The evaluation of white blood cells is essential to assess the quality of the human immune system; however, the assessment of the blood smear depends on the pathologist’s expertise. Most machine learning tools make a one-level classification for white blood cell classification. This work presents a two-stage hybrid multi-level scheme that efficiently classifies four cell groups: lymphocytes and monocytes (mononuclear) and segmented neutrophils and eosinophils (polymorphonuclear). At the first level, a Faster R-CNN network is applied for the identification of the region of interest of white blood cells, together with the separation of mononuclear cells from polymorphonuclear cells. Once separated, two parallel convolutional neural networks with the MobileNet structure are used to recognize the subclasses in the second level. The results obtained using Monte Carlo cross-validation show that the proposed model has a performance metric of around 98.4% (accuracy, recall, precision, and F1-score). The proposed model represents a good alternative for computer-aided diagnosis (CAD) tools for supporting the pathologist in the clinical laboratory in assessing white blood cells from blood smear images.

No abstract

759Gorbanev -Pago por desempeño en sistema de salud Nivel de conocimiento sobre factores de riesgo cardiovascular en una comunidad de Naguanagua, Venezuela RESUMENObjetivo Evaluar el nivel de conocimiento de los factores de riesgo cardiovascular y asociarlo con alteraciones de los marcadores clínicos, antropométricos y bioquímicos de riesgo cardiovascular en una comunidad del Municipio Naguanagua, Venezuela. Métodos Se evaluaron 205 pacientes con edades comprendidas entre 18 y 77 años, a los cuales se les determinó peso, talla, circunferencia abdominal, presión arterial, glicemia y perfil lipídico. Se aplicó una encuesta para medir el nivel de conocimiento de los factores de riesgo cardiovascular. Resultados Se evidenció una alta frecuencia de obesidad abdominal (67 %) sobrepeso y obesidad (38 %) e Hipertensión (26 %). Casi 60 % de los participantes afirmó conocer los factores de riesgo cardiovascular, pero sólo 14,7 % reconocieron los once factores que se consideraron para definir el nivel de conocimiento. Más de la mitad de los participantes mostraron un bajo nivel de conocimiento de factores de riesgo cardiovasculares cuyos niveles promedio de colesterol total, LDL colesterol y triglicéridos fueron significativamente menores a los del grupo de alto nivel de conocimiento. Conclusión Se encontró un porcentaje elevado de individuos con bajo nivel de conocimiento de los factores de riesgo cardiovascular y una frecuencia de alteraciones de los parámetros clínicos, antropométricos y bioquímicos mayor entre los participantes con alto nivel de conocimiento, confirmando la necesidad de ejecutar estrategias que no sólo eleven el nivel de conocimiento de las comunidades venezolanas, sino también motiven efectivamente a la adopción de un estilo de vida asociado a la reducción de los factores de riesgo cardiovascular y al autocuidado de la salud.Rev. salud pública. 13 (5): 759-771, 2011759

Medical image quality is crucial to obtaining reliable diagnostics. Most quality controls rely on routine tests using phantoms, which do not reflect closely the reality of images obtained on patients and do not reflect directly the quality perceived by radiologists. The purpose of this work is to develop a method that classifies the image quality perceived by radiologists in MR images. The focus was set on lumbar images as they are widely used with different challenges. Three neuroradiologists evaluated the image quality of a dataset that included T1-weighting images in axial and sagittal orientation, and sagittal T2-weighting. In parallel, we introduced the computational assessment using a wide range of features extracted from the images, then fed them into a classifier system. A total of 95 exams were used, from our local hospital and a public database, and part of the images was manipulated to broaden the distribution quality of the dataset. Good recall of 82% and an area under curve (AUC) of 77% were obtained on average in testing condition, using a Support Vector Machine. Even though the actual implementation still relies on user interaction to extract features, the results are promising with respect to a potential implementation for monitoring image quality online with the acquisition process.