TY - GEN
T1 - PC-based medical image analysis system for brain CT hemorrhage area extraction
AU - Cheng, Da Chuan
AU - Cheng, Kuo-Sheng
PY - 1998/1/1
Y1 - 1998/1/1
N2 - A PC based medical image analysis system for extracting the brain CT hemorrhage area is developed. Two kinds of segmentation method are investigated, fuzzy Hopfield neural network (FHNN) and possibilistic neural network (PHNN), for classifying the histogram of hemorrhage images and the near optimal threshold values can then be found. In addition, a function for professional doctors to extract the hematoma area is also included. The manual extraction areas are compared to those of the automatic extraction system and the average accuracy can be estimated. The fuzzy Hopfield neural network is a neural network based classification method for fuzzy c-means algorithm. It was proposed for automatic CT and MRI image segmentation to extract the region of interest (ROI). In addition, we develop a new algorithm for classification, which is called as the possibilistic Hopfield neural network. It is developed by imbedding the objective function of possibilistic c-means (PCM) into the energy function of a modified Hopfield neural network. Thus, the near optimal solution can be found by minimizing the energy function.
AB - A PC based medical image analysis system for extracting the brain CT hemorrhage area is developed. Two kinds of segmentation method are investigated, fuzzy Hopfield neural network (FHNN) and possibilistic neural network (PHNN), for classifying the histogram of hemorrhage images and the near optimal threshold values can then be found. In addition, a function for professional doctors to extract the hematoma area is also included. The manual extraction areas are compared to those of the automatic extraction system and the average accuracy can be estimated. The fuzzy Hopfield neural network is a neural network based classification method for fuzzy c-means algorithm. It was proposed for automatic CT and MRI image segmentation to extract the region of interest (ROI). In addition, we develop a new algorithm for classification, which is called as the possibilistic Hopfield neural network. It is developed by imbedding the objective function of possibilistic c-means (PCM) into the energy function of a modified Hopfield neural network. Thus, the near optimal solution can be found by minimizing the energy function.
UR - http://www.scopus.com/inward/record.url?scp=0031620862&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031620862&partnerID=8YFLogxK
U2 - 10.1109/CBMS.1998.701362
DO - 10.1109/CBMS.1998.701362
M3 - Conference contribution
AN - SCOPUS:0031620862
SN - 0818685646
T3 - Proceedings of the IEEE Symposium on Computer-Based Medical Systems
SP - 240
EP - 245
BT - Proceedings of the IEEE Symposium on Computer-Based Medical Systems
A2 - Anon, null
T2 - Proceedings of the 1998 11th IEEE Symposium on Computer-Based Medical Systems
Y2 - 12 June 1998 through 14 June 1998
ER -