Self-Organizing Map Neural Network-Based Depth-of-Interaction Determination for Continuous Crystal PET Detectors

Abstract

For continuous crystal-based PET detectors, not only the two-dimensional (2D) plane coordinate of the interaction point, but also the depth-of-interaction (DOI) of the event could be precisely estimated by the single-end readout of the scintillation light. In this paper, we propose a practical method for DOI determination for continuous crystal PET detectors. By self-organizing map (SOM) neural network with unsupervised learning, the perpendicularly irradiated reference events in each reference position are classified into a certain number of groups, which are simultaneously used for the plane coordinate estimation and the DOI decoding. The reference events measured in an oblique irradiation are used to generate the initial weights of the SOM neurons and to calibrate the DOI decoding. Applying the new method to our experimental data, the SOM-based DOI estimation could achieve an average resolution of 2.56 mm over the whole thickness (0 -10 mm) of the crystal. The DOI effect is also evaluated by comparing the plane position resolutions of the test beams in different incident angles with and without the DOI correction. The test results show that the DOI determination could seamlessly integrate into our previously proposed the SOM-based plane coordinate estimation scheme to realize the high performance real-time three-dimensional position estimation for continuous crystal-based PET detectors.Index Terms-Depth-of-interaction (DOI), nearest neighbor algorithm, PET detector, position estimation, SOM neural network.

Self-organizing Community Learning Based on P2P Network in a University Computer Foundation Course

“…Based on a header compression and reuse optimization method, Rohmer and others [3] created a management package and sent to the same destination with the packets. Wang and others [4] added a new application layer to UDP to improve the QOS assurance capability of UDP, reduce the demand for the network and improve the scalability of the method; the traffic volume of the entire network is reduced by compressing and reusing data packet head. QuintanaRamirez et al [5] illustrated that the disadvantage of the application layer was that the processing time was increased and the average delay of the packet was delayed.…”

Metodologias para desenvolvimento de mapas auto-organizáveis de Kohonen executados em FPGA.

“…Estes fatos mostram uma tendência de originalidade no conjunto de ideias de emprego da rede neural. Por exemplo, na área de Medicina, os trabalhos deWang et al (2015) eDe, Zhang e Guo (2016) propõem o uso do SOM para segmentação de imagens médicas concomitantemente com a realização do exame, e para a computação em tempo real de detectores PET, usados em tomografias, com o processamento do DOI sejam discutidas as propriedades dos circuitos elétricos usados na computação dos algoritmos de treinamento e operação do SOM. A partir desse estudo, serão realizadas duas implementações práticas das metodologias desenvolvidas no trabalho, as quais pertencem (ainda com referência à Tabela 2) às áreas de telecomunicações e processamento de vídeo: a última seção do capítulo 5 apresenta o uso do SOM executado em FPGA para identificação de sinais QAM e a última seção do capítulo 6 descreve seu emprego no processamento de vídeos para reconhecimento de ações humanas.…”