A Feasibility Study on Automated Protein Aggregate Characterization Utilizing a Hybrid Classification Model

Simple item page
dc.contributor.authorEschweiler, Dennisen_US
dc.contributor.authorGadermayr, Michaelen_US
dc.contributor.authorUnger, Jakoben_US
dc.contributor.authorNippold, Markusen_US
dc.contributor.authorFalkenburger, Björnen_US
dc.contributor.authorMerhof, Doriten_US
dc.contributor.editorStefan Bruckner and Bernhard Preim and Anna Vilanova and Helwig Hauser and Anja Hennemuth and Arvid Lundervolden_US
dc.date.accessioned2016-09-07T05:37:50Z
dc.date.available2016-09-07T05:37:50Z
dc.date.issued2016
dc.description.abstractThe characterization of cytoplasmic protein aggregates based on time-lapse fluorescence microscopy imaging data is important for research in neuro-degenerative diseases such as Parkinson. As the manual assessment is time-consuming and subject to significant variability, incentive for the development of an objective automated system is provided. We propose and evaluate a pipeline consisting of cell-segmentation, tracking and classification of neurological cells. Focus is specifically on the novel and challenging classification task which is covered by relying on feature extraction followed by a hybrid classification approach incorporating a support vector machine focusing on mainly stationary information and a hidden Markov model to incorporate temporal context. Several image representations are experimentally evaluated to identify cell properties that are important for discrimination. Relying on the proposed approach, classification accuracies up to 80 % are reached. By extensively analyzing the outcomes, we discuss about strengths and weaknesses of our method as a quantitative assessment tool.en_US
dc.description.sectionheadersMedical Data Analysis and Visualization (Short Papers)
dc.description.seriesinformationEurographics Workshop on Visual Computing for Biology and Medicine
dc.identifier.doi10.2312/vcbm.20161277
dc.identifier.isbn978-3-03868-010-9
dc.identifier.issn2070-5786
dc.identifier.pages105-109
dc.identifier.urihttps://doi.org/10.2312/vcbm.20161277
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/vcbm20161277
dc.publisherThe Eurographics Associationen_US
dc.titleA Feasibility Study on Automated Protein Aggregate Characterization Utilizing a Hybrid Classification Modelen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
105-109.pdf
Size:
3.18 MB
Format:
Adobe Portable Document Format
Download
Collections
VCBM 16: Eurographics Workshop on Visual Computing for Biology and Medicine