Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382052948> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4382052948 abstract "Automatic staging of non-small cell lung cancer based on CT images is an important auxiliary diagnostic method for lung cancer. Many deep learning methods have been proposed for this task, but they cannot measure the confidence of model predictions. Therefore, it is necessary to develop new deep learning methods that can measure the uncertainty of the model predictions. In this paper, we propose a Bayesian neural network (BNN) model based on CT images for staging non-small cell lung cancer patients, which can measure and utilize the uncertainty of the model predictions. The entire workflow consists of two stages: image-level classification and patient-level classification. Unlike conventional neural networks, the model's trainable pa-rameters (or weights) are set to be random, so for a fixed input, the model outputs a distribution of predictions rather than a unique result. Based on the uncertainty measurement results, two post-processing methods for model refinement are developed: 1) investigating the correlation between high uncertainty and misclassification and selecting a low uncertainty subset on the validation set to prevent the model from being overconfident, and 2) weighting and integrating the image prediction scores to obtain patient staging results. The results of training and validation on the public dataset Lung-PET-CT-Dx show that the proposed BNN model and its refined versions outperform the Cascade NN model and the RepVgg model based on transfer learning in terms of prediction accuracy and area under the receiver operating characteristic curve (AUROC) metrics. The BNN model achieved an average accuracy and AUROC of 0.760 and 0.836, respectively, with improvements 0.030 and 0.055 over Cascade NN and 0.080 and 0.067 over RepVGG, respectively. In addition, the two model refinement methods improved the performance to 0.792 and 0.842, and 0.770 and 0.841, respectively." @default.
- W4382052948 created "2023-06-27" @default.
- W4382052948 creator A5016558617 @default.
- W4382052948 creator A5078975143 @default.
- W4382052948 date "2023-04-21" @default.
- W4382052948 modified "2023-09-23" @default.
- W4382052948 title "A Bayesian neural network model based on CT images for staging non-small cell lung cancer" @default.
- W4382052948 cites W1965555277 @default.
- W4382052948 cites W2131695829 @default.
- W4382052948 cites W2148143831 @default.
- W4382052948 cites W2184779060 @default.
- W4382052948 cites W2659698999 @default.
- W4382052948 cites W2899393783 @default.
- W4382052948 cites W2902315714 @default.
- W4382052948 cites W2910509426 @default.
- W4382052948 cites W2910873889 @default.
- W4382052948 cites W2930921659 @default.
- W4382052948 cites W2947505342 @default.
- W4382052948 cites W2971376088 @default.
- W4382052948 cites W2994824962 @default.
- W4382052948 cites W3003511227 @default.
- W4382052948 cites W3026396140 @default.
- W4382052948 cites W3129747129 @default.
- W4382052948 cites W3130798577 @default.
- W4382052948 cites W3167976421 @default.
- W4382052948 cites W3168600003 @default.
- W4382052948 cites W3211109300 @default.
- W4382052948 cites W4200159581 @default.
- W4382052948 cites W4324080629 @default.
- W4382052948 doi "https://doi.org/10.1109/icccs57501.2023.10150484" @default.
- W4382052948 hasPublicationYear "2023" @default.
- W4382052948 type Work @default.
- W4382052948 citedByCount "0" @default.
- W4382052948 crossrefType "proceedings-article" @default.
- W4382052948 hasAuthorship W4382052948A5016558617 @default.
- W4382052948 hasAuthorship W4382052948A5078975143 @default.
- W4382052948 hasConcept C107673813 @default.
- W4382052948 hasConcept C119857082 @default.
- W4382052948 hasConcept C124101348 @default.
- W4382052948 hasConcept C126838900 @default.
- W4382052948 hasConcept C153180895 @default.
- W4382052948 hasConcept C154945302 @default.
- W4382052948 hasConcept C183115368 @default.
- W4382052948 hasConcept C2780009758 @default.
- W4382052948 hasConcept C33724603 @default.
- W4382052948 hasConcept C41008148 @default.
- W4382052948 hasConcept C50644808 @default.
- W4382052948 hasConcept C58471807 @default.
- W4382052948 hasConcept C71924100 @default.
- W4382052948 hasConceptScore W4382052948C107673813 @default.
- W4382052948 hasConceptScore W4382052948C119857082 @default.
- W4382052948 hasConceptScore W4382052948C124101348 @default.
- W4382052948 hasConceptScore W4382052948C126838900 @default.
- W4382052948 hasConceptScore W4382052948C153180895 @default.
- W4382052948 hasConceptScore W4382052948C154945302 @default.
- W4382052948 hasConceptScore W4382052948C183115368 @default.
- W4382052948 hasConceptScore W4382052948C2780009758 @default.
- W4382052948 hasConceptScore W4382052948C33724603 @default.
- W4382052948 hasConceptScore W4382052948C41008148 @default.
- W4382052948 hasConceptScore W4382052948C50644808 @default.
- W4382052948 hasConceptScore W4382052948C58471807 @default.
- W4382052948 hasConceptScore W4382052948C71924100 @default.
- W4382052948 hasLocation W43820529481 @default.
- W4382052948 hasOpenAccess W4382052948 @default.
- W4382052948 hasPrimaryLocation W43820529481 @default.
- W4382052948 hasRelatedWork W1581446651 @default.
- W4382052948 hasRelatedWork W2065314469 @default.
- W4382052948 hasRelatedWork W2114151954 @default.
- W4382052948 hasRelatedWork W2368984408 @default.
- W4382052948 hasRelatedWork W2902946190 @default.
- W4382052948 hasRelatedWork W2963058055 @default.
- W4382052948 hasRelatedWork W3154094704 @default.
- W4382052948 hasRelatedWork W3174196512 @default.
- W4382052948 hasRelatedWork W32248825 @default.
- W4382052948 hasRelatedWork W1629725936 @default.
- W4382052948 isParatext "false" @default.
- W4382052948 isRetracted "false" @default.
- W4382052948 workType "article" @default.