Literature DB >> 18218375

Optimization neural networks for the segmentation of magnetic resonance images.

S C Amartur1, D Piraino, Y Takefuji.   

Abstract

The application of the Hopfield neural network for the multispectral unsupervised classification of MR images is reported. Winner-take-all neurons were used to obtain a crisp classification map using proton density-weighted and T(2)-weighted images in the head. The preliminary studies indicate that the number of iterations needed to reach ;good' solutions was nearly constant with the number of clusters chosen for the problem.

Year:  1992        PMID： 18218375     DOI： 10.1109/42.141645

Source DB:  PubMed          Journal:  IEEE Trans Med Imaging        ISSN： 0278-0062            Impact factor:   10.048


  4 in total

Review 1.  Multivariate statistical model for 3D image segmentation with application to medical images.

Authors:  Nigel M John; Mansur R Kabuka; Mohamed O Ibrahim
Journal:  J Digit Imaging       Date:  2004-02-02       Impact factor: 4.056

Review 2.  An artificial immune-activated neural network applied to brain 3D MRI segmentation.

Authors:  Akmal Younis; Mohamed Ibrahim; Mansur Kabuka; Nigel John
Journal:  J Digit Imaging       Date:  2007-12-11       Impact factor: 4.056

3.  Classification of brain compartments and head injury lesions by neural networks applied to MRI.

Authors:  E R Kischell; N Kehtarnavaz; G R Hillman; H Levin; M Lilly; T A Kent
Journal:  Neuroradiology       Date:  1995-10       Impact factor: 2.804

4.  Modification of the mean-square error principle to double the convergence speed of a special case of Hopfield neural network used to segment pathological liver color images.

Authors:  Rachid Sammouda; Mohamed Sammouda
Journal:  BMC Med Inform Decis Mak       Date:  2004-12-12       Impact factor: 2.796
  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.