A carregar...
Publicação
REDUÇÃO DA ATIVIDADE ADMINISTRADA ATRAVÉS DA MELHORIA DA QUALIDADE DA IMAGEM EM CINTIGRAFIA PEDIÁTRICA
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 3.58 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
O objetivo deste estudo foi reduzir a atividade administrada em imagens de cintigrafia
renal pediátrica por meio da aplicação de técnicas de melhoria de qualidade da mesma.
As imagens obtidas após a administração do radiofármaco 99mTc-mercaptoacetiltriglicina
(99mTc-MAG3) foram submetidas a diferentes processos de redução de ruído. A redução
da atividade administrada foi simulada através da soma parcial dos dados das imagens
originais (100 %, 75 %, 50 %, e 25 %).
Para melhorar a qualidade das imagens, foram aplicadas quatro redes neuronais
(DnCNN, UDnCNN, DUDnCNN, e AttnGAN) e um Filtro de minimização da variação
total (TVmin) aos dados. A qualidade das imagens foi avaliada através da Razão Sinal-
Ruído (SNR) dos rins e do Índice de Similaridade Estrutural Multiescala (MS-SSIM),
comparando a preservação dos detalhes com a redução do ruído.
Imagens simuladas com menor atividade administrada (25 % dos dados) apresentam
níveis mais altos de ruído. O uso do filtro TVmin e da rede UDnCNN resultou em
melhorias significativas na qualidade das imagens. A rede UDnCNN destacou-se pelo seu
equilíbrio eficaz entre a redução de ruído e a preservação dos detalhes estruturais. Além
disso, a combinação do filtro TVmin com a rede UDnCNN demonstrou ser promissora
devido ao seu tempo de teste mais rápido.
A análise dos tempos de treino e teste revelou que a combinação dessas técnicas
oferece um bom equilíbrio entre a qualidade da imagem e a eficiência de processamento. A
abordagem integrada pode permitir a aquisição de imagens com atividades administradas
reduzidas (cerca de 50 %) sem comprometer a qualidade, representando um avanço
significativo na redução de radiação administrada aos pacientes.
Este estudo demonstra que a integração de técnicas avançadas de processamento de
imagem e redes neuronais pode melhorar significativamente a qualidade das imagens de
cintigrafia renal, permitindo a aquisição de imagens de alta qualidade com atividades
administradas menores de radiação, beneficiando a população pediátrica.
The aim of this study was to reduce the activity administered in pediatric renal scintig- raphy images by applying quality improvement techniques. The images obtained after administration of the radiopharmaceutical 99mTc-mercaptoacetylglycine (99mTc-MAG3) were subjected to different noise reduction processes. Activity administered reduction was simulated using the partial sum of the original image data (100 %, 75 %, 50 %, and 25 %). To improve image quality, four neural networks (DnCNN, UDnCNN, DUDnCNN, and AttnGAN) and a total variation minimization filter (TVmin) were applied to the data. The quality of the images was assessed using the Signal-to-Noise Ratio (SNR) of the kidneys and the Multiscale Structural Similarity Index (MS-SSIM), comparing the preservation of detail with noise reduction. It was observed that the simulated images with the lowest activity administered (25 % of the data) showed higher levels of noise. However, the use of the TVmin filter and the UDnCNN network resulted in significant improvements in image quality. The UDnCNN network stood out for its effective balance between noise reduction and preservation of structural details. The combination of the TVmin filter with the UDnCNN network proved promising due to its faster test time. Analysis of training and test times revealed that the combination of these techniques offers a good balance between image quality and processing efficiency. The integrated approach can allow images to be acquired at low activities administered (around 50 %) without compromising quality, representing a significant advance in reducing the radiation administered to patients. This study demonstrates that the integration of advanced image processing techniques and neural networks can significantly improve the quality of renal scintigraphy images, allowing the acquisition of high-quality images with lower activities administered of radiation, benefiting the pediatric population.
The aim of this study was to reduce the activity administered in pediatric renal scintig- raphy images by applying quality improvement techniques. The images obtained after administration of the radiopharmaceutical 99mTc-mercaptoacetylglycine (99mTc-MAG3) were subjected to different noise reduction processes. Activity administered reduction was simulated using the partial sum of the original image data (100 %, 75 %, 50 %, and 25 %). To improve image quality, four neural networks (DnCNN, UDnCNN, DUDnCNN, and AttnGAN) and a total variation minimization filter (TVmin) were applied to the data. The quality of the images was assessed using the Signal-to-Noise Ratio (SNR) of the kidneys and the Multiscale Structural Similarity Index (MS-SSIM), comparing the preservation of detail with noise reduction. It was observed that the simulated images with the lowest activity administered (25 % of the data) showed higher levels of noise. However, the use of the TVmin filter and the UDnCNN network resulted in significant improvements in image quality. The UDnCNN network stood out for its effective balance between noise reduction and preservation of structural details. The combination of the TVmin filter with the UDnCNN network proved promising due to its faster test time. Analysis of training and test times revealed that the combination of these techniques offers a good balance between image quality and processing efficiency. The integrated approach can allow images to be acquired at low activities administered (around 50 %) without compromising quality, representing a significant advance in reducing the radiation administered to patients. This study demonstrates that the integration of advanced image processing techniques and neural networks can significantly improve the quality of renal scintigraphy images, allowing the acquisition of high-quality images with lower activities administered of radiation, benefiting the pediatric population.
Descrição
Palavras-chave
99mTc-MAG3 Filtro de minimização Total Variation Aprendizagem Profunda redução de ruído redução da atividade administrada cintigrafia renal pediátrica