Radiology
HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
 QUICK SEARCH:   [advanced]


     


This Article
Right arrow Abstract Freely available
Right arrow Full Text
Right arrow Full Text (PDF)
Right arrow Submit a response
Right arrow Alert me when this article is cited
Right arrow Alert me when eLetters are posted
Right arrow Alert me if a correction is posted
Right arrow Citation Map
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Download to citation manager
Right arrow reprints & permissions
Citing Articles
Right arrow Citing Articles via HighWire
Right arrow Citing Articles via Google Scholar
Google Scholar
Right arrow Articles by Magnotta, V. A.
Right arrow Articles by Yuh, W. T. C.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Magnotta, V. A.
Right arrow Articles by Yuh, W. T. C.

Measurement of Brain Structures with Artificial Neural Networks: Two- and Three-dimensional Applications1

Vincent A. Magnotta, PhD, Dan Heckel, BS, Nancy C. Andreasen, MD, PhD, Ted Cizadlo, BS, Patricia Westmoreland Corson, MD, James C. Ehrhardt, PhD and William T. C. Yuh, MD

1 Department of Radiology, Mental Health Clinical Research Center, the University of Iowa Hospitals and Clinics, 2911 JPP, 200 Hawkins Dr, Iowa City, IA 52242. Received July 10, 1998; revision requested August 13; revision received September 21; accepted November 13. Supported in part by National Institutes of Mental Health grants MH31593, MH40856, and MHCRC43271 and Research Scientist award MH00625, and an Established Investigator Award from the National Alliance for Research on Schizophrenia and Depression. Address reprint requests to V.A.M.



View larger version (37K):

[in a new window]
 
Figure 1. Diagram of the ANN used for the corpus callosum. The figure shows connections from the input nodes to one of the hidden layer nodes and from the hidden layer node to the output node.

 


View larger version (11K):

[in a new window]
 
Figure 2. Graph depicts mean squared error of the ANN during training. At first, there is a rapid decline in the mean squared error because initially the weights are assigned randomly. After training, the mean squared error approaches an asymptote.

 


View larger version (122K):

[in a new window]
 
Figure 3a. Corpus callosum. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red line) generated by the ANN.

 


View larger version (136K):

[in a new window]
 
Figure 3b. Corpus callosum. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red line) generated by the ANN.

 


View larger version (140K):

[in a new window]
 
Figure 3c. Corpus callosum. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red line) generated by the ANN.

 


View larger version (144K):

[in a new window]
 
Figure 3d. Corpus callosum. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red line) generated by the ANN.

 


View larger version (130K):

[in a new window]
 
Figure 4a. Whole brain. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red line) generated by the ANN.

 


View larger version (128K):

[in a new window]
 
Figure 4b. Whole brain. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red line) generated by the ANN.

 


View larger version (124K):

[in a new window]
 
Figure 4c. Whole brain. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red line) generated by the ANN.

 


View larger version (122K):

[in a new window]
 
Figure 4d. Whole brain. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red line) generated by the ANN.

 


View larger version (137K):

[in a new window]
 
Figure 5a. Caudate. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red [right] and yellow [left] lines) generated by the ANN.

 


View larger version (124K):

[in a new window]
 
Figure 5b. Caudate. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red [right] and yellow [left] lines) generated by the ANN.

 


View larger version (154K):

[in a new window]
 
Figure 5c. Caudate. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red [right] and yellow [left] lines) generated by the ANN.

 


View larger version (148K):

[in a new window]
 
Figure 5d. Caudate. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red [right] and yellow [left] lines) generated by the ANN.

 


View larger version (153K):

[in a new window]
 
Figure 6a. Putamen. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red [right] and yellow [left] lines) generated by the ANN.

 


View larger version (132K):

[in a new window]
 
Figure 6b. Putamen. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red [right] and yellow [left] lines) generated by the ANN.

 


View larger version (140K):

[in a new window]
 
Figure 6c. Putamen. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red [right] and yellow [left] lines) generated by the ANN.

 


View larger version (145K):

[in a new window]
 
Figure 6d. Putamen. (a–d) MR images in the testing set were obtained in four subjects and depict ROIs (red [right] and yellow [left] lines) generated by the ANN.

 


View larger version (56K):

[in a new window]
 
Figure 7a. Caudate (right, green; left, blue). (a, b) The 3D renderings identified by the ANN for two subjects. (a) Side view of the caudate nuclei in one subject and (b) top view in the other.

 


View larger version (64K):

[in a new window]
 
Figure 7b. Caudate (right, green; left, blue). (a, b) The 3D renderings identified by the ANN for two subjects. (a) Side view of the caudate nuclei in one subject and (b) top view in the other.

 





HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS
RADIOLOGY RADIOGRAPHICS RSNA JOURNALS ONLINE
Copyright © 1999 by the Radiological Society of North America.