FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216077153> ?p ?o ?g. }

• W3216077153 endingPage "vi138" @default.
• W3216077153 startingPage "vi137" @default.
• W3216077153 abstract "Abstract Glioblastoma (GBM) is a devastating primary brain tumor known for its heterogeneity with a median survival of 15 months. Clinical imaging remains the primary modality to assess brain tumor response, but it is nearly impossible to distinguish between tumor growth and treatment response. Ki67 is a marker of active cell proliferation that shows inter- and intra-patient heterogeneity and should change under many therapies. In this work, we assessed the utility of a semi-supervised deep learning approach for regionally predicting high-vs-low Ki67 in GBM patients based on MRI. We used both labeled and unlabeled datasets to train the model. Labeled data included 114 MRI-localized biopsies from 43 unique GBM patients with available immunohistochemistry Ki67 labels. Unlabeled data included nine repeat routine pretreatment paired scans of newly-diagnosed GBM patients acquired within three days. Data augmentation techniques were utilized to enhance the size of our data and increase generalizability. Data was split between training, validation, and testing sets using 65-15-20 percent ratios. Model inputs were 16x16x3 patches around biopsies on T1Gd and T2 MRIs for labeled data, and around randomly selected patches inside the T2 abnormal region for unlabeled data. The network was a 4-conv layered VGG-inspired architecture. Training objective was accurate prediction of Ki67 in labeled patches and consistency in predictions across repeat unlabeled patches. We measured final model accuracy on held-out test samples. Our promising preliminary results suggest potential for deep learning in deconvolving the spatial heterogeneity of proliferative GBM subpopulations. If successful, this model can provide a non-invasive readout of cell proliferation and reveal the effectiveness of a given cytotoxic therapy dynamically during the patient's routine follow up. Further, the spatial resolution of our approach provides insights into the intra-tumoral heterogeneity of response which can be related to heterogeneity in localization of therapies (e.g. radiation therapy, drug dose heterogeneity)." @default.
• W3216077153 created "2021-12-06" @default.
• W3216077153 creator A5007678788 @default.
• W3216077153 creator A5014011778 @default.
• W3216077153 creator A5027970167 @default.
• W3216077153 creator A5046673359 @default.
• W3216077153 creator A5066820418 @default.
• W3216077153 creator A5069062178 @default.
• W3216077153 creator A5078763626 @default.
• W3216077153 date "2021-11-02" @default.
• W3216077153 modified "2023-10-16" @default.
• W3216077153 title "NIMG-40. MRI-BASED ESTIMATION OF THE ABUNDANCE OF IMMUNOHISTOCHEMISTRY MARKERS IN GBM BRAIN USING DEEP LEARNING" @default.
• W3216077153 doi "https://doi.org/10.1093/neuonc/noab196.539" @default.
• W3216077153 hasPublicationYear "2021" @default.
• W3216077153 type Work @default.
• W3216077153 sameAs 3216077153 @default.
• W3216077153 citedByCount "0" @default.
• W3216077153 crossrefType "journal-article" @default.
• W3216077153 hasAuthorship W3216077153A5007678788 @default.
• W3216077153 hasAuthorship W3216077153A5014011778 @default.
• W3216077153 hasAuthorship W3216077153A5027970167 @default.
• W3216077153 hasAuthorship W3216077153A5046673359 @default.
• W3216077153 hasAuthorship W3216077153A5066820418 @default.
• W3216077153 hasAuthorship W3216077153A5069062178 @default.
• W3216077153 hasAuthorship W3216077153A5078763626 @default.
• W3216077153 hasBestOaLocation W32160771531 @default.
• W3216077153 hasConcept C105795698 @default.
• W3216077153 hasConcept C108583219 @default.
• W3216077153 hasConcept C142724271 @default.
• W3216077153 hasConcept C154945302 @default.
• W3216077153 hasConcept C204232928 @default.
• W3216077153 hasConcept C27158222 @default.
• W3216077153 hasConcept C2779130545 @default.
• W3216077153 hasConcept C2989005 @default.
• W3216077153 hasConcept C33923547 @default.
• W3216077153 hasConcept C41008148 @default.
• W3216077153 hasConcept C71924100 @default.
• W3216077153 hasConceptScore W3216077153C105795698 @default.
• W3216077153 hasConceptScore W3216077153C108583219 @default.
• W3216077153 hasConceptScore W3216077153C142724271 @default.
• W3216077153 hasConceptScore W3216077153C154945302 @default.
• W3216077153 hasConceptScore W3216077153C204232928 @default.
• W3216077153 hasConceptScore W3216077153C27158222 @default.
• W3216077153 hasConceptScore W3216077153C2779130545 @default.
• W3216077153 hasConceptScore W3216077153C2989005 @default.
• W3216077153 hasConceptScore W3216077153C33923547 @default.
• W3216077153 hasConceptScore W3216077153C41008148 @default.
• W3216077153 hasConceptScore W3216077153C71924100 @default.
• W3216077153 hasIssue "Supplement_6" @default.
• W3216077153 hasLocation W32160771531 @default.
• W3216077153 hasOpenAccess W3216077153 @default.
• W3216077153 hasPrimaryLocation W32160771531 @default.
• W3216077153 hasRelatedWork W118346583 @default.
• W3216077153 hasRelatedWork W2060950703 @default.
• W3216077153 hasRelatedWork W2084136175 @default.
• W3216077153 hasRelatedWork W2606018528 @default.
• W3216077153 hasRelatedWork W2952846726 @default.
• W3216077153 hasRelatedWork W3094221504 @default.
• W3216077153 hasRelatedWork W3186932144 @default.
• W3216077153 hasRelatedWork W3196786996 @default.
• W3216077153 hasRelatedWork W4225304418 @default.
• W3216077153 hasRelatedWork W4287009405 @default.
• W3216077153 hasVolume "23" @default.
• W3216077153 isParatext "false" @default.
• W3216077153 isRetracted "false" @default.
• W3216077153 magId "3216077153" @default.
• W3216077153 workType "article" @default.