Stroke Tissue Pattern Recognition Based on CT Texture Analysis

Ostrek, Grzegorz; Nowakowski, Artur; Jasionowska, Magdalena; Przelaskowski, Artur; Szopiński, Kazimierz

doi:10.1007/978-3-319-26227-7_8

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, brain lesions, especially WMHs, have significant variations with respect to size, shape, intensity, and location, which makes their automatic and accurate segmentation challenging [197]. For example, even though stroke is considered to be easy to recognize and differentiate from other WMHs for experienced neuroradiologists, it could be a challenge and a difficult task for general physicians, especially in rural areas or in developing countries where there are shortages of radiologists and neurologists, and for that reason, it is important to employ computer-assisted methods as well as telemedicine [213,214]. Montemurro and Perrini [215] state that the current COVID-19 pandemic situation further underscores the importance of telemedicine in neurology and other health aspects (e.g., ophthalmology [216]), is no longer a futuristic concept, and has become new normal (see, for example, [217]).…”

Section: Discussionmentioning

confidence: 99%

MR Images, Brain Lesions, and Deep Learning

2021

View full text Add to dashboard Cite

Medical brain image analysis is a necessary step in computer-assisted/computer-aided diagnosis (CAD) systems. Advancements in both hardware and software in the past few years have led to improved segmentation and classification of various diseases. In the present work, we review the published literature on systems and algorithms that allow for classification, identification, and detection of white matter hyperintensities (WMHs) of brain magnetic resonance (MR) images, specifically in cases of ischemic stroke and demyelinating diseases. For the selection criteria, we used bibliometric networks. Of a total of 140 documents, we selected 38 articles that deal with the main objectives of this study. Based on the analysis and discussion of the revised documents, there is constant growth in the research and development of new deep learning models to achieve the highest accuracy and reliability of the segmentation of ischemic and demyelinating lesions. Models with good performance metrics (e.g., Dice similarity coefficient, DSC: 0.99) were found; however, there is little practical application due to the use of small datasets and a lack of reproducibility. Therefore, the main conclusion is that there should be multidisciplinary research groups to overcome the gap between CAD developments and their deployment in the clinical environment.

show abstract

Section: Discussionmentioning

confidence: 99%

MR Images, Brain Lesions, and Deep Learning

2021

View full text Add to dashboard Cite

show abstract

“…However, brain lesions, and especially the WMHs have significant variants with respect to size, shape, intensity, and location, which makes their automatic and accurate segmentation challenging [159]; e.g. in spite of the fact that stroke is considered to be easy to recognize and differentiate from other WMHs for experienced neuroradiologists, it could be a challenge and difficult task for general physicians, especially in rural areas or in developing countries where there are shortages of radiologists and neurologists and, for that reason it is important to employ computer-assisted methods as well as telemedicine [180], in this sense, e.g. Mollura et al, [181] gives some strategies in order to get an effective and sustainable implementation of radiology in developing countries.…”

Section: Discussionmentioning

confidence: 99%

MRI Images, Brain Lesions and Deep Learning

Castillo¹,

Lakshminarayanan²,

Rodríguez-Álvarez³

2021

Preprint

View full text Add to dashboard Cite

Medical brain image analysis is a necessary step in the Computers Assisted /Aided Diagnosis (CAD) systems. Advancements in both hardware and software in the past few years have led to improved segmentation and classification of various diseases. In the present work, we review the published literature on systems and algorithms that allow for classification, identification, and detection of White Matter Hyperintensities (WMHs) of brain MRI images specifically in cases of ischemic stroke and demyelinating diseases. For the selection criteria, we used the bibliometric networks. Out of a total of 140 documents we selected 38 articles that deal with the main objectives of this study. Based on the analysis and discussion of the revised documents, there is constant growth in the research and proposal of new models of deep learning to achieve the highest accuracy and reliability of the segmentation of ischemic and demyelinating lesions. Models with indicators (Dice Score, DSC: 0.99) were found, however with little practical application due to the uses of small datasets and lack of reproducibility. Therefore, the main conclusion is to establish multidisciplinary research groups to overcome the gap between CAD developments and their complete utilization in the clinical environment.

show abstract

“…Por ejemplo, el diseño utilizado para la alimentación de árboles de decisión en [46] se formó de un conjunto de 14 atributos obtenidos de las características sugeridas por especialistas, formando un conjunto de referencia que ayudan en la descripción de ECV isquémica; algo parecido se plantea en [27], donde usando el algoritmo K-NN y clasificadores bayesianos, para extraer características de una imagen médica se toman decisiones con respecto a la patología de una estructura o tejido ateromatosa. Para el diagnóstico de la enfermedad de Alzheimer [47], se hace un etiquetado de voxels a partir la segmentación hipo campal dimensional o mediante una red neuronal pulsante (SNN, por sus siglas en inglés) [69]. Para representar la actividad normal y anormal del cerebro, se usan diversas técnicas como: características binarias, análisis de componentes principales, análisis discriminante lineal, código de cadena, transformación de características invariante a escala, filtrado Gabor, distancia euclidiana, red neuronal artificial, máquinas de soporte vectorial [13], matriz de co-ocurrencia de niveles de grises [39,40], descriptores de textura Haralick [44], umbralización (cambio en los niveles de intensidad); Stier et al [43] utiliza una red neuronal convolucional (CNN) para generar un modelo predictivo.…”

Section: Representación Y Descripción (Extracción Y Selección De Caraunclassified

Estado del arte y elementos del reconocimiento automático de imágenes del cerebro

Cortés-Martínez¹,

Mejía-Lavalle²

2017

RCS

View full text Add to dashboard Cite

Resumen. El área de la Inteligencia Artificial ha incursionando en el ámbito médico con el propósito de apoyar en el reconocimiento automático de imágenes del cerebro. Una de las enfermedades que ha ido en aumento en la última década es la Enfermedad Cerebro Vascular, cuyo conjunto de enfermedades, afectan los vasos sanguíneos cerebrales. Dados los efectos que puede causar este tipo de enfermedad, es importante caracterizar las fuentes que generan imágenes médicas y los procedimientos empleados para mejorarlas e interpretarlas. El documento describe los avances reportados en la literatura en relación a las fuentes que obtienen las imágenes y las etapas seguidas para su reconocimiento. El trabajo considera que existe la oportunidad de mejorar o desarrollar más algoritmos avanzados, que ofrezca un nivel más alto en la detección de enfermedades en imágenes del cerebro. Palabras clave: enfermedad cerebro vascular, reconocimiento de imágenes médicas, inteligencia artificial, técnicas de visión artificial. State of the Art and Elements of Automatic Image Recognition of the Brain Abstract. Artificial Intelligence area has penetrated the medical field with the purpose of supporting the automatic recognition of brain imaging. One of the diseases that has been increasing in the last decade are Brain Stroke, whose set of diseases, affect the cerebral blood vessels. Given that effects that can cause this type of disease, it is important to characterize the sources that generate medical images and the methods used to improve and interpret them. This paper describes the advances reported in the literature in relation to the sources that obtain the images and the stages followed for their recognition. Moreover considers that there is an opportunity to improve and development of advanced algorithms, which will offer a higher level in the detection of diseases in brain images.

show abstract

Stroke Tissue Pattern Recognition Based on CT Texture Analysis

Cited by 4 publications

References 19 publications

MR Images, Brain Lesions, and Deep Learning

MR Images, Brain Lesions, and Deep Learning

MRI Images, Brain Lesions and Deep Learning

Estado del arte y elementos del reconocimiento automático de imágenes del cerebro

Contact Info

Product

Resources

About