Instituto de Instrumentación para Imagen Molecular
Cargando...
Fecha de establecimiento
Ciudad
País
ID
Descripción
81 resultados
Resultados de la búsqueda de publicaciones
Mostrando 1 - 10 de 81
- PublicaciónBRANET: A mobil application for breast image classification based on deep learning algorithms(Springer-Verlag, 2024-05-02) Jimenez-Gaona, Yuliana; Rodríguez Álvarez, María José; Castillo-Malla, Darwin Patricio; García, Santiago; Carrión, Diana; Corral, Patricio; Lakshminarayanan, Vasudevan; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen Molecular; Generalitat Valenciana; Agencia Estatal de Investigación; Universitat Politècnica de València; Universidad Técnica Particular de Loja[EN] Mobile health apps are widely used for breast cancer detection using artifcial intelligence algorithms, providing radiologists with second opinions and reducing false diagnoses. This study aims to develop an open-source mobile app named "BraNet" for 2D breast imaging segmentation and classifcation using deep learning algorithms. During the phase of-line, an SNGAN model was previously trained for synthetic image generation, and subsequently, these images were used to pre-trained SAM and ResNet18 segmentation and classifcation models. During phase online, the BraNet app was developed using the react native framework, ofering a modular deep-learning pipeline for mammography (DM) and ultrasound (US) breast imaging classifcation. This application operates on a client-server architecture and was implemented in Python for iOS and Android devices. Then, two diagnostic radiologists were given a reading test of 290 total original RoI images to assign the perceived breast tissue type. The reader's agreement was assessed using the kappa coefcient. The BraNet App Mobil exhibited the highest accuracy in benign and malignant US images (94.7%/93.6%) classifcation compared to DM during training I (80.9%/76.9%) and training II (73.7/72.3%). The information contrasts with radiological experts¿ accuracy, with DM classifcation being 29%, concerning US 70% for both readers, because they achieved a higher accuracy in US ROI classifcation than DM images. The kappa value indicates a fair agreement (0.3) for DM images and moderate agreement (0.4) for US images in both readers. It means that not only the amount of data is essential in training deep learning algorithms. Also, it is vital to consider the variety of abnormalities, especially in the mammography data, where several BI-RADS categories are present (microcalcifcations, nodules, mass, asymmetry, and dense breasts) and can afect the API accuracy model.
- PublicaciónDerivadas de funciones reales. Regla de la cadena(Universitat Politècnica de València, 2016-05-17) Rodríguez Álvarez, María José; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen MolecularEste objeto de aprendizaje esta dedicado al calculo de derivadas haciendo uso de la regla de la cadena.
- PublicaciónMagnetic resonance brain images algorithm to identify demyelinating and ischemic diseases(The International Society for Optical Engineering., 2018) Castillo-Malla, Darwin Patricio; Samaniego, R.; Jimenez, Y.; Cuenca González, María Llanos; Vivanco, O.; Rodríguez Álvarez, María José; Departamento de Organización de Empresas; Departamento de Matemática Aplicada; Centro de Investigación en Gestión e Ingeniería de Producción; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen Molecular[EN] Brain demyelination lesions occur due to damage of the myelin layer of nerve fibers, this deterioration is the cause of pathologies such as multiple sclerosis, leukodystrophy, encephalomyelitis. Brain ischemia is the interruption of the blood supply to the brain, and the flow of oxygen and nutrients needed to maintain the correct functioning of brain cells. This project presents the results of an algorithm processing images with the the main objective of identify and differentiate between demyelination and ischemic brain diseases through the automatic detection, classification and identification of their features found in the magnetic resonance images. The sequences of images used were T1, T2, and FLAIR and with a dataset of 300 patients with and without these or other pathologies, respectively. The algorithm in this stage uses Discrete Wavelet Transform (DWT), principal component analysis (PCA) and a kernel support vector machine (SVM). The algorithm developed indicates a 75% of accuracy, for that reason, with an effective validation could be applied for the fast diagnosis and contribute to an effective treatment of these brain diseases especially in the rural places.
- PublicaciónRecurrencias no homogéneas lineales de segundo orden con coeficientes constantes(Universitat Politècnica de València, 2015-04-29T06:10:30Z) Rodríguez Álvarez, María José; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen MolecularEn este vídeo se explica brevemente como resolver una recurrencia no homogénea con coeficientes constantes.
- PublicaciónIntegrales con Mathematica(Universitat Politècnica de València, 2017-06-13) Rodríguez Álvarez, María José; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen MolecularEste vídeo esta pensado para hacer una introducción a la utilización de Mathematica para hacer integrales
- PublicaciónMTS image analyzer: a software tool to identify mesial temporal sclerosis in MRI images(SPIE, The International Society for Optical Engineering, 2021-08-01) Castillo, D.; Macas, J.; Samaniego, R.; Jiménez, Y.; Díaz, P.; Rodríguez Álvarez, María José; Lakshminarayanan, Vasudevan; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen Molecular[EN] Epilepsy is a chronic neurological disorder that causes unprovoked and recurrent seizures which according to WHO affects approximately 50 million people worldwide. Functional magnetic resonance images (MRI) help to identify certain affected areas of the brain, namely, the gliosis and hippocampal volume loss. These losses cause complex epilepsy, and is known as hippocampal sclerosis or Mesial Temporal Sclerosis (MTS). This work presents the development of a Computer Aided Diagnosis CAD system software package) that can be used to identify the characteristics and patterns of MTS from brain magnetic resonance images. The image processing techniques involve texture analysis, statistical features, evaluation of the 3D Region of interest (ROI), and threshold analysis. The software allows the automatic evaluation of the degeneration of hippocampal structures, hippocampal volume and signal intensity. We will describe and demonstrate the software (which can currently be accessed on GitHub). It is expected that this tool will be useful in new neurology/radiology specialists and can serve as a secondary diagnosis. However, it is necessary to validate the software system qualitatively and quantitatively in order to get more effectiveness and efficiency in a real-world clinical application.
- PublicaciónDeep learning for MRI-based CT synthesis: a comparison of MRI sequences and neural network architectures(IEEE, 2019-11-02) Larroza, Andrés; Moliner Martínez, Laura; Álvarez-Gómez, Juan Manuel; Oliver Gil, Sandra; Espinós-Morató, Héctor; Vergara-Díaz, Marina; Rodríguez Álvarez, María José; Departamento de Física Aplicada; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Industrial; Instituto Universitario de Seguridad Industrial, Radiofísica y Medioambiental; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen Molecular; European Regional Development Fund; Ministerio de Economía y Competitividad[EN] Synthetic computed tomography (CT) images derived from magnetic resonance images (MRI) are of interest for radiotherapy planning and positron emission tomography (PET) attenuation correction. In recent years, deep learning implementations have demonstrated improvement over atlasbased and segmentation-based methods. Nevertheless, several open questions remain to be addressed, such as which is the best of MRI sequences and neural network architectures. In this work, we compared the performance of different combinations of two common MRI sequences (T1- and T2-weighted), and three state-of-the-art neural networks designed for medical image processing (Vnet, HighRes3dNet and ScaleNet). The experiments were conducted on brain datasets from a public database. Our results suggest that T1 images perform better than T2, but the results further improve when combining both sequences. The lowest mean average error over the entire head (MAE = 101.76 ± 10.4 HU) was achieved combining T1 and T2 scans with HighRes3dNet. All tested deep learning models achieved significantly lower MAE (p < 0.01) than a well-known atlas-based method.
- PublicaciónSmall animal PET scanner based on monolithic LYSO crystals: Performance evaluation(American Association of Physicists in Medicine: Medical Physics, 2012) Sánchez Martínez, Filomeno; Moliner Martínez, Laura; Correcher, C.; González Martínez, Antonio Javier; Orero Palomares, Abel; Carles Fariña, Montserrat; Soriano Asensi, Antonio; Rodríguez Álvarez, María José; Medina, L.A; Mora Mas, Francisco José; Benlloch Baviera, Jose María; Departamento de Ingeniería Electrónica; Escuela Técnica Superior de Ingeniería de Telecomunicación; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen Molecular; Ministerio de Ciencia e Innovación; Generalitat ValencianaPurpose: The authors have developed a small animal Positron emission tomography(PET)scanner based on monolithic LYSO crystals coupled to multi-anode photomultiplier tubes (MA-PMTs). In this study, the authors report on the design, calibration procedure, and performance evaluation of a PET system that the authors have developed using this innovative nonpixelated detector design. Methods : The scanner is made up of eight compact modules forming an octagon with an axial field of view (FOV) of 40 mm and a transaxial FOV of 80 mm diameter. In order to fully determine its performance, a recently issued National Electrical Manufacturers Association (NEMA) NU-4 protocol, specifically developed for small animal PETscanners, has been followed. By measuring the width of light distribution collected in the MA-PMT the authors are able to determine depth of interaction (DOI), thus making the proper identification of lines of response (LORs) with large incidence angles possible. PET performances are compared with those obtained with currently commercially available small animal PETscanners. Results : At axial center when the point-like source is located at 5 mm from the radial center, the spatial resolution measured was 1.65, 1.80, and 1.86 mm full width at half maximum (FWHM) for radial, tangential, and axial image profiles, respectively. A system scatter fraction of 7.5% (mouse-like phantom) and 13% (rat-like phantom) was obtained, while the maximum noise equivalent count rate (NECR) was 16.9 kcps at 12.7 MBq (0.37 MBq/ml) for mouse-like phantom and 12.8 kcps at 12.4 MBq (0.042 MBq/ml) for rat-like phantom The peak absolute sensitivity in the center of the FOV is 2% for a 30% peak energy window. Several animal images are also presented. Conclusions: The overall performance of our small animal PET is comparable to that obtained with much more complex crystal pixelated PET systems. Moreover, the new proposed PET produces high-quality images suitable for studies with small animals.
- PublicaciónIdentifying Demyelinating and Ischemia brain diseases through magnetic resonance images processing(IEEE, 2019-11-02) Castillo, Darwin P.; Samaniego, René J.; Jimenez, Yuliana; Cuenca, Luis A.; Vivanco, Oscar A; Álvarez-Gómez, Juan Manuel; Rodríguez Álvarez, María José; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen Molecular[EN] ¿Brain Magnetic Resonance Images are a very useful tool for the diagnosis of brain diseases and analyse brain changes. The appropriate processing (neuroimaging) can help to identify, measure and classify different lesions or abnormalities. The principal aim of this project is to develop an algorithm that can identify and differentiate ischemic disease than the demyelinating disease in the brain through the processing of magnetic resonance images. The damage and deterioration of the myelin layer of nerve fibers (brain demyelination) is the cause of pathologies like multiple sclerosis. Ischemic stroke is produced by the interruption of the blood supply to the brain. The dataset used was composed of images T1, T2 and FLAIR modalities of 90 patients from the hospital. For the segmentation of the features, the identification and the classification of the lesions have used the methods of Discrete Wavelet Transform (DWT), principal component analysis (PCA) and support vector machine (SVM). The results present 60 to 80% of accuracy to identify and differentiate the diseases.
- PublicaciónResults of a combined monolithic crystal and an array of ASICs controlled SiPMs(Elsevier, 2014-01) Conde Castellanos, Pablo Eloy; González Martínez, Antonio Javier; Hernández Hernández, Liczandro; Bellido, P.; Iborra Carreres, Amadeo; Crespo Navarro, Efren; Moliner Martínez, Laura; Rigla, JP.; Rodríguez Álvarez, María José; Sánchez, F.; Seimetz, Michael; Soriano Asensi, Antonio; Vidal San Sebastián, Luis Fernando; Benlloch Baviera, Jose María; Departamento de Matemática Aplicada; Escuela Técnica Superior de Ingeniería Informática; Instituto de Instrumentación para Imagen Molecular; European Regional Development Fund; Generalitat Valenciana; Ministerio de Ciencia e Innovación; Centro para el Desarrollo Tecnológico Industrial[EN] In this work we present the energy and spatial resolutions we have obtained for a γ ray detector based on a monolithic LYSO crystal coupled to an array of 256 SiPMs. Two crystal configurations of the same trapezoidal shape have been tried. In one approach all surfaces were black painted but the exit one facing the photosensor array which was polished. The other approach included a retroreflector (RR) layer coupled to the entrance face of the crystal powering the amount of transmitted light to the photosensors. Two coupling media between the scintillator and the SiPM array were used, namely direct coupling by means of optical grease and coupling through an array of light guides. Since the same operational voltage was supplied to the entire array, it was needed to equalize their gains before feeding their signals to the Data Acquisition system. Such a job was performed by means of 4 scalable Application Specific Circuits (ASICs). An energy resolution of about 24.4% has been achieved for the direct coupling with the RR layer together with a spatial resolution of approximately 2.9 mm at the detector center. With the light guides coupling the effects of image compression at the edges are significantly minimized, but worsening the energy resolution to about 33.1% with a spatial resolution nearing 4 mm at the detector center. & 2013 Elsevier B.V. All rights reserved.