Matches in SemOpenAlex for { <https://semopenalex.org/work/W3134177550> ?p ?o ?g. }
- W3134177550 endingPage "e11006" @default.
- W3134177550 startingPage "e11006" @default.
- W3134177550 abstract "Prostate cancer is one of the most common cancers worldwide. Currently, convolution neural networks (CNNs) are achieving remarkable success in various computer vision tasks, and in medical imaging research. Various CNN architectures and methodologies have been applied in the field of prostate cancer diagnosis. In this work, we evaluate the impact of the adaptation of a state-of-the-art CNN architecture on domain knowledge related to problems in the diagnosis of prostate cancer. The architecture of the final CNN model was optimised on the basis of the Prostate Imaging Reporting and Data System (PI-RADS) standard, which is currently the best available indicator in the acquisition, interpretation, and reporting of prostate multi-parametric magnetic resonance imaging (mpMRI) examinations.A dataset containing 330 suspicious findings identified using mpMRI was used. Two CNN models were subjected to comparative analysis. Both implement the concept of decision-level fusion for mpMRI data, providing a separate network for each multi-parametric series. The first model implements a simple fusion of multi-parametric features to formulate the final decision. The architecture of the second model reflects the diagnostic pathway of PI-RADS methodology, using information about a lesion's primary anatomic location within the prostate gland. Both networks were experimentally tuned to successfully classify prostate cancer changes.The optimised knowledge-encoded model achieved slightly better classification results compared with the traditional model architecture (AUC = 0.84 vs. AUC = 0.82). We found the proposed model to achieve convergence significantly faster.The final knowledge-encoded CNN model provided more stable learning performance and faster convergence to optimal diagnostic accuracy. The results fail to demonstrate that PI-RADS-based modelling of CNN architecture can significantly improve performance of prostate cancer recognition using mpMRI." @default.
- W3134177550 created "2021-03-15" @default.
- W3134177550 creator A5000833811 @default.
- W3134177550 creator A5053870753 @default.
- W3134177550 creator A5079325366 @default.
- W3134177550 creator A5080338584 @default.
- W3134177550 date "2021-03-09" @default.
- W3134177550 modified "2023-09-26" @default.
- W3134177550 title "Effect of domain knowledge encoding in CNN model architecture—a prostate cancer study using mpMRI images" @default.
- W3134177550 cites W1997563283 @default.
- W3134177550 cites W2012978594 @default.
- W3134177550 cites W2044999678 @default.
- W3134177550 cites W2072033391 @default.
- W3134177550 cites W2150730101 @default.
- W3134177550 cites W2511949746 @default.
- W3134177550 cites W2623298038 @default.
- W3134177550 cites W2737065784 @default.
- W3134177550 cites W2748604568 @default.
- W3134177550 cites W2756834619 @default.
- W3134177550 cites W2767969013 @default.
- W3134177550 cites W2790005069 @default.
- W3134177550 cites W2800850596 @default.
- W3134177550 cites W2804517750 @default.
- W3134177550 cites W2806817930 @default.
- W3134177550 cites W2902977244 @default.
- W3134177550 cites W2937483840 @default.
- W3134177550 cites W2970546341 @default.
- W3134177550 cites W2979653841 @default.
- W3134177550 cites W2985947390 @default.
- W3134177550 cites W3004227146 @default.
- W3134177550 cites W3004819763 @default.
- W3134177550 cites W3008128620 @default.
- W3134177550 cites W3038862319 @default.
- W3134177550 cites W3103145119 @default.
- W3134177550 doi "https://doi.org/10.7717/peerj.11006" @default.
- W3134177550 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7953869" @default.
- W3134177550 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33732553" @default.
- W3134177550 hasPublicationYear "2021" @default.
- W3134177550 type Work @default.
- W3134177550 sameAs 3134177550 @default.
- W3134177550 citedByCount "6" @default.
- W3134177550 countsByYear W31341775502023 @default.
- W3134177550 crossrefType "journal-article" @default.
- W3134177550 hasAuthorship W3134177550A5000833811 @default.
- W3134177550 hasAuthorship W3134177550A5053870753 @default.
- W3134177550 hasAuthorship W3134177550A5079325366 @default.
- W3134177550 hasAuthorship W3134177550A5080338584 @default.
- W3134177550 hasBestOaLocation W31341775501 @default.
- W3134177550 hasConcept C105795698 @default.
- W3134177550 hasConcept C108583219 @default.
- W3134177550 hasConcept C117251300 @default.
- W3134177550 hasConcept C119857082 @default.
- W3134177550 hasConcept C121608353 @default.
- W3134177550 hasConcept C125411270 @default.
- W3134177550 hasConcept C126322002 @default.
- W3134177550 hasConcept C153180895 @default.
- W3134177550 hasConcept C154945302 @default.
- W3134177550 hasConcept C207685749 @default.
- W3134177550 hasConcept C24574437 @default.
- W3134177550 hasConcept C2780192828 @default.
- W3134177550 hasConcept C33923547 @default.
- W3134177550 hasConcept C41008148 @default.
- W3134177550 hasConcept C45347329 @default.
- W3134177550 hasConcept C50644808 @default.
- W3134177550 hasConcept C71924100 @default.
- W3134177550 hasConcept C81363708 @default.
- W3134177550 hasConceptScore W3134177550C105795698 @default.
- W3134177550 hasConceptScore W3134177550C108583219 @default.
- W3134177550 hasConceptScore W3134177550C117251300 @default.
- W3134177550 hasConceptScore W3134177550C119857082 @default.
- W3134177550 hasConceptScore W3134177550C121608353 @default.
- W3134177550 hasConceptScore W3134177550C125411270 @default.
- W3134177550 hasConceptScore W3134177550C126322002 @default.
- W3134177550 hasConceptScore W3134177550C153180895 @default.
- W3134177550 hasConceptScore W3134177550C154945302 @default.
- W3134177550 hasConceptScore W3134177550C207685749 @default.
- W3134177550 hasConceptScore W3134177550C24574437 @default.
- W3134177550 hasConceptScore W3134177550C2780192828 @default.
- W3134177550 hasConceptScore W3134177550C33923547 @default.
- W3134177550 hasConceptScore W3134177550C41008148 @default.
- W3134177550 hasConceptScore W3134177550C45347329 @default.
- W3134177550 hasConceptScore W3134177550C50644808 @default.
- W3134177550 hasConceptScore W3134177550C71924100 @default.
- W3134177550 hasConceptScore W3134177550C81363708 @default.
- W3134177550 hasLocation W31341775501 @default.
- W3134177550 hasLocation W31341775502 @default.
- W3134177550 hasLocation W31341775503 @default.
- W3134177550 hasOpenAccess W3134177550 @default.
- W3134177550 hasPrimaryLocation W31341775501 @default.
- W3134177550 hasRelatedWork W2337926734 @default.
- W3134177550 hasRelatedWork W2732542196 @default.
- W3134177550 hasRelatedWork W2738221750 @default.
- W3134177550 hasRelatedWork W2963958939 @default.
- W3134177550 hasRelatedWork W3129634582 @default.
- W3134177550 hasRelatedWork W4311257506 @default.
- W3134177550 hasRelatedWork W4312417841 @default.
- W3134177550 hasRelatedWork W4319994054 @default.
- W3134177550 hasRelatedWork W4327499916 @default.