Automated analysis of multidimensional brain imagery
Author(s)
Tuxworth, Gervase
Cavanagh, Brenton
Meedeniya, Adrian
Blumenstein, Michael
Griffith University Author(s)
Year published
2012
Metadata
Show full item recordAbstract
Neural cells are highly plastic, mirroring their functional state in their morphology. Data from classification of three dimensional images of individual cells would enable the functional state of the cell to be determined. Due to the complexity of the data, namely, the extreme irregularity in neural shape, existing three dimensional segmentation and feature extraction techniques do not perform well. The ever increasing dimensionality and quantity of image data also demands the image analysis process to be automated. To meet these goals, we have begun developing a fully automated image analysis technique, which allow us to ...
View more >Neural cells are highly plastic, mirroring their functional state in their morphology. Data from classification of three dimensional images of individual cells would enable the functional state of the cell to be determined. Due to the complexity of the data, namely, the extreme irregularity in neural shape, existing three dimensional segmentation and feature extraction techniques do not perform well. The ever increasing dimensionality and quantity of image data also demands the image analysis process to be automated. To meet these goals, we have begun developing a fully automated image analysis technique, which allow us to quantitatively analyse neural cells in high resolution three dimensional images. We demonstrated the capacity of artificial neural networks to classify differing functional classes of neurons in our earlier work1. We have extended this work to automatically locate and segment cells from raw three dimensional image data.
View less >
View more >Neural cells are highly plastic, mirroring their functional state in their morphology. Data from classification of three dimensional images of individual cells would enable the functional state of the cell to be determined. Due to the complexity of the data, namely, the extreme irregularity in neural shape, existing three dimensional segmentation and feature extraction techniques do not perform well. The ever increasing dimensionality and quantity of image data also demands the image analysis process to be automated. To meet these goals, we have begun developing a fully automated image analysis technique, which allow us to quantitatively analyse neural cells in high resolution three dimensional images. We demonstrated the capacity of artificial neural networks to classify differing functional classes of neurons in our earlier work1. We have extended this work to automatically locate and segment cells from raw three dimensional image data.
View less >
Conference Title
Publisher URI
Subject
Biochemistry and cell biology
Neurosciences