Your browser doesn't support javascript.
loading
An adaptive parameter selection strategy based on maximizing the probability of data for robust fluorescence molecular tomography reconstruction.
Li, Jintao; Zhang, Lizhi; Liu, Jia; Zhang, Diya; Kang, Dizhen; Wang, Beilei; He, Xiaowei; Zhang, Heng; Zhao, Yizhe; Guo, Hongbo; Hou, Yuqing.
Afiliación
  • Li J; The Xi'an Key Laboratory of Radiomics and Intelligent Perception, Xi'an, China.
  • Zhang L; School of Information Sciences and Technology, Northwest University, Xi'an, China.
  • Liu J; The Xi'an Key Laboratory of Radiomics and Intelligent Perception, Xi'an, China.
  • Zhang D; School of Information Sciences and Technology, Northwest University, Xi'an, China.
  • Kang D; Xi'an Company of Shaanxi Tobacco Company, The Information Center, Xi'an, China.
  • Wang B; The Xi'an Key Laboratory of Radiomics and Intelligent Perception, Xi'an, China.
  • He X; School of Information Sciences and Technology, Northwest University, Xi'an, China.
  • Zhang H; The Xi'an Key Laboratory of Radiomics and Intelligent Perception, Xi'an, China.
  • Zhao Y; School of Information Sciences and Technology, Northwest University, Xi'an, China.
  • Guo H; The Xi'an Key Laboratory of Radiomics and Intelligent Perception, Xi'an, China.
  • Hou Y; School of Information Sciences and Technology, Northwest University, Xi'an, China.
J Biophotonics ; 16(8): e202300031, 2023 08.
Article en En | MEDLINE | ID: mdl-37074336
To alleviate the ill-posed of the inverse problem in fluorescent molecular tomography (FMT), many regularization methods based on L2 or L1 norm have been proposed. Whereas, the quality of regularization parameters affects the performance of the reconstruction algorithm. Some classical parameter selection strategies usually need initialization of parameter range and high computing costs, which is not universal in the practical application of FMT. In this paper, an universally applicable adaptive parameter selection method based on maximizing the probability of data (MPD) strategy was proposed. This strategy used maximum a posteriori (MAP) estimation and maximum likelihood (ML) estimation to establish a regularization parameters model. The stable optimal regularization parameters can be determined by multiple iterative estimates. Numerical simulations and in vivo experiments show that MPD strategy can obtain stable regularization parameters for both regularization algorithms based on L2 or L1 norm and achieve good reconstruction performance.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Procesamiento de Imagen Asistido por Computador / Tomografía Idioma: En Revista: J Biophotonics Asunto de la revista: BIOFISICA Año: 2023 Tipo del documento: Article País de afiliación: China Pais de publicación: Alemania
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Procesamiento de Imagen Asistido por Computador / Tomografía Idioma: En Revista: J Biophotonics Asunto de la revista: BIOFISICA Año: 2023 Tipo del documento: Article País de afiliación: China Pais de publicación: Alemania