Low-complexity PDE-based approach for automatic microarray image processing.
Microarray image processing is known as a valuable tool for gene expression estimation, a crucial step in understanding biological processes within living organisms. Automation and reliability are open subjects in microarray image processing, where grid alignment and spot segmentation are essential...
| Publicado en: | Medical & Biological Engineering & Computing Vol. 53; no. 2; pp. 99 - 111 |
|---|---|
| Autores principales: | , , |
| Formato: | research Journal Article |
| Publicado: |
Springer Nature
Feb2015
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=109775339&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 109775339 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 01400118 PO0 jtl: Medical & Biological Engineering & Computing issn: 01400118 maglogo: N pubinfo: dt: Feb2015 vid: 53 iid: 2 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 109775339 NLM25351476 2012885911 10.1007/s11517-014-1214-2 NLM25351476 109775339 ppf: 99 ppct: 12 formats: fmt: @attributes: type: P tig: atl: Low-complexity PDE-based approach for automatic microarray image processing. aug: au: Belean, Bogdan Terebes, Romulus Bot, Adrian sug: subj: Image Processing, Computer Assisted Methods Microarray Analysis Methods Reproducibility of Results Software ab: Microarray image processing is known as a valuable tool for gene expression estimation, a crucial step in understanding biological processes within living organisms. Automation and reliability are open subjects in microarray image processing, where grid alignment and spot segmentation are essential processes that can influence the quality of gene expression information. The paper proposes a novel partial differential equation (PDE)-based approach for fully automatic grid alignment in case of microarray images. Our approach can handle image distortions and performs grid alignment using the vertical and horizontal luminance function profiles. These profiles are evolved using a hyperbolic shock filter PDE and then refined using the autocorrelation function. The results are compared with the ones delivered by state-of-the-art approaches for grid alignment in terms of accuracy and computational complexity. Using the same PDE formalism and curve fitting, automatic spot segmentation is achieved and visual results are presented. Considering microarray images with different spots layouts, reliable results in terms of accuracy and reduced computational complexity are achieved, compared with existing software platforms and state-of-the-art methods for microarray image processing. pubtype: Academic Journal doctype: research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|