FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367060074> ?p ?o ?g. }

• W4367060074 abstract "Deep learning networks are state-of-the-art approaches for 3D brain image segmentation, and the radiological characteristics extracted from tumors are of great significance for clinical diagnosis, treatment planning, and treatment outcome evaluation. However, two problems have been the hindering factors in brain image segmentation techniques. One is that deep learning networks require large amounts of manually annotated data. Another issue is the computational efficiency of 3D deep learning networks. In this study, we propose a vector quantization (VQ)-based 3D segmentation method that employs a novel unsupervised 3D deep embedding clustering (3D-DEC) network and an efficiency memory reserving-and-fading strategy. The VQ-based 3D-DEC network is trained on volume data in an unsupervised manner to avoid manual data annotation. The memory reserving-and-fading strategy beefs up model efficiency greatly. The designed methodology makes deep learning-based model feasible for biomedical image segmentation. The experiment is divided into two parts. First, we extensively evaluate the effectiveness and robustness of the proposed model on two authoritative MRI brain tumor databases (i.e., IBSR and BrainWeb). Second, we validate the model using real 3D brain tumor data collected from our institute for clinical practice significance. Results show that our method (without data manual annotation) has superior accuracy ( $$0.74pm 0.04$$ Tanimoto coefficient on IBSR, 97.5% TP and 97.7% TN on BrainWeb, and 91% Dice, 88% sensitivity and 87% specificity on real brain data) and remarkable efficiency (speedup ratio is 18.72 on IBSR, 31.16 on BrainWeb, 31.00 on real brain data) compared to the state-of-the-art methods. The results show that our proposed model can address the lacks of manual annotations, and greatly increase computation speedup with competitive segmentation accuracy compared to other state-of-the-art 3D CNN models. Moreover, the proposed model can be used for tumor treatment follow-ups every 6 months, providing critical details for surgical and postoperative treatment by correctly extracting numerical radiomic features of tumors." @default.
• W4367060074 created "2023-04-27" @default.
• W4367060074 creator A5014199804 @default.
• W4367060074 creator A5025851882 @default.
• W4367060074 creator A5041345716 @default.
• W4367060074 creator A5042937962 @default.
• W4367060074 creator A5053416901 @default.
• W4367060074 date "2023-04-26" @default.
• W4367060074 modified "2023-09-30" @default.
• W4367060074 title "An efficient memory reserving-and-fading strategy for vector quantization based 3D brain segmentation and tumor extraction using an unsupervised deep learning network" @default.
• W4367060074 cites W1596680487 @default.
• W4367060074 cites W1884191083 @default.
• W4367060074 cites W1901129140 @default.
• W4367060074 cites W1970989973 @default.
• W4367060074 cites W1987245793 @default.
• W4367060074 cites W1999286885 @default.
• W4367060074 cites W2016420833 @default.
• W4367060074 cites W2019009403 @default.
• W4367060074 cites W2019804975 @default.
• W4367060074 cites W2034588763 @default.
• W4367060074 cites W2047929990 @default.
• W4367060074 cites W2071297770 @default.
• W4367060074 cites W2082526668 @default.
• W4367060074 cites W2097117768 @default.
• W4367060074 cites W2111006384 @default.
• W4367060074 cites W2112796928 @default.
• W4367060074 cites W2116895317 @default.
• W4367060074 cites W2120303002 @default.
• W4367060074 cites W2127558098 @default.
• W4367060074 cites W2142332605 @default.
• W4367060074 cites W2159779884 @default.
• W4367060074 cites W2165012164 @default.
• W4367060074 cites W2168031320 @default.
• W4367060074 cites W2194775991 @default.
• W4367060074 cites W2294402243 @default.
• W4367060074 cites W2301358467 @default.
• W4367060074 cites W2310992461 @default.
• W4367060074 cites W2441649867 @default.
• W4367060074 cites W2502805798 @default.
• W4367060074 cites W2562469482 @default.
• W4367060074 cites W2589409328 @default.
• W4367060074 cites W2608353599 @default.
• W4367060074 cites W2618530766 @default.
• W4367060074 cites W2630529475 @default.
• W4367060074 cites W2775021768 @default.
• W4367060074 cites W2792124446 @default.
• W4367060074 cites W2908469802 @default.
• W4367060074 cites W2947005892 @default.
• W4367060074 cites W2954704152 @default.
• W4367060074 cites W2963446712 @default.
• W4367060074 cites W2963516899 @default.
• W4367060074 cites W2984254165 @default.
• W4367060074 cites W3013630101 @default.
• W4367060074 cites W3016950250 @default.
• W4367060074 cites W3017037418 @default.
• W4367060074 cites W3023289862 @default.
• W4367060074 cites W3027360541 @default.
• W4367060074 cites W3035775638 @default.
• W4367060074 cites W3039137888 @default.
• W4367060074 cites W3125832420 @default.
• W4367060074 cites W3172728522 @default.
• W4367060074 cites W3174355196 @default.
• W4367060074 cites W3191766264 @default.
• W4367060074 cites W33787415 @default.
• W4367060074 cites W4205736652 @default.
• W4367060074 cites W4206775437 @default.
• W4367060074 cites W4283737877 @default.
• W4367060074 cites W4296197501 @default.
• W4367060074 cites W4308158142 @default.
• W4367060074 cites W4310623152 @default.
• W4367060074 cites W4318985355 @default.
• W4367060074 doi "https://doi.org/10.1007/s11571-023-09965-9" @default.
• W4367060074 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37362765" @default.
• W4367060074 hasPublicationYear "2023" @default.
• W4367060074 type Work @default.
• W4367060074 citedByCount "0" @default.
• W4367060074 crossrefType "journal-article" @default.
• W4367060074 hasAuthorship W4367060074A5014199804 @default.
• W4367060074 hasAuthorship W4367060074A5025851882 @default.
• W4367060074 hasAuthorship W4367060074A5041345716 @default.
• W4367060074 hasAuthorship W4367060074A5042937962 @default.
• W4367060074 hasAuthorship W4367060074A5053416901 @default.
• W4367060074 hasBestOaLocation W43670600741 @default.
• W4367060074 hasConcept C104317684 @default.
• W4367060074 hasConcept C108583219 @default.
• W4367060074 hasConcept C119857082 @default.
• W4367060074 hasConcept C153180895 @default.
• W4367060074 hasConcept C154945302 @default.
• W4367060074 hasConcept C185592680 @default.
• W4367060074 hasConcept C41008148 @default.
• W4367060074 hasConcept C55493867 @default.
• W4367060074 hasConcept C63479239 @default.
• W4367060074 hasConcept C73555534 @default.
• W4367060074 hasConcept C8038995 @default.
• W4367060074 hasConcept C89600930 @default.
• W4367060074 hasConceptScore W4367060074C104317684 @default.
• W4367060074 hasConceptScore W4367060074C108583219 @default.
• W4367060074 hasConceptScore W4367060074C119857082 @default.
• W4367060074 hasConceptScore W4367060074C153180895 @default.
• W4367060074 hasConceptScore W4367060074C154945302 @default.

• next