PURPOSE: To evaluate the ability of an artificial neural network (ANN) to identify brain structures. This ANN was applied to postprocessed magnetic resonance (MR) images to segment various brain structures in both two- and three-dimensional applications. MATERIALS AND METHODS: An ANN was designed that learned from experience to define the corpus callosum, whole brain, caudate, and putamen. Manual segmentation was used as a training set for the ANN. The ANN was trained on two-thirds of the manually segmented images and was tested on the remaining one-third. The reliability of the ANN was compared against manual segmentations by two technicians. RESULTS: The ANN was able to identify the brain structures as readily and as well as did the two technicians. Reliability of the ANN compared with the technicians was 0.96 for the corpus callosum, 0.95 for the whole brain, 0.86 (right) and 0.93 (left) for the caudate, and 0.71 (right) and 0.88 (left) for the putamen. CONCLUSION: The ANN was able to identify the structures used in this study as well as did the two technicians. The ANN could do this much more rapidly and without rater drift. Several other cortical and subcortical structures could also be readily identified with this method.
PURPOSE: To evaluate the ability of an artificial neural network (ANN) to identify brain structures. This ANN was applied to postprocessed magnetic resonance (MR) images to segment various brain structures in both two- and three-dimensional applications. MATERIALS AND METHODS: An ANN was designed that learned from experience to define the corpus callosum, whole brain, caudate, and putamen. Manual segmentation was used as a training set for the ANN. The ANN was trained on two-thirds of the manually segmented images and was tested on the remaining one-third. The reliability of the ANN was compared against manual segmentations by two technicians. RESULTS: The ANN was able to identify the brain structures as readily and as well as did the two technicians. Reliability of the ANN compared with the technicians was 0.96 for the corpus callosum, 0.95 for the whole brain, 0.86 (right) and 0.93 (left) for the caudate, and 0.71 (right) and 0.88 (left) for the putamen. CONCLUSION: The ANN was able to identify the structures used in this study as well as did the two technicians. The ANN could do this much more rapidly and without rater drift. Several other cortical and subcortical structures could also be readily identified with this method.
Authors: Cheryl J Aine; Chad C Woodruff; Janice E Knoefel; John C Adair; David Hudson; Clifford Qualls; Jeremy Bockholt; Elaine Best; Sanja Kovacevic; Wayne Cobb; Denise Padilla; Blaine Hart; Julia M Stephen Journal: Neuroimage Date: 2006-06-21 Impact factor: 6.556
Authors: Stephanie Powell; Vincent A Magnotta; Hans Johnson; Vamsi K Jammalamadaka; Ronald Pierson; Nancy C Andreasen Journal: Neuroimage Date: 2007-08-22 Impact factor: 6.556
Authors: Sergio Paradiso; Jatin G Vaidya; Laurie M McCormick; Andria Jones; Robert G Robinson Journal: Am J Geriatr Psychiatry Date: 2008-08-12 Impact factor: 4.105
Authors: Benjamin Y Durkee; Sarah R Mudd; Calista N Roen; Linda Clipson; Michael A Newton; Jamey P Weichert; Perry J Pickhardt; Richard B Halberg Journal: Acad Radiol Date: 2008-03 Impact factor: 3.173