Design and evaluation of an accurate CNR-guided small region iterative restoration-based tumor segmentation scheme for PET using both simulated and real heterogeneous tumors.
Tumor delineation accuracy directly affects the effectiveness of radiotherapy. This study presents a methodology that minimizes potential errors during the automated segmentation of tumors in PET images. Iterative blind deconvolution was implemented in a region of interest encompassing the tumor wit...
| Publicado en: | Medical & Biological Engineering & Computing Vol. 58; no. 2; pp. 335 - 356 |
|---|---|
| Autores principales: | , |
| Formato: | diagnostic images equations & formulas research tables/charts Journal Article |
| Publicado: |
Springer Nature
Feb2020
|
| 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=141513931&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 141513931 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 01400118 PO0 jtl: Medical & Biological Engineering & Computing issn: 01400118 maglogo: N pubinfo: dt: Feb2020 vid: 58 iid: 2 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 141513931 141513931 NLM31848977 141513931 10.1007/s11517-019-02094-8 NLM31848977 141513931 ppf: 335 ppct: 21 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Design and evaluation of an accurate CNR-guided small region iterative restoration-based tumor segmentation scheme for PET using both simulated and real heterogeneous tumors. aug: au: Koç, Alpaslan Güveniş, Albert affil: Institute of Biomedical Engineering, Boğaziçi University, Kandilli Kampüs, Çengelköy, 34684, Istanbul, Turkey sug: subj: Tomography, Emission-Computed Contrast Media Algorithms Image Processing, Computer Assisted Neoplasms Computer Simulation Body Weights and Measures Imaging, Three-Dimensional Phantoms, Imaging Neoplasms Pathology Fludeoxyglucose F 18 Physics Neoplasm Staging Human ab: Tumor delineation accuracy directly affects the effectiveness of radiotherapy. This study presents a methodology that minimizes potential errors during the automated segmentation of tumors in PET images. Iterative blind deconvolution was implemented in a region of interest encompassing the tumor with the number of iterations determined from contrast-to-noise ratios. The active contour and random forest classification-based segmentation method was evaluated using three distinct image databases that included both synthetic and real heterogeneous tumors. Ground truths about tumor volumes were known precisely. The volumes of the tumors were in the range of 0.49-26.34 cm3, 0.64-1.52 cm3, and 40.38-203.84 cm3 respectively. Widely available software tools, namely, MATLAB, MIPAV, and ITK-SNAP were utilized. When using the active contour method, image restoration reduced mean errors in volumes estimation from 95.85 to 3.37%, from 815.63 to 17.45%, and from 32.61 to 6.80% for the three datasets. The accuracy gains were higher using datasets that include smaller tumors for which PVE is known to be more predominant. Computation time was reduced by a factor of about 10 in the smaller deconvolution region. Contrast-to-noise ratios were improved for all tumors in all data. The presented methodology has the potential to improve delineation accuracy in particular for smaller tumors at practically feasible computational times. Graphical abstract Evaluation of accurate lesion volumes using CNR-guided and ROI-based restoration method for PET images. pubtype: Academic Journal doctype: diagnostic images equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|