Antonio Bosnjak

Antonio Bosnjak
University of Ulster · Nanotechnology and Integrated Bioengineering Centre (NIBEC)

Doctor and Professor
Bioengineering, medical and Biomedical Engineering.

About

106
Publications
29,970
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
228
Citations
Introduction
He obtained PhD Title of ENSTB "École Nationale Supérieure des Télécommunications de Bretagne". He presented the PhD thesis on Mars 28, 2003. The work title is: "Segmentation et Modélisation Dynamiques: Application à la Reconstruction 3D d'Images Échocardiographiques", and obtained a "très Honorable" mention for his excellent work. Professor Bosnjak is the Head of the Image Processing Center at the Universidad de Carabobo, and a Titular Professor of Electronics and Communications Department.
Additional affiliations
May 1999 - March 2003
ENST Bretagne
Position
  • PhD Student
February 2005 - present
University of Carabobo
Position
  • Professor (Full)
Description
  • Profesor Titular del Departamento de Electrónica y Comunicaciones desde Febrero del 2005
January 1995 - present
University of Carabobo
Description
  • Director del Centro de Procesamiento de Imágenes de la Facultad de Ingeniería de la Universidad de Carabobo.
Education
September 1999 - March 2003
University of Rennes 2
Field of study
  • Traitement du Signal et Télécommunications.

Publications

Publications (106)
Conference Paper
Full-text available
Left Ventricular Assist Devices (LVADs) are used as a bridge to cardiac transplantation, and for long-term support in patients with advanced Heart Failure. LVADs are relatively high-power demanding implanted devices (>3W), provided via a percutaneous driveline (cable) from an external supply. However, incidence of driveline infection is a severe an...
Article
Full-text available
This article presents the development of a power loss emulation (PLE) system device to study and find ways of mitigating skin tissue heating effects in transcutaneous energy transmission systems (TETS) for existing and next generation left ventricular assist devices (LVADs). Skin thermal profile measurements were made using the PLE system prototype...
Conference Paper
Full-text available
This work focuses on the thermal analysis of a transdermal wireless radiofrequency (RF) energy transfer system, to power artificial heart pumps, particularly left ventricular assist devices (LVADs). We aim to understand the blood perfusion factors to mitigate the skin heating effects and thermal injury to subcutaneous tissue under the RF coupling a...
Conference Paper
Full-text available
This work focuses on developing Transcutaneous Energy Transfer Systems (TETS) to power wirelessly the next generation of artificial heart pumps, particularly Left-Ventricular Assist Devices (LVADs). Conventional TETS use inductive coupling for transferring relatively high-power across the skin but are associated with significant skin heating effect...
Chapter
Full-text available
The use of wearable dry sensors for long term recordings of electrocardiographic bipolar leads located in comfortable areas of the body, is a requirement for detecting certain heart rhythms. Knowledge of the skin-electrode electrical performance of dry electrodes is necessary when seeking to improve various processing stages for signal quality enha...
Conference Paper
Full-text available
The use of wearable dry sensors for long term recordings of electro-cardiographic bipolar leads located in comfortable areas of the body, is a re-quirement for detecting certain heart rhythms. Knowledge of the skin-electrode electrical performance of dry electrodes is necessary when seeking to improve various processing stages for signal quality en...
Conference Paper
Full-text available
There are cardiac patients requiring their ECG to be constantly monitored. The quality of long-term electrical activity feature measurements in the ECG may rely considerably on the electrodes and their long-term skin interface performance stability; thus, affecting the accuracy of clinical diagnosis and treatment. Particularly, misbehavior of the s...
Conference Paper
Full-text available
The use of wearable dry sensors for recording long term ECG signals is a requirement for certain studies of heart rhythm. Knowledge of the skin-electrode electrical performance of dry electrodes is necessary when seeking to improve various processing stages for signal quality enhancement. In this paper, methods for the assessment of dry skin-electr...
Conference Paper
Full-text available
The global burden of diabetes is projected to increase from 246 million people to over 380 million people by 2025 [1]. The main pathogenic mechanisms involved in diabetic foot complication include ischemia, neuropathy, and infection which combined with the presence of foot deformities and high pressure can produce tissue ulceration, necrosis, and f...
Conference Paper
Full-text available
The use of wearable sensors for recording very long term ECG signals, is an important clinical need for some assessments of heart function. Knowledge concerning the electrode-skin interface characteristics and sustainability are critical for attaining acceptable signal quality for the reliable performance of different stages of signal processing. T...
Conference Paper
Full-text available
This work presents a novel approach to ECG R-peak detection based on the Discrete Wavelet Transform. 18,647 beats were analysed from thirty AF patients who underwent DC cardioversion at Royal Victoria Hospital, Belfast. The efficacy of the R-peak detection algorithm for both normal sinus rhythm and atrial fibrillation beats was assessed using three...
Chapter
Full-text available
Actualmente, cualquiera posee una cámara o un teléfono celular para tomar fotografías, y además podría acceder a un servicio de Telemedicina con las imágenes capturadas, enviándolas a través de Internet, si está disponible y conectado con un sistema de salud pública o privada. Así, se puede desarrollar un sistema de Teledermatología que puede gener...
Chapter
Full-text available
El trazado cefalométrico es una técnica que evoluciona constantemente con el tiempo. Actualmente existen nuevos métodos y software que asisten el proceso de trazado y utilizan como entrada imágenes 2D (Rx) o 3D (CT), mostrando el trazado final en 2D o 3D de acuerdo al tipo imágenes de entrada. Los mejores y más precisos resultados se obtienen con u...
Conference Paper
Full-text available
Dentro de las actividades de Docencia de un Profesor Universitario, se encuentra el diseño y aplicación de quices y exámenes, los cuales deben ser corregidos muchas veces fuera del horario de permanencia en la Universidad, y como consecuencia se desperdicia mucho tiempo valioso que podría ser dedicado a la investigación o extensión. En el caso de l...
Conference Paper
Full-text available
La Tele-dermatología es una disciplina que puede generar un diagnóstico médico preciso procesando la imagen enviada con un Software apropiado. La alta disponibilidad de pequeñas cámaras digitales con una alta resolución está disponible en dispositivos de consumo masivo como son, los teléfonos celulares y las tablets, los cuales se encuentran en cua...
Article
Full-text available
The task of reef restoration is very challenging for volunteer SCUBA divers, if it has to be carried out at deep sea, 200 meters, and low temperatures. This kind of task can be properly performed by an Autonomous Underwater Vehicle (AUV); able to detect the location of reef areas and approach them. The aim of this study is the development of a visi...
Article
Full-text available
This work focuses on developing a fast coral reef detector, which is used for an autonomous underwater vehicle, AUV. A fast detection secures the AUV stabilization respect to an area of reef as fast as possible, and prevents devastating collisions. We use the algorithm of Purser et al. (2009) because of its precision. This detector has two parts: f...
Conference Paper
Full-text available
Se propone una nueva cadena de procesamiento que incluye un clasificador utilizando Máquinas de Vector de Soporte (SVM) para la segmentación. Este clasificador tiene un error relativo menor al 7%, y puede ser usado para cirugía guiada por computadora, y también se puede extender a tres dimensiones para modelar los núcleos basales. Segmentar las est...
Conference Paper
Full-text available
Se desarrolló un protocolo de tele-gestión en salud que contribuya a la evaluación de la eficiencia, eficacia y calidad de servicio prestado por los centros de atención primaria en las comunidades; haciendo énfasis en la participación ciudadana y el uso de las nuevas tecnologías de la información y comunicación para la promoción de un estilo de vid...
Conference Paper
Full-text available
Las enfermedades cardiovasculares son las primeras causas de muerte a nivel nacional y debido a que el análisis de las señales cardiacas, se realiza manualmente utilizando métodos de comparación con experiencias y estudios previos, trae como consecuencia que el diagnóstico sea lento y tenga altas probabilidades de presentar errores, entonces se dec...
Conference Paper
Full-text available
Segmentation of structures inside of the brain are essential for planning computer assisted surgery. Structures such as basal nuclei are difficult to detect in MR images because they have fuzzy edges, and exhibit few changes on the gray level intensities relative to the anatomical structures surroundings. The traditional techniques of image process...
Conference Paper
Full-text available
La calibración del localizador electromagnético MiniBirdTM es una tarea compleja. Realizar la calibración de este equipo es un procedimiento necesario para obtener importantes puntos en el espacio 3D para Neurocirugía Asistida por Computadora utilizando imágenes. Así como también para realizar una reconstrucción de objetos 3D en ambientes de Realid...
Conference Paper
Full-text available
The segmentation of cerebral structures in medical images has numerous clinical applications. It can provide significant aids for the diagnosis of some pathology. In this work, we developed a software application for the segmentation of medical images using a new segmentation method based on the theory of deformable models. We use the advantages of...
Conference Paper
Full-text available
We began using the same variables as SAPS-1 score, adding the rest of variables one by one as recommended by physicians, to observe whether the SVM classification improves. These variables include: Age, HR, SysABP, NISysABP, Temp, RespRate, MechVent, Urine, BUN, HCT, WBC, Glucose, K, Na, HCO3, GCS, and other variables that were added for phase 1: D...
Conference Paper
Full-text available
This paper proposes a new technique for 3D motion estimation of the left ventricle from a sequence of a heartbeat. Accurate motion estimation of the movement of cardiac walls has been shown to be very important for studying the cardiovascular illnesses. This technique is based on a processing chain from the acquisition to the 3D segmentation of the...
Article
Full-text available
We developed a new approach based on Support Vector Machines (SVM) to model solids defined by a set of points on their surface. In problems of classification, regression and support of distribution, SVM are focused in the hyper-planes of maximum margin in the feature space. However, the forms that could be described by these surfaces when they retu...
Conference Paper
Full-text available
This research proposes an innovative method for obtaining a computer assisted anatomical model when for structures complex to segment using either the traditional or advanced methods of image processing. Our method combines medical knowledge of the organ to define the contours, and adds a Support Vector Machine (SVM) when the images are diffuse or...
Conference Paper
Full-text available
The segmentation of cerebral structures in medical images has numerous clinical applications. It can provide significant aids for the diagnosis of some pathology. In this work, we developed a software application for the segmentation of medical images using a new segmentation method based on the theory of deformable models. Taking advantage of the...
Conference Paper
Full-text available
Between 2006 and 2008, a research on the Anatomy course of the Medical School at University of Carabobo, based on interviews to teachers, was performed, regarding the conditions for teaching-learning processes, specifically with regards to the subject matter of Neuro - anatomy. The necessities expressed by the teachers revolved around the students’...
Conference Paper
Desarrollo de un Laboratorio Virtual de Neuroanatomía con Tecnología VTK.
Conference Paper
Full-text available
Aplicación de Máquinas de Vectores de Soporte para Identificación de Núcleos basales en imágenes de Resonancia Magnética.
Conference Paper
Full-text available
During a minimal invasive neurosurgery it is necessary to know precisely the 3D position of the surgical instruments and their relationship and interaction with the anatomy of the human brain. Today, on developing countries many surgeons still operate without 3D visual aids, managing instruments in the blind. With this idea we developed a new techn...
Conference Paper
Full-text available
En respuesta a la masificación de estudiantes, falta de materiales didácticos para enseñanza y poca disposición de cadáveres para las prácticas, se desarrolló un entorno virtual para el aprendizaje de Neuro-Anatomía, como complemento a las clases presenciales, según las necesidades planteadas por parte del profesorado de anatomía en la carrera de m...
Chapter
Full-text available
Brain navigation consists in travelling along an established trajectory inside the brain anatomy in order to locate and reach a target of interest. To achieve this, neuronavigation systems provide a set of technological resources to the surgeons, allowing them to observe images from patients’ anatomy and monitor surgical instruments while performin...
Chapter
Full-text available
Durante una neurocirugía mínimamente invasiva es necesario conocer con mucha precisión la posición del instrumental quirúrgico y su relación e interacción con la compleja anatomía 3D del cerebro humano, para realizar estos procedimientos se desarrollaron técnicas de cirugía asistida por computadora (CAS). Con la finalidad de realizar una neurocirug...
Chapter
Full-text available
Este trabajo presenta un sistema de Cirugía Asistida por Computador basado en Navegación Electromagnética para ser aplicado en procesos de neurocirugía. El sistema se desarrolló en el lenguaje C# sobre .NET, se escribieron envolturas para bibliotecas diseñadas en C++ y se utilizaron las bibliotecas VTK, ITK y DCMTK, el programa se alojó en la plata...
Chapter
Full-text available
This work is about the calibration of the magnetic tracker MiniBirdTM used to register spatial positions. This calibration is a procedure done necessarily to obtain important points for the execution of Computer Assisted Neuro-Surgery using 3D Images (CANS); as well as the reconstruction of three-dimensional objects inside a Virtual Reality environ...
Article
Full-text available
Esta investigación plantea el análisis comparativo de algoritmos desarrollados en ITK (Insight Toolkit) para la segmentación de imágenes. La evaluación se hace en imágenes médicas de ventrículos cerebrales humanos, seleccionando para el estudio los métodos de Magnitud del Gradiente y Umbralización Binaria. La metodología general está conformada por...
Conference Paper
Full-text available
Esta investigación plantea el análisis comparativo de algoritmos desarrollados en ITK (Insight Toolkit) para la segmentación de imágenes. La evaluación se hace en imágenes médicas de ventrículos cerebrales humanos, seleccionando para el estudio los métodos de Magnitud del Gradiente y Umbralización Binaria. La metodología general está conformada por...
Conference Paper
Full-text available
This research proposes an innovative method for obtaining a computer assisted anatomical model when the structures are complex to segment using either the traditional or advanced methods of image processing. Our method combines the medical knowledge of the organ to define the contours, and adds a Support Vector Machine (SVM) when the images are dif...
Conference Paper
Full-text available
Basal nuclei are brain structures related to motion control and treatment of neurological pathologies, such as Parkinson’s or Huntington’s diseases; therefore, to determine their location has great relevance for neurosurgical procedures planning. These structures are difficult to detect on MR images because they have fuzzy borders and present few c...
Conference Paper
Full-text available
This work creates a 3D anatomical models of the brain as well as its virtual images. It is to be applied in virtual training of neuroanatomy. These models are based on studies of Magnetic Resonance (MRI) and Computer Tomography (CT). These models contain information of the anatomical structures of the brain’s soft tissues. This research was develop...
Conference Paper
Full-text available
The segmentation of cerebral structures in medical images has numerous clinical applications. It can provide signifi cant aids for the diagnosis of some pathology. In this work, we propose a comparative study of the new segmentation method based on the theory of deformable models along with the front propagation method, which can make a semi-automa...
Conference Paper
Full-text available
This paper proposes a new segmentation method for echocardiogaphic images based on data fusion theory. This proposal consists on a data fusion system with two inputs: Input “A” corresponds to the gradient image after having made the pre-processing links to the acquisition, fi ltering and interpolation. Input “B” corresponds to a parametric equation...
Conference Paper
Full-text available
This work aimed to design a device that is capable of measuring the displacement of surgical needles during the process of training in minimally invasive neurosurgery, using stereotactic frame. This device can be used from data previously determined by the neurosurgeon in a planning process to achieve a goal within a model of patient, so that, in a...
Article
Full-text available
Actualmente se han mejorado mucho las técnicas de renderizado volumétrico directo basado en el mapeo de textura 3D. Sin embargo, todavía existen limitaciones en cuanto a la visualización 3D simultánea a partir de diferentes fuentes (es decir, la integración de imágenes multi-modales). Este trabajo presenta tres opciones para visualizar objetos a pa...
Chapter
Full-text available
Este trabajo presenta el desarrollo de un sistema automatizado de: estimulación, adquisición y procesamiento de imágenes pupilares (que incluye la segmentación y la visualización en tiempo real), provenientes de las respuestas fotomotora y consensual del iris; de manera que, el médico puede observar en la interfaz del sistema: la representación grá...
Chapter
Full-text available
Esta investigación propone un nuevo método de modelado de estructuras anatómicas cuando estas son difíciles de segmentar por los métodos tradicionales o aún utilizando métodos avanzados. Nuestro método combina el conocimiento médico del órgano para definir los contornos sobre imágenes difusas o ruidosas, y una máquina de soporte vectorial (SVM) par...
Chapter
Full-text available
La finalidad del trabajo es realizar la identificación de una persona utilizando únicamente la imagen de su huella dactilar. Para realizar esta actividad se desarrolló un sistema de análisis para las imágenes de las huellas. El sistema contesta dos preguntas: ¿Quien soy? ó ¿Dime si soy quien digo que soy? La primera pregunta se refiere a la identif...
Chapter
Full-text available
Este proyecto se puede ver como dos cadenas de procesamiento de reconstrucción y visualización, cada una de ellas se subdivide en varios módulos denominados: Adquisición, Filtraje, Segmentación, Reconstrucción, Modelaje y Visualización 3D. La segunda cadena de procesamiento utiliza un modelo a priori del órgano, el cual, es ajustado a los datos ext...
Chapter
Full-text available
Este documento describe un proyecto de planificación quirúrgica asistida por computador en el área de neurocirugía, el cual ha sido desarrollado durante los últimos dos años. Se presenta una síntesis de su soporte tecnológico y de sus logros. El proyecto se produce después de 16 años de experiencia en procesamiento de imágenes afianzada durante la...
Chapter
Full-text available
La evaluación médica con finalidades diagnósticas, para planificación de cirugías, entre otras; requiere del manejo amplio de técnicas de procesamiento de imágenes. En el caso de la ecografía 3D se pueden obtener representaciones tridimensionales basadas en imágenes ecocardiográficas convencionales, lo cual permite disminuir los costos, en comparac...
Chapter
Full-text available
El diagnóstico por imágenes y la cirugía son áreas de la medicina que se han beneficiado con el uso de software como herramientas de asistencia tecnológica, debido a que las aplicaciones en estas áreas tienen requisitos demandantes de procesamiento, interacción y visualización. Sin embargo, en nuestro país el desarrollo de este tipo de aplicaciones...
Article
Full-text available
Inspection and visualization of sections extracted from volume data help to improve the exploration of the information contained in the volumes, and to enhance the comprehension of it. Appearing of Graphics Process Units (GPUs) and specialized programming libraries has permitted the development of new techniques and algorithms for interactive extra...
Article
Full-text available
This paper proposes a new technique for 3D motion estimation of the left ventricle from a sequence of a heartbeat. Accurate motion estimation of the movement of cardiac walls has been shown to be very important for studying the cardiovascular illnesses. This technique is based on a processing chain from the acquisition to the 3D segmentation of the...
Chapter
Full-text available
The segmentation of cerebral structures in medical images has numerous clinical applications. It can provide significant aids for the diagnosis of some pathology. In this work, we propose a comparative study of the new segmentation method based on the theory of deformable models along with the front propagation method, which it can make an semiauto...
Chapter
Full-text available
This paper proposes a new technique for 3D motion estimation of the left ventricle from a sequence of a heartbeat. Accurate motion estimation of the movement of cardiac walls has been shown to be very important for studying the cardiovascular illnesses. This technique is based on a processing chain from the acquisition to the 3D segmentation of the...
Chapter
Full-text available
Inspection and visualization of sections extracted from volume data help to improve the exploration of the information contained in the volumes, and to enhance the comprehension of it. Appearing of Graphics Process Units (GPUs) and specialized programming libraries has permitted the development of new techniques and algorithms for interactive extra...
Article
Full-text available
This paper presents a new development of an automated system for: stimulation, acquisition and the pupilar image processing (it includes segmentation and visualization in real time), issued from the fhoto-motor and consensual response of the iris. The physician can observe in the system interface: a graphic representation of the variation and chang...
Article
Full-text available
This paper proposes an innovation in the application for image guided surgery using a comparative study of three different method of segmentation. This segmentation method is faster than the manual segmentation of images, with the advantage that it allows to use the same patient as anatomical reference, which has more precision than a generic atlas...
Chapter
Full-text available
The segmentation of brain structures from Magnetic resonance imaging, is a very important tool in the diagnostic and follow up of several pathologies of the central nervous system. The obtaining of the contours of brain structures presents following problems: the great volume of data and noises in the images introduced by the acquisition equipment....
Chapter
Full-text available
The new echocardiographic equipment produces volumes of 3D images. However, the processing and the information extraction of these volumetric data is troubled by complexity due to the high quantity of speckle noise, low resolution, and the loss of regions at the echocardiographic images. Our work presents a new methodology to extract the 3D informa...
Conference Paper
Full-text available
The segmentation of cerebral structures for medical images has numerous clinical applications. The segmentation can provide a significant aid for the diagnosis of some pathology. Several segmentation methods of anatomical structures have been published in the bibliography, but some of them need the intervention of an operator. For example, the algo...
Conference Paper
Full-text available
Direct volume rendering based on 3D-texture mapping has improved recently. [1]. However, simultaneous visualisation by different sources (multi-modality image integration) or, the single source of information from different time intervals, is yet limited [2]. This work presents three options to visualise objects, issued from two or more sources tha...
Book
Dynamic Segmentation and Modeling, Application to 3D Reconstruction of Echocardiographic images.