Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313496495> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4313496495 abstract "Hyperspectral (HS) imaging (HSI) techniques have demonstrated to be useful in the medical field to characterize tissues without any contact and without ionizing the patient. Besides, HSI combined with supervised machine learning (ML) algorithms have proven to be an effective technique to assist neurosurgeons to resect brain tumors. This research looks at the effects of hyperparameter optimization on two common supervised ML algorithms used for brain tumor classification: support vector machines (SVM) and random forest (RF). Correctly classifying brain tumor with HS data containing low spatial and spectral information can be challenging. To tackle this problem, this study has applied hyperparameter optimization techniques on SVM and RF with 10 brain images of patients suffering from glioblastoma multiforme (GBM) with non-mutated isocitrate dehydrogenase (IDH) enzymes. These captures have 409x217 spatial resolution and 25 normalized reflectance wavelengths gathered from 665 to 960 nm with a HS snapshot camera. Results show how this work has been able to obtain 98,60% of weighted area under the curve (AUC) on the test score by employing naive optimizations like grid search (GS) or random search (RS) and even more complex methods based on Bayesian optimization (BO). Not only the weighted AUC of SVM has been improved by 8%, but BO have also enhanced the AUC of the tumor class by 22.50% in comparison with non-optimized SVM models in the state-of-the-art, achieving AUC values of 95,49% on the tumor class. Furthermore, these improvements have been illustrated with classification maps to demonstrate the importance of hyperparameter optimization on SVM to clearly classify brain tumor, whereas non-optimized models from previous studies are unable to detect the tumor." @default.
- W4313496495 created "2023-01-06" @default.
- W4313496495 creator A5004708657 @default.
- W4313496495 creator A5005664531 @default.
- W4313496495 creator A5009031856 @default.
- W4313496495 creator A5022382568 @default.
- W4313496495 creator A5024011229 @default.
- W4313496495 creator A5034957952 @default.
- W4313496495 creator A5050579303 @default.
- W4313496495 creator A5059637395 @default.
- W4313496495 creator A5073876341 @default.
- W4313496495 creator A5091313837 @default.
- W4313496495 date "2022-08-01" @default.
- W4313496495 modified "2023-09-26" @default.
- W4313496495 title "Hyperparameter Optimization for Brain Tumor Classification with Hyperspectral Images" @default.
- W4313496495 cites W1994197834 @default.
- W4313496495 cites W2139510234 @default.
- W4313496495 cites W2187633770 @default.
- W4313496495 cites W2407212869 @default.
- W4313496495 cites W2788703804 @default.
- W4313496495 cites W2793848630 @default.
- W4313496495 cites W2911964244 @default.
- W4313496495 cites W2949676527 @default.
- W4313496495 cites W2950680102 @default.
- W4313496495 cites W3165128717 @default.
- W4313496495 cites W60686164 @default.
- W4313496495 doi "https://doi.org/10.1109/dsd57027.2022.00117" @default.
- W4313496495 hasPublicationYear "2022" @default.
- W4313496495 type Work @default.
- W4313496495 citedByCount "2" @default.
- W4313496495 countsByYear W43134964952023 @default.
- W4313496495 crossrefType "proceedings-article" @default.
- W4313496495 hasAuthorship W4313496495A5004708657 @default.
- W4313496495 hasAuthorship W4313496495A5005664531 @default.
- W4313496495 hasAuthorship W4313496495A5009031856 @default.
- W4313496495 hasAuthorship W4313496495A5022382568 @default.
- W4313496495 hasAuthorship W4313496495A5024011229 @default.
- W4313496495 hasAuthorship W4313496495A5034957952 @default.
- W4313496495 hasAuthorship W4313496495A5050579303 @default.
- W4313496495 hasAuthorship W4313496495A5059637395 @default.
- W4313496495 hasAuthorship W4313496495A5073876341 @default.
- W4313496495 hasAuthorship W4313496495A5091313837 @default.
- W4313496495 hasConcept C10485038 @default.
- W4313496495 hasConcept C119857082 @default.
- W4313496495 hasConcept C12267149 @default.
- W4313496495 hasConcept C153180895 @default.
- W4313496495 hasConcept C154945302 @default.
- W4313496495 hasConcept C159078339 @default.
- W4313496495 hasConcept C169258074 @default.
- W4313496495 hasConcept C2778049539 @default.
- W4313496495 hasConcept C41008148 @default.
- W4313496495 hasConcept C52001869 @default.
- W4313496495 hasConcept C8642999 @default.
- W4313496495 hasConceptScore W4313496495C10485038 @default.
- W4313496495 hasConceptScore W4313496495C119857082 @default.
- W4313496495 hasConceptScore W4313496495C12267149 @default.
- W4313496495 hasConceptScore W4313496495C153180895 @default.
- W4313496495 hasConceptScore W4313496495C154945302 @default.
- W4313496495 hasConceptScore W4313496495C159078339 @default.
- W4313496495 hasConceptScore W4313496495C169258074 @default.
- W4313496495 hasConceptScore W4313496495C2778049539 @default.
- W4313496495 hasConceptScore W4313496495C41008148 @default.
- W4313496495 hasConceptScore W4313496495C52001869 @default.
- W4313496495 hasConceptScore W4313496495C8642999 @default.
- W4313496495 hasFunder F4320322930 @default.
- W4313496495 hasLocation W43134964951 @default.
- W4313496495 hasOpenAccess W4313496495 @default.
- W4313496495 hasPrimaryLocation W43134964951 @default.
- W4313496495 hasRelatedWork W2979979539 @default.
- W4313496495 hasRelatedWork W3013125858 @default.
- W4313496495 hasRelatedWork W3052467025 @default.
- W4313496495 hasRelatedWork W3127425528 @default.
- W4313496495 hasRelatedWork W3199608561 @default.
- W4313496495 hasRelatedWork W3212135906 @default.
- W4313496495 hasRelatedWork W4205958290 @default.
- W4313496495 hasRelatedWork W4311106074 @default.
- W4313496495 hasRelatedWork W4320494184 @default.
- W4313496495 hasRelatedWork W4375930479 @default.
- W4313496495 isParatext "false" @default.
- W4313496495 isRetracted "false" @default.
- W4313496495 workType "article" @default.