with very low birth weight) and another group of 55 children born at term (after 37 weeks of gestational age). The SVV results were analysed for comparison with respect to prematurity, sex and age. We found no significant differences in the SVV study in the comparison between preterm and term children. In addition, no significant differences were observed regarding sex or age between 7 and 10 years.Conclusion: We found no alterations in the perception of vertical subjectivity in children between 7 and 10 years of age, with antecedents of very preterm birth and/or very low birth weight.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Relationship of early brain growth pattern measured by ultrasound with neurological outcome at two years of age in very low birth weight infants

  • Ruiz González, Estefanía
  • Lubián López, Simón Pedro
  • Jiménez Luque, Natalia
  • Segado Arenas, Antonio
  • Lubián Gutiérrez, Manuel
  • Marín Almagro, Yolanda
  • Zafra Rodríguez, Pamela
  • Méndez Abad, Paula
  • Benavente Fernández, Isabel
The purpose of this study is to define the impact of early brain growth trajectory in very low birth weight infants (VLBWI) on neurological prognosis at 2 years, assessed using sequential ultrasound (US) scans. This is a prospective cohort study with consecutive inclusion of VLBWI ≤ 32 weeks gestational age and ≤ 1500 g at birth. Total brain volume (TBV) was assessed using sequential 3D-US from birth to discharge. Prognosis at 2 years (corrected age) was assessed using the Bayley Scales of Infant and Toddler Development Third Edition. TBV showed slower growth with postmenstrual age (PMA) in those VLBWI who had an adverse cognitive prognosis compared to those with good cognitive prognosis (mean difference in TBV between prognostic groups from 4.56 cm3 at 28 weeks to 42.58 cm3 at 43 weeks) as well as in those with adverse language prognosis (mean difference in TBV from 2.21 cm3 at 28 weeks to 26.98 cm3 at 43 weeks) although other variables showed more impact than TBV on language prognosis (gestational age at birth, brain injury at term, and socioeconomic status). No association was found between TBV and motor prognosis. Brain growth rate was also significantly higher in those VLBWI who presented good cognitive scores (18.78 + (0.33 × (PMA-33)) cm3/week) compared to those with adverse cognitive outcome (13.73 + (0.64 × (PMA-33)) cm3/week). Conclusion: Early altered brain growth is associated with poor cognitive prognosis at 2 years of age. Using sequential US monitoring, we can detect early brain growth deviation in patients who will have adverse cognitive outcomes. What is known: • The prediction of neurodevelopmental outcome of VLBWI is mostly based on the presence of brain injury in US and structural magnetic resonance imaging (MRI) at term. • Some studies have related brain volume measured on MRI at term with neurodevelopment outcome. What is new: • VLBWI with adverse cognitive prognosis at two years of age present smaller brain volumes detectable by sequential US during NICU admission. • Brain volume can be estimated from 2D and 3D US and has prognostic value in VLBWI., 11 páginas
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Ultrasonographic Estimation of Total Brain Volume: 3D Reliability and 2D Estimation. Enabling Routine Estimation During NICU Admission in the Preterm Infant

  • Benavente Fernández, Isabel
  • Ruiz González, Estefanía
  • Lubián Gutiérrez, Manuel
  • Lubián Fernández, Simón Pedro
  • Cabrales Fontela, Yunior
  • Roca Cornejo, Cristina
  • Olmo-Duran, Pedro
  • Lubián López, Simón Pedro
Objectives: The aim of this study is to explore if manually segmented total brain volume (TBV) from 3D ultrasonography (US) is comparable to TBV estimated by magnetic resonance imaging (MRI). We then wanted to test 2D based TBV estimation obtained through three linear axes which would enable monitoring brain growth in the preterm infant during admission. Methods: We included very low birth weight preterm infants admitted to our neonatal intensive care unit (NICU) with normal neuroimaging findings. We measured biparietal diameter, anteroposterior axis, vertical axis from US and MRI and TBV from both MRI and 3D US. We calculated intra- and interobserver agreement within and between techniques using the intraclass correlation coefficient and Bland-Altman methodology. We then developed a multilevel prediction model of TBV based on linear measurements from both US and MRI, compared them and explored how they changed with increasing age. The multilevel prediction model for TBV from linear measures was tested for internal and external validity and we developed a reference table for ease of prediction of TBV. Results: We used measurements obtained from 426 US and 93 MRI scans from 118 patients. We found good intra- and interobserver agreement for all the measurements. US measurements were reliable when compared to MRI, including TBV which achieved excellent agreement with that of MRI [ICC of 0.98 (95% CI 0.96-0.99)]. TBV estimated through 2D measurements of biparietal diameter, anteroposterior axis, and vertical axis was comparable among both techniques. We estimated the population 95% confidence interval for the mean values of biparietal diameter, anteroposterior axis, vertical axis, and total brain volume by post-menstrual age. A TBV prediction table based on the three axes is proposed to enable easy implementation of TBV estimation in routine 2D US during admission in the NICU. Conclusions: US measurements of biparietal diameter, vertical axis, and anteroposterior axis are reliable. TBV segmented through 3D US is comparable to MRI estimated TBV. 2D US accurate estimation of TBV is possible through biparietal diameter, vertical, and anteroposterior axes., This work was supported by the 2017 (PI0052/2017) and 2019 (ITI-0019-2019) ITI-Cadiz integrated territorial initiative for biomedical research European Regional Development Fund (ERDF) 2014-2020. Andalusian Ministry of Health and Families, Spain.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Parental competences in fathers and mothers of very-low-birth-weight preterm infants

  • Jiménez Luque, Natalia
  • Benavente Fernández, Isabel
  • Ruiz González, Estefanía
  • Lubián López, Simón Pedro
  • Sánchez Sandoval, Yolanda
Objective: The goal was to analyze parental competences in Spanish families with very-low-birth-weight infants (≤32 weeks and/or less 1500 g) over 18 months of corrected age. Background: Parenting in families of very preterm infants is an interesting focus of research as we advance in the knowledge of how parental competences can have an important impact on child development. Method: Sixty-eight mothers and 56 fathers completed measures of parental competences, sociofamily risk, parental stress, social support, and emotional symptoms. Clinical characteristics and neonatal medical risk data were collected after birth. Statistical analyses were performed to compare parental competences with those of mothers and fathers of non-preterm infants. Generalized estimating equations were used for analysis, adjusted by family unit. Results: Mothers and fathers of preterm infants score higher in most dimensions of parental competences compared to a control group. Focusing on the preterm population, mothers score higher than fathers in daily involvement and mentalization and lower in parental self-care. When studied separately, we found different scores for fathers and mothers in parental competences (sociofamily risk, parental stress, social support, and emotional symptoms). Conclusion: Parents of preterm infants present better parental competences than parents of non-preterm infants when their children reach 18 months of age. It is important to consider the differences in parental competences between the mothers and fathers of these children. Implications: Our findings suggest the need to address parental competences to develop preventive and adaptive strategies in parents of preterm infants to promote positive parenting., This paper is part of the project PID2019‐110484RB‐I00 funded by MCIN/AEI/ 0.13039/501100011033. It was also funded by the 2017 (PI0052/2017) and 2019 (ITI‐0019‐2019) Cadiz‐integrated territorial initiative for biomedical research and the European Regional Development Fund (ERDF) 2014–2020, Andalusian Ministry of Health and Families, Spain. Funding information
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Gaussian processes for missing value imputation

  • Jafrasteh, Bahram
  • Hernández Lobato, Daniel
  • Lubián López, Simón Pedro
  • Benavente Fernández, Isabel
A missing value indicates that a particular attribute of an instance of a learning problem is not recorded. They are very common in many real-life datasets. In spite of this, however, most machine learning methods cannot handle missing values. Thus, they should be imputed before training. Gaussian Processes (GPs) are non-parametric models with accurate uncertainty estimates that combined with sparse approximations and stochastic variational inference scale to large data sets. Sparse GPs (SGPs) can be used to get a predictive distribution for missing values. We present a hierarchical composition of sparse GPs that is used to predict the missing values at each dimension using the observed values from the other dimensions. Importantly, we consider that the input attributes to each sparse GP used for prediction may also have missing values. The missing values in those input attributes are replaced by the predictions of the previous sparse GPs in the hierarchy. We call our approach missing GP (MGP). MGP can impute all observed missing values. It outputs a predictive distribution for each missing value that is then used in the imputation of other missing values. We evaluate MGP on one private clinical data set and on four UCI datasets with a different percentage of missing values. Furthermore, we compare the performance of MGP with other state-of-the-art methods for imputing missing values, including variants based on sparse GPs and deep GPs. Our results show that the performance of MGP is significantly better.