Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387398565> ?p ?o ?g. }
- W4387398565 endingPage "106117" @default.
- W4387398565 startingPage "106117" @default.
- W4387398565 abstract "A typical problem in the registration of MRI and X-ray mammography is the nonlinear deformation applied to the breast during mammography. We have developed a method for virtual deformation of the breast using a biomechanical model automatically constructed from MRI. The virtual deformation is applied in two steps: unloaded state estimation and compression simulation. The finite element method is used to solve the deformation process. However, the extensive computational cost prevents its usage in clinical routine.We propose three machine learning models to overcome this problem: an extremely randomized tree (first model), extreme gradient boosting (second model), and deep learning-based bidirectional long short-term memory with an attention layer (third model) to predict the deformation of a biomechanical model. We evaluated our methods with 516 breasts with realistic compression ratios up to 76%.We first applied one-fold validation, in which the second and third models performed better than the first model. We then applied ten-fold validation. For the unloaded state estimation, the median RMSE for the second and third models is 0.8 mm and 1.2 mm, respectively. For the compression, the median RMSE is 3.4 mm for both models. We evaluated correlations between model accuracy and characteristics of the clinical datasets such as compression ratio, breast volume, and tissue types.Using the proposed models, we achieved accurate results comparable to the finite element model, with a speedup of factor 240 using the extreme gradient boosting model. These proposed models can replace the finite element model simulation, enabling clinically relevant real-time application." @default.
- W4387398565 created "2023-10-07" @default.
- W4387398565 creator A5003047845 @default.
- W4387398565 creator A5005480071 @default.
- W4387398565 creator A5015268976 @default.
- W4387398565 creator A5017963342 @default.
- W4387398565 creator A5029994918 @default.
- W4387398565 creator A5079699761 @default.
- W4387398565 date "2023-12-01" @default.
- W4387398565 modified "2023-10-18" @default.
- W4387398565 title "Estimation of the biomechanical mammographic deformation of the breast using machine learning models" @default.
- W4387398565 cites W1970471390 @default.
- W4387398565 cites W2008861894 @default.
- W4387398565 cites W2013888203 @default.
- W4387398565 cites W2024120507 @default.
- W4387398565 cites W2032222443 @default.
- W4387398565 cites W2047720179 @default.
- W4387398565 cites W2049309414 @default.
- W4387398565 cites W2055360731 @default.
- W4387398565 cites W2056132907 @default.
- W4387398565 cites W2065830726 @default.
- W4387398565 cites W2066809302 @default.
- W4387398565 cites W2071061938 @default.
- W4387398565 cites W2078420436 @default.
- W4387398565 cites W2106804889 @default.
- W4387398565 cites W2110229770 @default.
- W4387398565 cites W2145913256 @default.
- W4387398565 cites W2413431392 @default.
- W4387398565 cites W2581891111 @default.
- W4387398565 cites W2758941972 @default.
- W4387398565 cites W2770839846 @default.
- W4387398565 cites W2917571395 @default.
- W4387398565 cites W3107393033 @default.
- W4387398565 doi "https://doi.org/10.1016/j.clinbiomech.2023.106117" @default.
- W4387398565 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37826970" @default.
- W4387398565 hasPublicationYear "2023" @default.
- W4387398565 type Work @default.
- W4387398565 citedByCount "0" @default.
- W4387398565 crossrefType "journal-article" @default.
- W4387398565 hasAuthorship W4387398565A5003047845 @default.
- W4387398565 hasAuthorship W4387398565A5005480071 @default.
- W4387398565 hasAuthorship W4387398565A5015268976 @default.
- W4387398565 hasAuthorship W4387398565A5017963342 @default.
- W4387398565 hasAuthorship W4387398565A5029994918 @default.
- W4387398565 hasAuthorship W4387398565A5079699761 @default.
- W4387398565 hasConcept C105795698 @default.
- W4387398565 hasConcept C111919701 @default.
- W4387398565 hasConcept C11413529 @default.
- W4387398565 hasConcept C119857082 @default.
- W4387398565 hasConcept C121608353 @default.
- W4387398565 hasConcept C126322002 @default.
- W4387398565 hasConcept C127413603 @default.
- W4387398565 hasConcept C135628077 @default.
- W4387398565 hasConcept C139945424 @default.
- W4387398565 hasConcept C154945302 @default.
- W4387398565 hasConcept C159985019 @default.
- W4387398565 hasConcept C192562407 @default.
- W4387398565 hasConcept C204366326 @default.
- W4387398565 hasConcept C2780472235 @default.
- W4387398565 hasConcept C33923547 @default.
- W4387398565 hasConcept C41008148 @default.
- W4387398565 hasConcept C530470458 @default.
- W4387398565 hasConcept C66938386 @default.
- W4387398565 hasConcept C68339613 @default.
- W4387398565 hasConcept C71924100 @default.
- W4387398565 hasConceptScore W4387398565C105795698 @default.
- W4387398565 hasConceptScore W4387398565C111919701 @default.
- W4387398565 hasConceptScore W4387398565C11413529 @default.
- W4387398565 hasConceptScore W4387398565C119857082 @default.
- W4387398565 hasConceptScore W4387398565C121608353 @default.
- W4387398565 hasConceptScore W4387398565C126322002 @default.
- W4387398565 hasConceptScore W4387398565C127413603 @default.
- W4387398565 hasConceptScore W4387398565C135628077 @default.
- W4387398565 hasConceptScore W4387398565C139945424 @default.
- W4387398565 hasConceptScore W4387398565C154945302 @default.
- W4387398565 hasConceptScore W4387398565C159985019 @default.
- W4387398565 hasConceptScore W4387398565C192562407 @default.
- W4387398565 hasConceptScore W4387398565C204366326 @default.
- W4387398565 hasConceptScore W4387398565C2780472235 @default.
- W4387398565 hasConceptScore W4387398565C33923547 @default.
- W4387398565 hasConceptScore W4387398565C41008148 @default.
- W4387398565 hasConceptScore W4387398565C530470458 @default.
- W4387398565 hasConceptScore W4387398565C66938386 @default.
- W4387398565 hasConceptScore W4387398565C68339613 @default.
- W4387398565 hasConceptScore W4387398565C71924100 @default.
- W4387398565 hasFunder F4320320879 @default.
- W4387398565 hasFunder F4320321181 @default.
- W4387398565 hasLocation W43873985651 @default.
- W4387398565 hasLocation W43873985652 @default.
- W4387398565 hasOpenAccess W4387398565 @default.
- W4387398565 hasPrimaryLocation W43873985651 @default.
- W4387398565 hasRelatedWork W2013643406 @default.
- W4387398565 hasRelatedWork W2027972911 @default.
- W4387398565 hasRelatedWork W2058965144 @default.
- W4387398565 hasRelatedWork W2111089054 @default.
- W4387398565 hasRelatedWork W2146343568 @default.
- W4387398565 hasRelatedWork W2150291671 @default.
- W4387398565 hasRelatedWork W2157978810 @default.