1,720,992 research outputs found
A deep learning approach for quantification of brain characteristics using MRI
No full textDissertação de mestrado integrado em Engenharia Biomédica (especialidade em Informática Médica)Preterm birth is connected to impairments, altered brain growth and underdevelopment. Preterm
infants have a high risk of problems related to cognition, socialization and behavior later in life since
most part of their brain development is in extra-uterine conditions. By studying the anatomy of the
brain, many disabilities can be found, and MRI brain scans are important in the identification of these
details.
Accordingly, the goal of this dissertation is the development of different Deep Learning (DL)
approaches with the objective of quantifying the volumes of 8 brain tissues and other 5 descriptors,
necessary for the prediction of social and cognitive disabilities. Without DL, the first step for this
quantification is a previous segmentation of the studies. With DL, it is possible to quantify directly
from the brain MRI scans, skipping the segmentation step.
As data, two datasets were used: one with 86 studies of preterm patients around 30 weeks PMA and
the other with 153 preterm patients around 40 weeks PMA. Non-image data was also needed for
some ground truth descriptors. Three main procedures are performed: 2D approaches, 3D
approaches using chunks of the brain and a 3D approach with full brains. Each approach consists
of image processing techniques such as image cropping and downscale, a DL training and validation
steps, prediction of unseen studies and, finally, statistical metrics combined with prediction vs ground
truth graphs to assess the results.
The 2D approaches allowed high correlation (a mean of 0.95 for the 8 tissues for the dataset at 30
weeks PMA and a mean of 0.98 for the 40 weeks one) and low normalized RMSE (respectively, a
mean of 6.26% and 5.98% for the 8 tissues). The 3D approaches using (small) chunks allowed a
slightly improvement on the prediction vs ground truth graphs and metrics for both datasets
(respectively, a mean correlation of 0.97 and 0.98 and a mean normalized RMSE of 5.69% and
5.38%, for all tissues). Using full 3D brains only allowed good predictions for half of the descriptors.
A second case study, using a dataset of MRI brain scans on rats (139 studies), was also executed in
order to predict the volumes of 3 tissues. A 2D approach and a 3D approach were developed and
the 2D one revealed to be the most accurate. These approaches are very similar to the ones
developed for the neonatal brain.Os nascimentos prematuros estão relacionados com deficiências, crescimento cerebral alterado e
subdesenvolvimento. Os bebés prematuros têm um risco maior de ter problemas relacionados com
cognição, socialização e comportamento mais tarde na vida, dado que a maior parte do seu
desenvolvimento cerebral ocorre em condições extrauterinas. Ao estudar a anatomia do cérebro,
muitas deficiências podem ser detetadas, e os exames cerebrais de ressonância magnética são
importantes na identificação desses detalhes.
Nesse sentido, o objetivo desta tese é o desenvolvimento de diferentes abordagens de Deep Learning
(DL) com o objetivo de quantificar os volumes de 8 tecidos cerebrais e de outros 5 descritores,
necessários para a previsão de deficiências cognitivas e sociais. Sem DL, o primeiro passo para esta
quantificação e uma segmentação prévia dos studies. Com DL, é possível quantificar diretamente a
partir dos exames de ressonância magnética do cérebro, ignorando o passo da segmentação.
Como material, foram utilizados dois conjuntos de dados: um com 86 studies de pacientes pré-termo por volta das 30 semanas de idade pós-menstrual (PMA) e outro com 153 pacientes pré-termo por volta de 40 semanas IPM. Material não-imagem também foi necessário como ground truth
para alguns descritores. Três abordagens principais são executadas: abordagens 2D, abordagens
3D usando pedaços de cérebro e uma abordagem 3D com cérebros inteiros. Cada método consiste
em técnicas de processamento de imagem tais como cortes de imagem e redução de tamanho da
mesma, passos de treino e validação em DL, previsão de studies nunca vistos e, finalmente, métricas
de estatística combinadas com gráficos previsão vs ground truth para avaliar os resultados.
As abordagens 2D permitiram uma correlação alta (média de 0.95 para os 8 tecidos para o dataset
de 30 semanas PMA e uma média de 0.98 para o de 40 semanas PMA) e um baixo RMSE
normalizado (respetivamente, uma média de 6.26% e 5.98% para os 8 tecidos). As abordagens 3D
usando pedaços (pequenos) permitiram uma ligeira melhoria nas métricas para os dois conjuntos
de dados (respetivamente, uma correlação de 0.97 e 0.98 e um RMSE normalizado médio de 5.69%
e 5.38% para todos os tecidos). Usando cérebros 3D inteiros permitiu boas previsões para metade
dos descritores.
Um segundo caso de estudo, usando um dataset com exames de ressonância em cérebros de ratos
(139 studies), foi também executados no sentido de prever os volumes de 3 tecidos. Um método
2D e um 3D foram desenvolvidos e o 2D revelou ser mais preciso. Estes métodos são muito
semelhantes aos que foram desenvolvidos para o cérebro neonatal
Automatic MRI-based quantication of brain characteristics in preterm newborns
No full textEven though survival of preterm infants has improved in recent years, preterm birth is still associated with developmental impairments, such as cognitive and behavioural problems. Brain development is particularly vulnerable in this population because an important part of development takes place after birth, which could lead to primary brain injury and secondary developmental consequences. Especially the cerebral cortex rapidly develops from a smooth surface to a complexly folded structure in the third trimester of pregnancy and is therefore vulnerable in extra-uterine conditions. Cortical development has also been described to be disturbed by white matter injury. Magnetic resonance imaging (MRI) provides an important non-invasive tool to assess brain development in preterm infants. This thesis describes an automated system for quantification of brain characteristics in preterm newborns based on MR brain images. To allow automatic quantification of brain characteristics based on these images, Chapters 2–5 describe automatic segmentation (i.e. labelling of regions of interest in the image) approaches for MR brain images. Chapter 2 describes an automatic segmentation method for cortical grey matter, unmyelinated white matter and extracerebral cerebrospinal fluid. The method is based on sequential supervised voxel classification and evaluated on coronal MR images of preterm newborns at 30 and 40 weeks postmenstrual age. Chapter 3 evaluates the approach described in Chapter 2 in the segmentation in MR images of ageing adults at an average age of 70 years. Chapter 4 describes an automatic segmentation method that uses a multiscale convolutional neural network to segment neonatal and adult MR brain images into a number of tissue classes. Chapter 5 describes a general medical image segmentation method using a convolutional neural network that is applied to the segmentation of seven tissue classes in MR brain images, the pectoral muscle in MR breast images and the coronary arteries in cardiac CT angiography. Based on automatic segmentations or MR brain images, Chapter 6 describes a system to compute characteristics of the cerebral cortex. The system is evaluated in a cohort of 85 preterm newborns imaged at 30 and 40 weeks postmenstrual age. The descriptors show longitudinal and regional differences, and show a relation with a conventional visual brain abnormality scoring system. Chapter 7 describes cortical morphology in newborns with severe congenital heart disease compared with healthy controls, using the system from Chapter 6. Chapter 8 describes prediction of cognitive and motor performance at later age based on descriptors automatically computed from MR images of preterm newborns, using the segmentation approach from Chapter 4 and the feature computation approach from Chapter 6. The work in this thesis showed that it is possible to automatically compute quantitative descriptors from an MR brain image that are valuable in the assessment of neurodevelopment of preterm infants: from image segmentation, to feature computation, to outcome prediction. Such a system could in the future be implemented in clinical practice to, directly after the image acquisition, compute quantitative measurements and possibly even identify preterm infants at risk of neurodevelopmental impairments
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
