ABSTRACT
ABSTRACT The novel coronavirus (COVID-19) is a disease that mainly affects the lung tissue. The detection of lesions caused by this disease can help to provide an adequate treatment and monitoring its evolution. This research focuses on the bi- nary classification of lung lesions caused by COVID-19 in images of computed tomography (CT) using deep learning. The database used in the experiments comes from two independent repositories, which contains tomographic scans of patients with a positive diagnosis of COVID-19. The output layers of four pre-trained convolutional networks were adapted to the proposed task and re-trained using the fine-tuning technique. The models were validated with test images from the two database's repositories. The model VGG19, considering one of the repositories, showed the best performance with 88% and 90.2% of accuracy and recall, respectively. The model combination using the soft voting technique presented the highest accuracy (84.4%), with a recall of 94.4% employing the data from the other repository. The area under the receiver operating characteristic curve was 0.92 at best. The proposed method based on deep learning represents a valuable tool to automatically classify COVID-19 lesions on CT images and could also be used to assess the extent of lung infection.
ABSTRACT
Introducción. La transmisión del SARS-CoV-2 principalmente se da por gotas y contacto cercano con las per-sonas infectadas, pero los aerosoles parecen ser también una fuente de infección. El neumotórax espontáneo o secundario puede presentarse en pacientes con COVID-19, ayudado por patologías de base como la enfermedad pulmonar obstructiva crónica. Es necesario garantizar procedimientos seguros para los pacientes y buscar todas las medidas posibles para la protección del personal de la salud, por eso el drenaje de neumotórax con catéter pleural en lugar de sonda de toracostomía puede ser una de ellas.El objetivo de este estudio es presentar a los cirujanos una alternativa a la toracostomía tradicional, mediante la utilización de catéteres de menor diámetro, para la resolución de la ocupación pleural.Aspectos Técnicos. Se presenta el protocolo para inserción segura de un catéter pleural para el drenaje de neumotórax, mediante un sistema completamente cerrado, y se dan recomendaciones sobre el uso de filtros virales y solución viricida en el sistema de drenaje pleural conectado al catéter. Conclusión. El estado de pandemia por COVID-19 y el riesgo que representa para los profesionales de la salud la exposición a fuentes de transmisión durante procedimientos generadores de aerosoles, hace que se deban extremar las medidas para evitar el contagio.
Introduction. The transmission of SARS-CoV-2 mainly occurs by drops and close contact with infected people, but aerosols also seem to be a source of infection. Spontaneous or secondary pneumothorax can occur in patients with COVID-19, helped by underlying pathologies such as chronic obstructive pulmonary disease. It is necessary to guarantee safe procedures for patients and to seek all possible measures for the protection of health personnel, so drainage of pneumothorax with a pleural catheter instead of a thoracostomy tube may be one of those. The objective of this study is to present surgeons with an alternative to traditional thoracostomy, using smaller diameter catheters, to resolve pleural occupancy.Technical aspects. The protocol for the safe insertion of a pleural catheter for pneumothorax drainage is presented, using a completely closed system, and recommendations are given on the use of viral filters and viricidal solution in the pleural drainage system connected to the catheter.Conclusions. The state of the COVID-19 pandemic and the risk that exposure to sources of transmission sources during aerosol-generating procedures represents for health professionals means that extreme measures must be taken to avoid contagion.
Subject(s)
Humans , Betacoronavirus , Pneumothorax , Thoracostomy , Coronavirus InfectionsABSTRACT
Background: The Postgraduate Hospital Education Environment Measure (PHEEM) questionnaire, is a valid and reliable instrument to measure the educational environment (EE) in postgraduate medical education. Aim: To evaluate the EE perceived by the residents of a postgraduate training program using the PHEEM. Material and Methods: The PHEEM was applied in 2010-2011 in 35 specialty programs. We calculated their individual results and compared means of both global and individual domain scores of the PHEEM, by gender, university of origin and nationality. Cronbach's alpha coefficients and D study (Generalizability theory) were performed for reliability. Results: Three hundred eighteen residents were surveyed (75.7% of the total universe). The mean score of the PHEEM was 105.09 ± 22.46 (65.7% of the maximal score) which is considered a positive EE. The instrument is highly reliable (Cronbach's alpha = 0.934). The D study found that 15 subjects are required to obtain reliable results (G coefficient = 0.813). There were no significant differences between gender and university of origin. Foreigners evaluated better the EE than Chileans and racism was not perceived. The programs showed a safe physical environment and teachers with good clinical skills. The negative aspects perceived were a lack of information about working hours, insufficient academic counseling, and scanty time left for extracurricular activities. Conclusions: This questionnaire allowed us to identify positive aspects of the EE, and areas to be improved in the specialty programs. The PHEEM is a useful instrument to evaluate the EE in Spanish-speaking participants of medical specialty programs.
Subject(s)
Female , Humans , Male , Education, Medical, Graduate/standards , Surveys and Questionnaires/standards , Social Environment , Brazil , Reproducibility of ResultsABSTRACT
Las metástasis hematógenas son la mayor causa de mortalidad en el cáncer de mama. Está documentado que una vez las células tumorales se diseminan el resultado es, generalmente, letal. Las células tumorales circulantes han sido consideradas por largo tiempo un reflejo de la agresividad de los tumores, y entre ellos uno de los más agresivos es el cáncer de mama metastásico. Los primeros resultados clínicos han permitido determinar una fuerte relación entre la detección y el número de las células tumorales circulantes, como un valor pronóstico y como marcador de la actividad antitumoral del tratamiento. El análisis inmunomagnético utilizando una nueva metodología permite determinar que un recuento de 5 células tumorales circulantes o más en 7,5 ml de sangre, en cualquier fase de la enfermedad, se asocia a un mal pronóstico, y es predictivo de una supervivencia global más corta.
Hematogenous metastasis is the major cause of mortality in breast cancer. Evidence indicates that tumor cells escape from the primary tumor mass into the blood stream and that these disseminated cells are the source of increased lethality. Circulating or metastatic tumour cells have been considered as useful indicators of the aggressiveness of breast cancer tumours. The first clinical results obtained with such assays strongly suggest that in metastatic breast cancer, circulating tumour cells detection and enumeration can be used to estimate prognosis and may serve as an early marker to assess anti-tumour activity of a treatment. Immunomagnetic analysis using a new methodology, determine that a circulating tumour cells count of 5 or more per 7,5 ml of blood, at any time during the course of the disease is associated with a poor prognosis and is predictive of shorter progression and overall survival.
Subject(s)
Humans , Female , Breast Neoplasms , Neoplasm Metastasis , Survival Analysis , Immunomagnetic Separation/classification , Immunomagnetic Separation/methods , ColombiaABSTRACT
Contenido: Método de diagnóstico por imágenes. Sistema respiratorio, mediastino y diafragma. Corazón y sistema circulatorio. Abdomen y pelvis. Sistema digestivo. Sistema urinario. Sistema ginecológico y obstetricia. Sistema musculoesquelético y tejidos blandos. Cabeza y cuello. Sistema nervios central. Radiología intervencionista...