Matches in SemOpenAlex for { <https://semopenalex.org/work/W3121234319> ?p ?o ?g. }
- W3121234319 abstract "We present an Expectation-Maximization (EM) Regularized Deep Learning (EMReDL) model for weakly supervised tumor segmentation. The proposed framework is tailored to glioblastoma, a type of malignant tumor characterized by its diffuse infiltration into the surrounding brain tissue, which poses significant challenge to treatment target and tumor burden estimation using conventional structural MRI. Although physiological MRI provides more specific information regarding tumor infiltration, the relatively low resolution hinders a precise full annotation. This has motivated us to develop a weakly supervised deep learning solution that exploits the partial labelled tumor regions. EMReDL contains two components: a physiological prior prediction model and EM-regularized segmentation model. The physiological prior prediction model exploits the physiological MRI by training a classifier to generate a physiological prior map. This map is passed to the segmentation model for regularization using the EM algorithm. We evaluated the model on a glioblastoma dataset with the pre-operative multiparametric and recurrence MRI available. EMReDL showed to effectively segment the infiltrated tumor from the partially labelled region of potential infiltration. The segmented core tumor and infiltrated tumor demonstrated high consistency with the tumor burden labelled by experts. The performance comparisons showed that EMReDL achieved higher accuracy than published state-of-the-art models. On MR spectroscopy, the segmented region displayed more aggressive features than other partial labelled region. The proposed model can be generalized to other segmentation tasks that rely on partial labels, with the CNN architecture flexible in the framework." @default.
- W3121234319 created "2021-02-01" @default.
- W3121234319 creator A5008171524 @default.
- W3121234319 creator A5017237504 @default.
- W3121234319 creator A5033880300 @default.
- W3121234319 creator A5060307752 @default.
- W3121234319 creator A5069648079 @default.
- W3121234319 creator A5079386554 @default.
- W3121234319 date "2021-01-21" @default.
- W3121234319 modified "2023-09-23" @default.
- W3121234319 title "Expectation-Maximization Regularized Deep Learning for Weakly Supervised Tumor Segmentation for Glioblastoma" @default.
- W3121234319 cites W1641498739 @default.
- W3121234319 cites W2096287682 @default.
- W3121234319 cites W2101762489 @default.
- W3121234319 cites W2130950654 @default.
- W3121234319 cites W2132358780 @default.
- W3121234319 cites W2159661815 @default.
- W3121234319 cites W2167878392 @default.
- W3121234319 cites W2326059109 @default.
- W3121234319 cites W2767623272 @default.
- W3121234319 cites W2806471870 @default.
- W3121234319 cites W2890740202 @default.
- W3121234319 cites W2900298334 @default.
- W3121234319 cites W2912347900 @default.
- W3121234319 cites W2940967976 @default.
- W3121234319 cites W2945276566 @default.
- W3121234319 cites W2952378269 @default.
- W3121234319 cites W2963046541 @default.
- W3121234319 cites W2975013431 @default.
- W3121234319 cites W2979754953 @default.
- W3121234319 cites W3020099303 @default.
- W3121234319 cites W3024238787 @default.
- W3121234319 cites W3028279406 @default.
- W3121234319 cites W3034453930 @default.
- W3121234319 cites W3035287677 @default.
- W3121234319 cites W3086458417 @default.
- W3121234319 hasPublicationYear "2021" @default.
- W3121234319 type Work @default.
- W3121234319 sameAs 3121234319 @default.
- W3121234319 citedByCount "0" @default.
- W3121234319 crossrefType "posted-content" @default.
- W3121234319 hasAuthorship W3121234319A5008171524 @default.
- W3121234319 hasAuthorship W3121234319A5017237504 @default.
- W3121234319 hasAuthorship W3121234319A5033880300 @default.
- W3121234319 hasAuthorship W3121234319A5060307752 @default.
- W3121234319 hasAuthorship W3121234319A5069648079 @default.
- W3121234319 hasAuthorship W3121234319A5079386554 @default.
- W3121234319 hasConcept C105795698 @default.
- W3121234319 hasConcept C108583219 @default.
- W3121234319 hasConcept C121332964 @default.
- W3121234319 hasConcept C126255220 @default.
- W3121234319 hasConcept C153180895 @default.
- W3121234319 hasConcept C153400128 @default.
- W3121234319 hasConcept C154945302 @default.
- W3121234319 hasConcept C165696696 @default.
- W3121234319 hasConcept C182081679 @default.
- W3121234319 hasConcept C2776135515 @default.
- W3121234319 hasConcept C2776194525 @default.
- W3121234319 hasConcept C2776330181 @default.
- W3121234319 hasConcept C33923547 @default.
- W3121234319 hasConcept C38652104 @default.
- W3121234319 hasConcept C41008148 @default.
- W3121234319 hasConcept C49781872 @default.
- W3121234319 hasConcept C502942594 @default.
- W3121234319 hasConcept C71924100 @default.
- W3121234319 hasConcept C89600930 @default.
- W3121234319 hasConcept C95623464 @default.
- W3121234319 hasConcept C97355855 @default.
- W3121234319 hasConceptScore W3121234319C105795698 @default.
- W3121234319 hasConceptScore W3121234319C108583219 @default.
- W3121234319 hasConceptScore W3121234319C121332964 @default.
- W3121234319 hasConceptScore W3121234319C126255220 @default.
- W3121234319 hasConceptScore W3121234319C153180895 @default.
- W3121234319 hasConceptScore W3121234319C153400128 @default.
- W3121234319 hasConceptScore W3121234319C154945302 @default.
- W3121234319 hasConceptScore W3121234319C165696696 @default.
- W3121234319 hasConceptScore W3121234319C182081679 @default.
- W3121234319 hasConceptScore W3121234319C2776135515 @default.
- W3121234319 hasConceptScore W3121234319C2776194525 @default.
- W3121234319 hasConceptScore W3121234319C2776330181 @default.
- W3121234319 hasConceptScore W3121234319C33923547 @default.
- W3121234319 hasConceptScore W3121234319C38652104 @default.
- W3121234319 hasConceptScore W3121234319C41008148 @default.
- W3121234319 hasConceptScore W3121234319C49781872 @default.
- W3121234319 hasConceptScore W3121234319C502942594 @default.
- W3121234319 hasConceptScore W3121234319C71924100 @default.
- W3121234319 hasConceptScore W3121234319C89600930 @default.
- W3121234319 hasConceptScore W3121234319C95623464 @default.
- W3121234319 hasConceptScore W3121234319C97355855 @default.
- W3121234319 hasOpenAccess W3121234319 @default.
- W3121234319 hasRelatedWork W1963937446 @default.
- W3121234319 hasRelatedWork W1971967920 @default.
- W3121234319 hasRelatedWork W2442839051 @default.
- W3121234319 hasRelatedWork W2597573836 @default.
- W3121234319 hasRelatedWork W2611826638 @default.
- W3121234319 hasRelatedWork W2790062442 @default.
- W3121234319 hasRelatedWork W2807889392 @default.
- W3121234319 hasRelatedWork W2903554604 @default.
- W3121234319 hasRelatedWork W2912574022 @default.
- W3121234319 hasRelatedWork W2919453619 @default.