Please use this identifier to cite or link to this item:
http://hdl.handle.net/10553/129902
DC Field | Value | Language |
---|---|---|
dc.contributor.author | de los Reyes, Alexander Mulet | en_US |
dc.contributor.author | Lord, Victoria Hyde | en_US |
dc.contributor.author | Buemi, Maria Elena | en_US |
dc.contributor.author | Gandía, Daniel | en_US |
dc.contributor.author | Gómez Déniz, Luis | en_US |
dc.contributor.author | Alemán, Maikel Noriega | en_US |
dc.contributor.author | Suárez, Cecilia | en_US |
dc.date.accessioned | 2024-04-18T15:08:55Z | - |
dc.date.available | 2024-04-18T15:08:55Z | - |
dc.date.issued | 2024 | en_US |
dc.identifier.issn | 0266-4720 | en_US |
dc.identifier.uri | http://hdl.handle.net/10553/129902 | - |
dc.description.abstract | Glioblastoma multiforme (GBM) is the most prevalent and aggressive primary brain tumour that has the worst prognosis in adults. Currently, the automatic segmentation of this kind of tumour is being intensively studied. Here, the automatic three dimensional segmentation of the GBM is achieved with its related subzones (active tumour, inner necrosis, and peripheral oedema). Preliminary segmentations were first defined based on the four basic magnetic resonance imaging modalities and classic image processing methods (multithreshold Otsu, Chan–Vese active contours, and morphological erosion). After an automatic gap-filling post processing step, these pre liminary segmentations were combined and corrected by a supervised artificial neural network of multilayer perceptron type with a hidden layer of 80 neurons, fed by 30 selected radiomic features of gray intensity and texture. Network classification has an overall accuracy of 83.9%, while the complete combined algorithm achieves average Dice similarity coefficients of 89.3%, 80.7%, 79.7%, and 66.4% for the entire region of interest, active tumour, oedema, and necrosis segmentations, respectively. These values are in the range of the best reported in the present bibliography, but even with better Hausdorff distances and lower computational costs. Results pres ented here evidence that it is possible to achieve the automatic segmentation of this kind of tumour by traditional radiomics. This has relevant clinical potential at the time of diagnosis, precision radiotherapy planning, or post-treatment response evaluation | en_US |
dc.language | eng | en_US |
dc.relation.ispartof | Expert Systems | en_US |
dc.source | Expert Systems [ISSN 0266-4720], (Abril 2024) | en_US |
dc.subject.other | Artificial neural networks | en_US |
dc.subject.other | Automatic segmentation | en_US |
dc.subject.other | Glioblastoma multiforme | en_US |
dc.subject.other | Image processing | en_US |
dc.subject.other | Radiomics | en_US |
dc.title | Combined use of radiomics and artificial neural networks for the three‐dimensional automatic segmentation of glioblastoma multiforme | en_US |
dc.type | info:eu-repo/semantics/article | en_US |
dc.type | Article | en_US |
dc.rights.license | BY | - |
dc.identifier.doi | 10.1111/exsy.13598 | en_US |
dc.investigacion | Artes y Humanidades | en_US |
dc.type2 | Artículo | en_US |
dc.description.numberofpages | 14 | en_US |
dc.utils.revision | Sí | en_US |
dc.date.coverdate | Abril 2024 | en_US |
dc.identifier.ulpgc | Sí | en_US |
dc.contributor.buulpgc | BU-TEL | en_US |
dc.description.sjr | 0,761 | |
dc.description.jcr | 3,3 | |
dc.description.sjrq | Q2 | |
dc.description.jcrq | Q2 | |
dc.description.scie | SCIE | |
dc.description.miaricds | 11,0 | |
item.fulltext | Con texto completo | - |
item.grantfulltext | open | - |
crisitem.author.dept | GIR IUCES: Centro de Tecnologías de la Imagen | - |
crisitem.author.dept | IU de Cibernética, Empresa y Sociedad (IUCES) | - |
crisitem.author.dept | Departamento de Ingeniería Electrónica y Automática | - |
crisitem.author.orcid | 0000-0003-0667-2302 | - |
crisitem.author.parentorg | IU de Cibernética, Empresa y Sociedad (IUCES) | - |
crisitem.author.fullName | Gómez Déniz, Luis | - |
Appears in Collections: | Artículos |
Page view(s)
92
checked on Oct 5, 2024
Download(s)
30
checked on Oct 5, 2024
Google ScholarTM
Check
Altmetric
Share
Export metadata
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.