Open Access Repository

Accurate and unbiased quantitation of Amyloid-β fluorescence images using ImageSURF

O'Mara, AR, Collins, JM ORCID: 0000-0002-1938-2470, King, AE ORCID: 0000-0003-1792-0965, Vickers, JC ORCID: 0000-0001-5671-4879 and Kirkcaldie, MTK ORCID: 0000-0003-3285-0168 2018 , 'Accurate and unbiased quantitation of Amyloid-β fluorescence images using ImageSURF' , Current Alzheimer Research, vol. 16, no. 2 , pp. 102-108 , doi: 10.2174/1567205016666181212152622.

Full text not available from this repository.


Background: Images of amyloid-β pathology characteristic of Alzheimer’s disease are difficult to consistently andaccurately segment, due to diffuse deposit boundaries and imaging variations.Methods: We evaluated the performance of ImageSURF, our open-source ImageJ plugin, which considers a range of imagederivatives to train image classifiers. We compared ImageSURF to standard image thresholding to assess its reproducibility,accuracy and generalizability when used on fluorescence images of amyloid pathology.Results: ImageSURF segments amyloid-β images significantly more faithfully, and with significantly greatergeneralizability, than optimized thresholding.Conclusion: In addition to its superior performance in capturing human evaluations of pathology images, ImageSURF isable to segment image sets of any size in a consistent and unbiased manner, without requiring additional blinding, and canbe retrospectively applied to existing images. The training process yields a classifier file which can be shared assupplemental data, allowing fully open methods and data, and enabling more direct comparisons between different studies.

Item Type: Article
Authors/Creators:O'Mara, AR and Collins, JM and King, AE and Vickers, JC and Kirkcaldie, MTK
Keywords: amyloid, Alzheimer's disease, segmentation, machine learning
Journal or Publication Title: Current Alzheimer Research
Publisher: Bentham Science Publishers
ISSN: 1567-2050
DOI / ID Number: 10.2174/1567205016666181212152622
Copyright Information:

© 2018 Bentham Science Publishers

Related URLs:
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page