SciELO - Scientific Electronic Library Online

vol.16 número30Lean construction LC under lean thinkingA proposal for standardized data models and exchange information protocols applicable in centralized metering systems índice de autoresíndice de assuntospesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados



Links relacionados

  • Em processo de indexaçãoCitado por Google
  • Não possue artigos similaresSimilares em SciELO
  • Em processo de indexaçãoSimilares em Google


Revista Ingenierías Universidad de Medellín

versão impressa ISSN 1692-3324


SERNA, Andrés  e  PRIETO, Flavio. Towards a 3D modeling of brain tumors by using endoneurosonography and neural networks. Rev. ing. univ. Medellín [online]. 2017, vol.16, n.30, pp.129-148. ISSN 1692-3324.

Minimally invasive surgeries have become popular because they reduce the typical risks of traditional interventions. In neurosurgery, recent trends suggest the combined use of endoscopy and ultrasound (endoneurosonography or ENS) for 3D virtualization of brain structures in real time. The ENS information can be used to generate 3D models of brain tumors during a surgery. This paper introduces a methodology for 3D modeling of brain tumors using ENS and unsupervised neural networks. The use of self-organizing maps (SOM) and neural gas networks (NGN) is particularly studied. Compared to other techniques, 3D modeling using neural networks offers advantages, since tumor morphology is directly encoded in synaptic weights of the network, no a priori knowledge is required, and the representation can be developed in two stages: off-line training and on-line adaptation. Experimental tests were performed using virtualized phantom brain tumors. At the end of the paper, the results of 3D modeling from an ENS database are presented.

Palavras-chave : brain tumors; endoneurosonography; 3D acquisition; 3D modeling..

        · resumo em Espanhol     · texto em Inglês     · Inglês ( pdf )