Publicação: Avaliação numérica da dose ocupacional em procedimentos intervencionistas utilizando métodos de deep learning em tempo real
Carregando...
Tipo do documento
Data
Direito de acesso
Área do conhecimento
CNPQ::CIENCIAS EXATAS E DA TERRA
Título da Revista
ISSN da Revista
Título de Volume
Autores
Orientador
Coorientador
Resumo
Este estudo aborda a avaliação da dose nos órgãos/tecidos, fundamentada na posição espacial do médico (representado por um manequim) durante o procedimento de radiologia intervencionista. O objetivo principal foi analisar a capacidade de previsão, considerando diferentes distâncias em relação ao tubo de raios-X, em diferentes órgãos/tecidos. Os métodos aplicados incluíram um modelo de previsão de baixo custo de treinamento, porém, com limitações específicas, destinado a um tipo de procedimento considerando pacientes imóveis, gênero fixo e condições estáticas do equipamento de raios-X. Restringir o movimento do médico dentro da área dos marcadores foi crucial para reduzir deformações na imagem. Os resultados destacaram que, em órgãos pequenos, como a próstata, ocorreram as maiores diferenças entre os valores de dose preditos e os calculados com o MCNP6.2. Os resultados ressaltam a viabilidade da integração do modelo Multilayer Perceptron (MLP), utilizado para fazer a predição de dose em cada órgão, com o modelo YOLOv4, para identificação em tempo real das posições espaciais do médico. Essa integração apresenta a vantagem de ser de baixo custo, sendo, assim, um recurso crucial para monitorar os valores de doses da equipe médica durante procedimentos de radiologia intervencionista, embora ainda existam oportunidades de melhoria identificadas para ambos os modelos.
Abstract
This study addresses the assessment of dose to organs/tissues, based on the spatial position
of the physician during the interventional radiology procedure. The main objective was to
analyze the prediction capacity, considering different distances in relation to the X-ray
tube, in different organs/tissues. The methods applied included a prediction model with
low training cost, however, with specific limitations, intended for a type of procedure
considering immobile patients, fixed gender and static conditions of the X-ray equipment.
Restricting the physician’s movement within the marker area was crucial to reducing
image deformation. The results highlighted that, in small organs, such as the prostate, the
greatest differences occurred between the predicted dose values and those calculated with
MCNP6.2. The results highlight the feasibility of integrating the Multilayer Perceptron
(MLP) model, used to predict doses in each organ, with the YOLOv4 model, for real-time
identification of the doctor’s spatial positions.This integration has the advantage of being
low cost, thus being a crucial resource for monitoring the dose values of the medical
team during interventional radiology procedures, although there are still opportunities for
improvement identified for both models.
This study addresses the assessment of dose to organs/tissues, based on the spatial position of the physician (represented by a mannequin) during the interventional radiology procedure. The main objective was to analyze the prediction capacity, considering different distances in relation to the X-ray tube, in different organs/tissues. The methods applied included a prediction model with low training cost, however, with specific limitations, intended for a type of procedure considering immobile patients, fixed gender and static conditions of the X-ray equipment. Restricting the physician’s movement within the marker area was crucial to reducing image deformation. The results highlighted that, in small organs, such as the prostate, the greatest differences occurred between the predicted dose values and those calculated with MCNP6.2. The results highlight the feasibility of integrating the Multilayer Perceptron (MLP) model, used to predict doses in each organ, with the YOLOv4 model, for real-time identification of the doctor’s spatial positions. This integration has the advantage of being low cost, thus being a crucial resource for monitoring the dose values of the medical team during interventional radiology procedures, although there are still opportunities for improvement identified for both models.
This study addresses the assessment of dose to organs/tissues, based on the spatial position of the physician (represented by a mannequin) during the interventional radiology procedure. The main objective was to analyze the prediction capacity, considering different distances in relation to the X-ray tube, in different organs/tissues. The methods applied included a prediction model with low training cost, however, with specific limitations, intended for a type of procedure considering immobile patients, fixed gender and static conditions of the X-ray equipment. Restricting the physician’s movement within the marker area was crucial to reducing image deformation. The results highlighted that, in small organs, such as the prostate, the greatest differences occurred between the predicted dose values and those calculated with MCNP6.2. The results highlight the feasibility of integrating the Multilayer Perceptron (MLP) model, used to predict doses in each organ, with the YOLOv4 model, for real-time identification of the doctor’s spatial positions. This integration has the advantage of being low cost, thus being a crucial resource for monitoring the dose values of the medical team during interventional radiology procedures, although there are still opportunities for improvement identified for both models.
Palavras-chave
Dose de órgãos, Organ Dose, Previsão espacial., Spatial Prediction, Exposição médica, Medical Exposition, Modelos de imagem, Imaging Models, Monitoramento durante procedimentos, Procedure Monitoring, Inteligência Artificial, Artificial Intelligence
Citação
TAVARES, Otávio Joaquim. Avaliação numérica da dose ocupacional em procedimentos intervencionistas utilizando métodos de deep learning em tempo real. 2024. 60 f. Dissertação (Mestrado em Engenharia Biomédica) - Universidade Federal de Uberlândia, 2024. DOI https://doi.org/10.14393/ufu.di.2024.124.
Avaliação
Revisão
Suplementado Por
Referenciado Por
Licença Creative Commons
Exceto quando indicado de outra forma, a licença deste item é descrita como Acesso Aberto