Search results for "image"

Efficient contour-based annotation by iterative deep learning for organ segmentation from volumetric medical images

2022

Abstract Purpose Training deep neural networks usually require a large number of human-annotated data. For organ segmentation from volumetric medical images, human annotation is tedious and inefficient. To save human labour and to accelerate the training process, the strategy of annotation by iterative deep learning recently becomes popular in the research community. However, due to the lack of domain knowledge or efficient human-interaction tools, the current AID methods still suffer from long training time and high annotation burden. Methods We develop a contour-based annotation by iterative deep learning (AID) algorithm which uses boundary representation instead of voxel labels to incorp…

Kuvien maaseutu : maaseutumaisemakuvaston luomat mielikuvat suomalaisesta maaseutukulttuurista

2013

Glottal Source Features for Automatic Speech-Based Depression Assessment

2017

Depression is one of the most prominent mental disorders, with an increasing rate that makes it the fourth cause of disability worldwide. The field of automated depression assessment has emerged to aid clinicians in the form of a decision support system. Such a system could assist as a pre-screening tool, or even for monitoring high risk populations. Related work most commonly involves multimodal approaches, typically combining audio and visual signals to identify depression presence and/or severity. The current study explores categorical assessment of depression using audio features alone. Specifically, since depression-related vocal characteristics impact the glottal source signal, we exa…

High content and dispersion of Gd in bimodal porous silica: T2 contrast agents under ultra-high magnetic fields

2022

Silica-based UVM-7-type bimodal mesoporous materials with high gadolinium content (∞ ≥ Si/Gd ≥ 13) have been synthesized through a one-pot surfactant-assisted procedure from hydroalcoholic solution using a cationic surfactant as template, and starting from atrane complexes of Gd and Si as inorganic precursors. The novel synthetic pathway developed in the study preserves the UVM-7-type architecture while optimizing the dispersion of the Gd-guest species at the nanoscale and even at atomic level. It has been determined that the number of Gd atoms forming clusters is always less than 10. The behaviour under exposure to ultra-high magnetic fields reveals a significant increase in the transversa…

LA IMAGEN CONSTRUIDA DEL PODER REAL EN LA CORONA DE ARAGÓN (SIGLOS XIII-XV): CASAS, CEREMONIAL Y MAGNIFICENCIA

2007

Command and obedience do not exist without emotional forms of shaping control. This is especially notable in the Kingdom of Aragon, since the heterogeneity of its territories was not only unified through the titles of the royal family, but the ceremonials, the aesthetic simplicity and balance of the buildings formed the charismatic ostentation of a command that demonstrated its power through the prizes seized from the enemy, the stately architectural forms and the civil rites of recognition. No existe el mando y obediencia sin formas sentimentales de conformar dominio. Esto es especialmente notable en el Reino de Aragón, pues la heterogeneidad de sus territorios, no sólo se unificaba median…

Motor imagery in unipolar major depression

2014

International audience; Background: Motor imagery is a potential tool to investigate action representation, as it can provide insights into the processes of action planning and preparation. Recent studies suggest that depressed patients present specific impairment in mental rotation. The present study was designed to investigate the influence of unipolar depression on motor imagery ability. Methods: Fourteen right-handed patients meeting DSM-IV criteria for unipolar depression were compared to 14 matched healthy controls. Imagery ability was accessed by the timing correspondence between executed and imagined movements during a pointing task, involving strong spatiotemporal constraints (spee…

L’importance de l’image dans le malaise social. Colloques de Bruxelles. « L’Esprit de ce temps et l’Esprit des profondeurs », Château de la Hulpe, S…

2019

Aplicación de la Termografía Infrarroja en Pediatría: Análisis de las alteraciones de la microcirculación cutánea

2020

Desde los inicios de la medicina, se conoce la relación entre enfermedad y las variaciones de temperatura corporal, lo que ha llevado al estudio y desarrollo de técnicas de termometría, que permitiesen cuantificar dichos cambios de temperatura. Entre ellas, destaca la Termografía Infrarroja, que es una técnica de imagen inocua, ya que se basa en captar la emisión de radiación del infrarrojo que emite el cuerpo, es rápida de realizar y accesible, pues se puede realizar cerca del paciente, sin necesidad de desplazamientos ni sedación. Todas estas características hacen que sea una técnica recomendable para utilizar en la población pediátrica que, por su corta edad, es más vulnerable a las radi…

Toolbox for Distance Estimation and Cluster Validation on Data With Missing Values

2022

Missing data are unavoidable in the real-world application of unsupervised machine learning, and their nonoptimal processing may decrease the quality of data-driven models. Imputation is a common remedy for missing values, but directly estimating expected distances have also emerged. Because treatment of missing values is rarely considered in clustering related tasks and distance metrics have a central role both in clustering and cluster validation, we developed a new toolbox that provides a wide range of algorithms for data preprocessing, distance estimation, clustering, and cluster validation in the presence of missing values. All these are core elements in any comprehensive cluster analy…

Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance

2022

Accurate sleep stage classification is vital to assess sleep quality and diagnose sleep disorders. Numerous deep learning based models have been designed for accomplishing this labor automatically. However, the class imbalance problem existing in polysomnography (PSG) datasets has been barely investigated in previous studies, which is one of the most challenging obstacles for the real-world sleep staging application. To address this issue, this paper proposes novel methods with signal-driven and image-driven ways of noise addition to balance the imbalanced relationship in the training dataset samples. We evaluate the effectiveness of the proposed methods which are integrated into a convolut…