Matches in SemOpenAlex for { <https://semopenalex.org/work/W4307019689> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4307019689 endingPage "197" @default.
- W4307019689 startingPage "183" @default.
- W4307019689 abstract "Machine learning algorithms are very effective at using medical imaging to study specific diseases. Numerous machine learning methods have been used to analyze medical images, such as linear discriminant analysis, support vector machines, decision trees, and random forests. Pixel/voxel-based machine learning model emerged in medical image analysis, which uses pixel/voxel values in images directly instead of features calculated from segmented objects as input information. ResNet50 is a 50-layer residual network. The main goal is to build a deeper neural network based on a modified ResNet50 without encountering the vanishing gradient problem. This chapter presents a case study which proposes and tests the feasibility of a new diagnostic methodology using both computational fluid dynamics and convolutional neural networks. The new methodology is able to identify the obstruction location in the left lung, right lung, or both lungs using hyperpolarized magnetic resonance imaging." @default.
- W4307019689 created "2022-10-22" @default.
- W4307019689 creator A5015963016 @default.
- W4307019689 creator A5026699023 @default.
- W4307019689 creator A5053354069 @default.
- W4307019689 creator A5074635902 @default.
- W4307019689 date "2022-10-21" @default.
- W4307019689 modified "2023-09-26" @default.
- W4307019689 title "Machine Learning and Deep Learning Applications in Medical Image Analysis" @default.
- W4307019689 cites W1518730042 @default.
- W4307019689 cites W1962021597 @default.
- W4307019689 cites W2028053538 @default.
- W4307019689 cites W2067927950 @default.
- W4307019689 cites W2135430305 @default.
- W4307019689 cites W2165115072 @default.
- W4307019689 cites W2305422646 @default.
- W4307019689 cites W2505030495 @default.
- W4307019689 cites W2777186991 @default.
- W4307019689 cites W2781797993 @default.
- W4307019689 cites W2804286258 @default.
- W4307019689 cites W2914093099 @default.
- W4307019689 cites W3087632574 @default.
- W4307019689 cites W3093597327 @default.
- W4307019689 cites W3093932484 @default.
- W4307019689 cites W3129095322 @default.
- W4307019689 cites W3175719338 @default.
- W4307019689 cites W3197500347 @default.
- W4307019689 cites W3181848732 @default.
- W4307019689 doi "https://doi.org/10.1002/9781119817512.ch8" @default.
- W4307019689 hasPublicationYear "2022" @default.
- W4307019689 type Work @default.
- W4307019689 citedByCount "0" @default.
- W4307019689 crossrefType "other" @default.
- W4307019689 hasAuthorship W4307019689A5015963016 @default.
- W4307019689 hasAuthorship W4307019689A5026699023 @default.
- W4307019689 hasAuthorship W4307019689A5053354069 @default.
- W4307019689 hasAuthorship W4307019689A5074635902 @default.
- W4307019689 hasConcept C108583219 @default.
- W4307019689 hasConcept C115961682 @default.
- W4307019689 hasConcept C119857082 @default.
- W4307019689 hasConcept C12267149 @default.
- W4307019689 hasConcept C153180895 @default.
- W4307019689 hasConcept C154945302 @default.
- W4307019689 hasConcept C160633673 @default.
- W4307019689 hasConcept C169258074 @default.
- W4307019689 hasConcept C31601959 @default.
- W4307019689 hasConcept C41008148 @default.
- W4307019689 hasConcept C50644808 @default.
- W4307019689 hasConcept C54170458 @default.
- W4307019689 hasConcept C69738355 @default.
- W4307019689 hasConcept C8038995 @default.
- W4307019689 hasConcept C81363708 @default.
- W4307019689 hasConcept C84525736 @default.
- W4307019689 hasConceptScore W4307019689C108583219 @default.
- W4307019689 hasConceptScore W4307019689C115961682 @default.
- W4307019689 hasConceptScore W4307019689C119857082 @default.
- W4307019689 hasConceptScore W4307019689C12267149 @default.
- W4307019689 hasConceptScore W4307019689C153180895 @default.
- W4307019689 hasConceptScore W4307019689C154945302 @default.
- W4307019689 hasConceptScore W4307019689C160633673 @default.
- W4307019689 hasConceptScore W4307019689C169258074 @default.
- W4307019689 hasConceptScore W4307019689C31601959 @default.
- W4307019689 hasConceptScore W4307019689C41008148 @default.
- W4307019689 hasConceptScore W4307019689C50644808 @default.
- W4307019689 hasConceptScore W4307019689C54170458 @default.
- W4307019689 hasConceptScore W4307019689C69738355 @default.
- W4307019689 hasConceptScore W4307019689C8038995 @default.
- W4307019689 hasConceptScore W4307019689C81363708 @default.
- W4307019689 hasConceptScore W4307019689C84525736 @default.
- W4307019689 hasLocation W43070196891 @default.
- W4307019689 hasOpenAccess W4307019689 @default.
- W4307019689 hasPrimaryLocation W43070196891 @default.
- W4307019689 hasRelatedWork W2731899572 @default.
- W4307019689 hasRelatedWork W3123344745 @default.
- W4307019689 hasRelatedWork W3195168932 @default.
- W4307019689 hasRelatedWork W4281616679 @default.
- W4307019689 hasRelatedWork W4321636153 @default.
- W4307019689 hasRelatedWork W4377964522 @default.
- W4307019689 hasRelatedWork W4381414210 @default.
- W4307019689 hasRelatedWork W4383535405 @default.
- W4307019689 hasRelatedWork W4386072274 @default.
- W4307019689 hasRelatedWork W4386123260 @default.
- W4307019689 isParatext "false" @default.
- W4307019689 isRetracted "false" @default.
- W4307019689 workType "other" @default.