Virtually Objective Quantification of in vitro Wound Healing Scratch Assays with the Segment Anything Model

Simple item page
dc.contributor.authorLöwenstein, Katjaen_US
dc.contributor.authorRehrl, Johannaen_US
dc.contributor.authorSchuster, Anjaen_US
dc.contributor.authorGadermayr, Michaelen_US
dc.contributor.editorGarrison, Lauraen_US
dc.contributor.editorJönsson, Danielen_US
dc.date.accessioned2024-09-17T06:06:52Z
dc.date.available2024-09-17T06:06:52Z
dc.date.issued2024
dc.description.abstractThe in vitro scratch assay is a widely used assay in cell biology to assess the rate of wound closure related to a variety of therapeutic interventions. While manual measurement is subjective and vulnerable to intra- and interobserver variability, computer-based tools are theoretically objective, but in practice often contain parameters which are manually adjusted (individually per image or data set) and thereby provide a source for subjectivity. Modern deep learning approaches typically require large annotated training data which complicates instant applicability. In this paper, we make use of the segment anything model, a deep foundation model based on interactive point-prompts, which enables class-agnostic segmentation without tuning the network's parameters based on domain specific training data. The proposed method clearly outperformed a semi-objective baseline method that required manual inspection and, if necessary, adjustment of parameters per image. Even though the point prompts of the proposed approach are theoretically also a source for subjectivity, results attested very low intra- and interobserver variability, even compared to manual segmentation of domain experts.en_US
dc.description.sectionheadersImage Processing and Machine Learning
dc.description.seriesinformationEurographics Workshop on Visual Computing for Biology and Medicine
dc.identifier.doi10.2312/vcbm.20241186
dc.identifier.isbn978-3-03868-244-8
dc.identifier.issn2070-5786
dc.identifier.pages5 pages
dc.identifier.urihttps://doi.org/10.2312/vcbm.20241186
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/vcbm20241186
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Image segmentation; Applied computing → Imaging
dc.subjectComputing methodologies → Image segmentation
dc.subjectApplied computing → Imaging
dc.titleVirtually Objective Quantification of in vitro Wound Healing Scratch Assays with the Segment Anything Modelen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
vcbm20241186.pdf
Size:
4.22 MB
Format:
Adobe Portable Document Format
Download
Collections
VCBM 2024: Eurographics Workshop on Visual Computing for Biology and Medicine