Abstract
Alzheimer's disease (AD) is a great challenge for the world and hardly to be cured, partly because of the lack of animal models that fully mimic pathological progress. Recently, a rat model exhibiting the most pathological symptoms of AD has been reported. However, high-resolution imaging and accurate quantification of beta-amyloid (Aβ) plaques in the whole rat brain have not been fulfilled due to substantial technical challenges. In this paper, a high-efficiency data analysis pipeline is proposed to quantify Aβ plaques in whole rat brain through several terabytes of image data acquired by a high-speed volumetric imaging approach we have developed previously. A novel segmentation framework applying a high-performance weakly supervised learning method which can dramatically reduce the human labeling consumption is described in this study. The effectiveness of our segmentation framework is validated with different metrics. The segmented Aβ plaques were mapped to a standard rat brain atlas for quantitative analysis of the Aβ distribution in each brain area. This pipeline may also be applied to the segmentation and accurate quantification of other non-specific morphology objects.