The volume of hippocampal subfields is closely related with early diagnosis of Alzheimer's disease.Due to the anatomical complexity of hippocampal subfields,automatic segmentation merely on the content of MR images is extremely difficult.We presented a method which combines multi-atlas image segmentation with extreme learning machine based bias detection and correction technique to achieve a fully automatic segmentation of hippocampal subfields.Symmetric diffeomorphic registration driven by symmetric mutual information energy was implemented in atlas registration,which allows multi-modal image registration and accelerates execution time.An exponential function based label fusion strategy was proposed for the normalized similarity measure case in segmentation combination,which yields better combination accuracy.The test results show that this method is effective,especially for the larger subfields with an overlap of more than 80%,which is competitive with the current methods and is of potential clinical significance.
To evaluate the performance of basic shape representation methods for the description of dynamic cellular morphology, several frequently-used shape descriptors are compared. The methods are examined by using 50 lymphocyte video clips including two kinds of lymphocyte cells. Our goal is to represent cell shape in each frame accurately, meanwhile precisely classify the two groups of cells based on the cellular morphological variations in the video clips. Experimental results illustrate that in general the region-based shape descriptors outperform the contour-based ones, since the contourbased methods are excessively sensitive and ignorant to cellular internal information. Due to their robustness to noise, the region-based shape descriptors are suitable for dynamic cell representation. Although region-based methods are more time-consuming, they analyze the entire cell area.
