Analysis of domain shift in whole prostate gland, zonal and lesions segmentation and detection, using multicentric retrospective data.

Despite being one of the most prevalent forms of cancer, prostate cancer (PCa) shows a significantly high survival rate, provided there is timely detection and treatment. Computational methods can help make this detection process considerably faster and more robust. However, some modern machine-learning approaches require accurate segmentation of the prostate gland and the index lesion. Since performing manual segmentations is a very time-consuming task, and highly prone to inter-observer variability, there is a need to develop robust semi-automatic segmentation models. In this work, we leverage the large and highly diverse ProstateNet dataset, which includes 638 whole gland and 461 lesion segmentation masks, from 3 different scanner manufacturers provided by 14 institutions, in addition to other 3 independent public datasets, to train accurate and robust segmentation models for the whole prostate gland, zones and lesions. We show that models trained on large amounts of diverse data are better at generalizing to data from other institutions and obtained with other manufacturers, outperforming models trained on single-institution single-manufacturer datasets in all segmentation tasks. Furthermore, we show that lesion segmentation models trained on ProstateNet can be reliably used as lesion detection models.

Delirium no doente critico: fatores de risco modificáveis / Delirium in the critically ill patient: modifiable risk factors

A literatura científica define delirium, como síndrome de disfunção mental, multifatorial e com maior prevalência em cuidados intensivos, que exige elevado nível atencional e cuidativo, não só pelo quadro em si, mas sobretudo pelas respetivas consequências. A presença de delirium em contexto do doente critico, desencadeia potencialmente, aumento o tempo de internamento, a mortalidade hospitalar e pós-alta, declínio cognitivo e funcional, custos globais de saúde e sobretudo o stress para a própria pessoa, para a família e para os profissionais, sendo a sua presença um determinante preditor de prognóstico. A monitorização desta síndrome, através de escalas adequadas e validadas, é essencial para a deteção precoce, prevenção e tratamento. O objetivo geral deste estudo é identificar fatores de risco modificáveis associados ao desenvolvimento de delirium em doentes internados no Serviço de Medicina Intensiva (SMI) da Unidade Local de Saúde do Nordeste (ULSNE). Foi desenvolvida um estudo observacional, transversal e de metodologia quantitativa, desenvolvida a partir dos registos de 190 momentos de observação de delirium - entre 15 de dezembro de 2019 a 31 de fevereiro de 2020 - numa amostra de 57 doentes críticos admitidos no SMI, e dos dados emergentes, pela aplicação de escalas específicas e um formulário de recolha de dados, que foram submetidos a tratamento, pelo programa estatístico SPSS, versão 23.0. Os resultados revelam o perfil sociodemográfico desta amostra de doentes críticos, caraterizado, por serem do sexo do sexo masculino, com idade superior a 65 anos. O perfil clínico à admissão no SMI enquadrava-o na categoria diagnóstica médica e apresentava HTA como fator prévio. A prevalência de delirium identificada nas 190 observações foi de 38,9%, que corrobora intervalos obtidos em estudos prévios. Identificaram-se vários fatores de risco potencialmente modificáveis, nomeadamente gestão de utilização de cateter venoso central, sonda nasogástrica, nutrição entérica, restrição física, imobilidade e sedação (propofol). Em conclusão e após a concretização dos objetivos propostos, foram identificados os fatores de risco modificáveis presentes no SMI da ULSNE. Não existindo ainda consenso na comunidade científica sobre medidas farmacológicas para a prevenção e tratamento deste fenómeno, pretende-se que todos os doentes críticos adultos sejam diariamente monitorizados, com escalas validadas para o país e região onde se inserem, identificando os fatores de risco, nomeadamente os modificáveis, intervindo com as medidas não farmacológicas/preventivas que, estas sim, têm vindo a reunir maior consenso internacional.

The scientific literature defines delirium as a syndrome of mental dysfunction, multifactorial and with a higher prevalence in intensive care, which requires a high level of care and care, not only because of the condition itself, but above all because of the respective consequences. The presence of delirium in the context of the critical patient potentially triggers an increase in hospital stay, hospital and post-discharge mortality, cognitive and functional decline, global health costs and, above all, stress for the person himself, for the family and for professionals, their presence being a determining predictor of prognosis. Monitoring of this syndrome, using appropriate and validated scales, is essential for early detection, prevention and treatment. The general objective of this study is to identify modifiable risk factors associated with the development of delirium in patients admitted to the Intensive Care Service of the Northeast Local Health Unit. An observational, transversal and quantitative methodology study was developed, based on the records of 190 moments of observation of delirium - between December 15, 2019 and February 31, 2020 - in a sample of 57 critically ill patients admitted to the SMI, and of emerging data, by applying specific scales and a data collection, which were submitted to treatment by the SPSS statistical program, version 23.0. The results reveal the sociodemographic profile of this sample of critically ill patients, characterized by being male, over 65 years of age. The clinical profile on admission to the SMI included him in the medical diagnostic category and had hypertension as a previous factor. The prevalence of delirium identified in 190 observations was 38.9%, which corroborates intervals obtained in previous studies. There was a statistical relationship between the development of delirium and the central venous catheter, nasogastric tube, enteral nutrition, physical restriction, early mobilization and sedation (propofol). In conclusion and after the achievement of the proposed objectives, the modifiable risk factors present in ULSNE's SMI were identified. As there is still no consensus in the scientific community on pharmacological measures for the prevention and treatment of this phenomenon, it is intended that all adult critical patients are monitored daily, with scales validated for the country and region where they operate, identifying the risk factors, namely the modifiable ones, intervening with the non-pharmacological / preventive measures that, yes, these have been gathering greater international consensus.