Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288804878> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4288804878 abstract "Pathologies systematically induce morphological changes, thus providing a major but yet insufficiently quantified source of observables for diagnosis. The study develops a predictive model of the pathological states based on morphological features (3D-morphomics) on Computed Tomography (CT) volumes. A complete workflow for mesh extraction and simplification of an organ's surface is developed, and coupled with an automatic extraction of morphological features given by the distribution of mean curvature and mesh energy. An XGBoost supervised classifier is then trained and tested on the 3D-morphomics to predict the pathological states. This framework is applied to the prediction of the malignancy of lung's nodules. On a subset of NLST database with malignancy confirmed biopsy, using 3D-morphomics only, the classification model of lung nodules into malignant vs. benign achieves 0.964 of AUC. Three other sets of classical features are trained and tested, (1) clinical relevant features gives an AUC of 0.58, (2) 111 radiomics gives an AUC of 0.976, (3) radiologist ground truth (GT) containing the nodule size, attenuation and spiculation qualitative annotations gives an AUC of 0.979. We also test the Brock model and obtain an AUC of 0.826. Combining 3D-morphomics and radiomics features achieves state-of-the-art results with an AUC of 0.978 where the 3D-morphomics have some of the highest predictive powers. As a validation on a public independent cohort, models are applied to the LIDC dataset, the 3D-morphomics achieves an AUC of 0.906 and the 3D-morphomics+radiomics achieves an AUC of 0.958, which ranks second in the challenge among deep models. It establishes the curvature distributions as efficient features for predicting lung nodule malignancy and a new method that can be applied directly to arbitrary computer aided diagnosis task." @default.
- W4288804878 created "2022-07-30" @default.
- W4288804878 creator A5011433814 @default.
- W4288804878 creator A5021293751 @default.
- W4288804878 creator A5028663698 @default.
- W4288804878 creator A5038148603 @default.
- W4288804878 creator A5041742956 @default.
- W4288804878 creator A5043631229 @default.
- W4288804878 creator A5057075392 @default.
- W4288804878 creator A5058831216 @default.
- W4288804878 creator A5067595350 @default.
- W4288804878 creator A5073719392 @default.
- W4288804878 creator A5079385353 @default.
- W4288804878 creator A5083026381 @default.
- W4288804878 date "2022-07-27" @default.
- W4288804878 modified "2023-09-27" @default.
- W4288804878 title "3D-Morphomics, Morphological Features on CT scans for lung nodule malignancy diagnosis" @default.
- W4288804878 doi "https://doi.org/10.48550/arxiv.2207.13830" @default.
- W4288804878 hasPublicationYear "2022" @default.
- W4288804878 type Work @default.
- W4288804878 citedByCount "0" @default.
- W4288804878 crossrefType "posted-content" @default.
- W4288804878 hasAuthorship W4288804878A5011433814 @default.
- W4288804878 hasAuthorship W4288804878A5021293751 @default.
- W4288804878 hasAuthorship W4288804878A5028663698 @default.
- W4288804878 hasAuthorship W4288804878A5038148603 @default.
- W4288804878 hasAuthorship W4288804878A5041742956 @default.
- W4288804878 hasAuthorship W4288804878A5043631229 @default.
- W4288804878 hasAuthorship W4288804878A5057075392 @default.
- W4288804878 hasAuthorship W4288804878A5058831216 @default.
- W4288804878 hasAuthorship W4288804878A5067595350 @default.
- W4288804878 hasAuthorship W4288804878A5073719392 @default.
- W4288804878 hasAuthorship W4288804878A5079385353 @default.
- W4288804878 hasAuthorship W4288804878A5083026381 @default.
- W4288804878 hasBestOaLocation W42888048781 @default.
- W4288804878 hasConcept C126838900 @default.
- W4288804878 hasConcept C142724271 @default.
- W4288804878 hasConcept C151730666 @default.
- W4288804878 hasConcept C153180895 @default.
- W4288804878 hasConcept C154945302 @default.
- W4288804878 hasConcept C2776731575 @default.
- W4288804878 hasConcept C2778559731 @default.
- W4288804878 hasConcept C2779399171 @default.
- W4288804878 hasConcept C41008148 @default.
- W4288804878 hasConcept C71924100 @default.
- W4288804878 hasConcept C86803240 @default.
- W4288804878 hasConceptScore W4288804878C126838900 @default.
- W4288804878 hasConceptScore W4288804878C142724271 @default.
- W4288804878 hasConceptScore W4288804878C151730666 @default.
- W4288804878 hasConceptScore W4288804878C153180895 @default.
- W4288804878 hasConceptScore W4288804878C154945302 @default.
- W4288804878 hasConceptScore W4288804878C2776731575 @default.
- W4288804878 hasConceptScore W4288804878C2778559731 @default.
- W4288804878 hasConceptScore W4288804878C2779399171 @default.
- W4288804878 hasConceptScore W4288804878C41008148 @default.
- W4288804878 hasConceptScore W4288804878C71924100 @default.
- W4288804878 hasConceptScore W4288804878C86803240 @default.
- W4288804878 hasLocation W42888048781 @default.
- W4288804878 hasOpenAccess W4288804878 @default.
- W4288804878 hasPrimaryLocation W42888048781 @default.
- W4288804878 hasRelatedWork W1089315 @default.
- W4288804878 hasRelatedWork W3633124 @default.
- W4288804878 hasRelatedWork W3896151 @default.
- W4288804878 hasRelatedWork W4632594 @default.
- W4288804878 hasRelatedWork W553262 @default.
- W4288804878 hasRelatedWork W5851984 @default.
- W4288804878 hasRelatedWork W7101404 @default.
- W4288804878 hasRelatedWork W7120361 @default.
- W4288804878 hasRelatedWork W7719265 @default.
- W4288804878 hasRelatedWork W8815345 @default.
- W4288804878 isParatext "false" @default.
- W4288804878 isRetracted "false" @default.
- W4288804878 workType "article" @default.