A hybrid approach based on logistic classification and iterative contrast enhancement algorithm for hyperintense multiple sclerosis lesion segmentation.
Multiple sclerosis (MS) is a neurodegenerative disease with increasing importance in recent years, in which the T2 weighted with fluid attenuation inversion recovery (FLAIR) MRI imaging technique has been addressed for the hyperintense MS lesion assessment. Many automatic lesion segmentation approac...
| Publicado en: | Medical & Biological Engineering & Computing Vol. 56; no. 6; pp. 1063 - 1077 |
|---|---|
| Autor principal: | |
| Formato: | diagnostic images equations & formulas research tables/charts Journal Article |
| Publicado: |
Springer Nature
Jun2018
|
| 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=129738993&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 129738993 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 01400118 PO0 jtl: Medical & Biological Engineering & Computing issn: 01400118 maglogo: N pubinfo: dt: Jun2018 vid: 56 iid: 6 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 129738993 129738993 NLM29150799 129738993 10.1007/s11517-017-1747-2 NLM29150799 129738993 ppf: 1063 ppct: 14 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: A hybrid approach based on logistic classification and iterative contrast enhancement algorithm for hyperintense multiple sclerosis lesion segmentation. aug: au: da Silva Senra Filho, Antonio Carlos affil: Av. Bandeirantes, 3900, Ribeirao Preto, Brazil sug: subj: Magnetic Resonance Imaging Methods Multiple Sclerosis Algorithms Image Interpretation, Computer Assisted Methods Pharmacokinetics Brain Funding Source ab: Multiple sclerosis (MS) is a neurodegenerative disease with increasing importance in recent years, in which the T2 weighted with fluid attenuation inversion recovery (FLAIR) MRI imaging technique has been addressed for the hyperintense MS lesion assessment. Many automatic lesion segmentation approaches have been proposed in the literature in order to assist health professionals. In this study, a new hybrid lesion segmentation approach based on logistic classification (LC) and the iterative contrast enhancement (ICE) method is proposed (LC+ICE). T1 and FLAIR MRI images from 32 secondary progressive MS (SPMS) patients were used in the LC+ICE method, in which manual segmentation was used as the ground truth lesion segmentation. The DICE, Sensitivity, Specificity, Area under the ROC curve (AUC), and Volume Similarity measures showed that the LC+ICE method is able to provide a precise and robust lesion segmentation estimate, which was compared with two recent FLAIR lesion segmentation approaches. In addition, the proposed method also showed a stable segmentation among lesion loads, showing a wide applicability to different disease stages. The LC+ICE procedure is a suitable alternative to assist the manual FLAIR hyperintense MS lesion segmentation task. pubtype: Academic Journal doctype: diagnostic images equations & formulas research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|