Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383313704> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4383313704 abstract "To develop and validate a fully automated machine learning (ML) algorithm that predicts bone marrow oedema (BMO) on a quadrant-level in sacroiliac (SI) joint MRI.A computer vision workflow automatically locates the SI joints, segments regions of interest (ilium and sacrum), performs objective quadrant extraction and predicts presence of BMO, suggestive of inflammatory lesions, on a quadrant-level in semi-coronal slices of T1/T2-weighted MRI scans. Ground truth was determined by consensus among human readers. The inflammation classifier was trained using a ResNet18 backbone and 5-fold cross-validated on scans of spondyloarthritis (SpA) patients (n=279), postpartum (n=71), and healthy subjects (n=114); while independent SpA patient MRIs (n=243) served as test dataset. Patient-level predictions were derived from aggregating quadrant-level predictions, i.e. at least one positive quadrant.The algorithm automatically detects the SI joints with a precision of 98.4% and segments ilium/sacrum with an intersection-over-union of 85.6% and 67.9%, respectively. The inflammation classifier performed well in cross-validation: area under the curve (AUC) 94.5%, balanced accuracy (B-ACC) 80.5%, and F1 score 64.1%. In the test dataset, AUC was 88.2%, B-ACC 72.1%, and F1 score 50.8%. On a patient-level, the model achieved a B-ACC of 81.6% and 81.4% in the cross-validation and test dataset, respectively.We propose a fully automated ML pipeline that enables objective and standardized evaluation of BMO along the SI joints on MRI. This method has the potential to screen large numbers of (suspected) SpA patients and is a step closer towards artificial intelligence assisted diagnosis and follow-up." @default.
- W4383313704 created "2023-07-07" @default.
- W4383313704 creator A5005204077 @default.
- W4383313704 creator A5007988300 @default.
- W4383313704 creator A5008510912 @default.
- W4383313704 creator A5022176194 @default.
- W4383313704 creator A5033532387 @default.
- W4383313704 creator A5033983216 @default.
- W4383313704 creator A5055544176 @default.
- W4383313704 creator A5063954652 @default.
- W4383313704 creator A5064309698 @default.
- W4383313704 creator A5064344455 @default.
- W4383313704 creator A5067656420 @default.
- W4383313704 creator A5089769631 @default.
- W4383313704 date "2023-07-06" @default.
- W4383313704 modified "2023-09-25" @default.
- W4383313704 title "A machine learning pipeline for predicting bone marrow oedema along the sacroiliac joints on magnetic resonance imaging" @default.
- W4383313704 doi "https://doi.org/10.1002/art.42650" @default.
- W4383313704 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37410803" @default.
- W4383313704 hasPublicationYear "2023" @default.
- W4383313704 type Work @default.
- W4383313704 citedByCount "0" @default.
- W4383313704 crossrefType "journal-article" @default.
- W4383313704 hasAuthorship W4383313704A5005204077 @default.
- W4383313704 hasAuthorship W4383313704A5007988300 @default.
- W4383313704 hasAuthorship W4383313704A5008510912 @default.
- W4383313704 hasAuthorship W4383313704A5022176194 @default.
- W4383313704 hasAuthorship W4383313704A5033532387 @default.
- W4383313704 hasAuthorship W4383313704A5033983216 @default.
- W4383313704 hasAuthorship W4383313704A5055544176 @default.
- W4383313704 hasAuthorship W4383313704A5063954652 @default.
- W4383313704 hasAuthorship W4383313704A5064309698 @default.
- W4383313704 hasAuthorship W4383313704A5064344455 @default.
- W4383313704 hasAuthorship W4383313704A5067656420 @default.
- W4383313704 hasAuthorship W4383313704A5089769631 @default.
- W4383313704 hasConcept C126838900 @default.
- W4383313704 hasConcept C141071460 @default.
- W4383313704 hasConcept C142724271 @default.
- W4383313704 hasConcept C143409427 @default.
- W4383313704 hasConcept C154945302 @default.
- W4383313704 hasConcept C2778614933 @default.
- W4383313704 hasConcept C2779455797 @default.
- W4383313704 hasConcept C2780639617 @default.
- W4383313704 hasConcept C2989005 @default.
- W4383313704 hasConcept C41008148 @default.
- W4383313704 hasConcept C71924100 @default.
- W4383313704 hasConceptScore W4383313704C126838900 @default.
- W4383313704 hasConceptScore W4383313704C141071460 @default.
- W4383313704 hasConceptScore W4383313704C142724271 @default.
- W4383313704 hasConceptScore W4383313704C143409427 @default.
- W4383313704 hasConceptScore W4383313704C154945302 @default.
- W4383313704 hasConceptScore W4383313704C2778614933 @default.
- W4383313704 hasConceptScore W4383313704C2779455797 @default.
- W4383313704 hasConceptScore W4383313704C2780639617 @default.
- W4383313704 hasConceptScore W4383313704C2989005 @default.
- W4383313704 hasConceptScore W4383313704C41008148 @default.
- W4383313704 hasConceptScore W4383313704C71924100 @default.
- W4383313704 hasLocation W43833137041 @default.
- W4383313704 hasLocation W43833137042 @default.
- W4383313704 hasOpenAccess W4383313704 @default.
- W4383313704 hasPrimaryLocation W43833137041 @default.
- W4383313704 hasRelatedWork W2007186823 @default.
- W4383313704 hasRelatedWork W2240727891 @default.
- W4383313704 hasRelatedWork W2359319730 @default.
- W4383313704 hasRelatedWork W2377341204 @default.
- W4383313704 hasRelatedWork W2389053997 @default.
- W4383313704 hasRelatedWork W2494811105 @default.
- W4383313704 hasRelatedWork W2748952813 @default.
- W4383313704 hasRelatedWork W2888821066 @default.
- W4383313704 hasRelatedWork W2899084033 @default.
- W4383313704 hasRelatedWork W32454361 @default.
- W4383313704 isParatext "false" @default.
- W4383313704 isRetracted "false" @default.
- W4383313704 workType "article" @default.