Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383472743> ?p ?o ?g. }
Showing items 1 to 59 of
59
with 100 items per page.
- W4383472743 abstract "Endometriosis is a common chronic gynecological disorder that has many characteristics, including the pouch of Douglas (POD) obliteration, which can be diagnosed using Transvaginal gynecological ultrasound (TVUS) scans and magnetic resonance imaging (MRI). TVUS and MRI are complementary non-invasive endometriosis diagnosis imaging techniques, but patients are usually not scanned using both modalities and, it is generally more challenging to detect POD obliteration from MRI than TVUS. To mitigate this classification imbalance, we propose in this paper a knowledge distillation training algorithm to improve the POD obliteration detection from MRI by leveraging the detection results from unpaired TVUS data. More specifically, our algorithm pre-trains a teacher model to detect POD obliteration from TVUS data, and it also pre-trains a student model with 3D masked auto-encoder using a large amount of unlabelled pelvic 3D MRI volumes. Next, we distill the knowledge from the teacher TVUS POD obliteration detector to train the student MRI model by minimizing a regression loss that approximates the output of the student to the teacher using unpaired TVUS and MRI data. Experimental results on our endometriosis dataset containing TVUS and MRI data demonstrate the effectiveness of our method to improve the POD detection accuracy from MRI." @default.
- W4383472743 created "2023-07-07" @default.
- W4383472743 creator A5017468053 @default.
- W4383472743 creator A5020577930 @default.
- W4383472743 creator A5029215323 @default.
- W4383472743 creator A5031767581 @default.
- W4383472743 creator A5052912720 @default.
- W4383472743 creator A5079344414 @default.
- W4383472743 creator A5085105499 @default.
- W4383472743 date "2023-07-04" @default.
- W4383472743 modified "2023-10-01" @default.
- W4383472743 title "Distilling Missing Modality Knowledge from Ultrasound for Endometriosis Diagnosis with Magnetic Resonance Images" @default.
- W4383472743 doi "https://doi.org/10.48550/arxiv.2307.02000" @default.
- W4383472743 hasPublicationYear "2023" @default.
- W4383472743 type Work @default.
- W4383472743 citedByCount "0" @default.
- W4383472743 crossrefType "posted-content" @default.
- W4383472743 hasAuthorship W4383472743A5017468053 @default.
- W4383472743 hasAuthorship W4383472743A5020577930 @default.
- W4383472743 hasAuthorship W4383472743A5029215323 @default.
- W4383472743 hasAuthorship W4383472743A5031767581 @default.
- W4383472743 hasAuthorship W4383472743A5052912720 @default.
- W4383472743 hasAuthorship W4383472743A5079344414 @default.
- W4383472743 hasAuthorship W4383472743A5085105499 @default.
- W4383472743 hasBestOaLocation W43834727431 @default.
- W4383472743 hasConcept C126838900 @default.
- W4383472743 hasConcept C142724271 @default.
- W4383472743 hasConcept C143409427 @default.
- W4383472743 hasConcept C143753070 @default.
- W4383472743 hasConcept C154945302 @default.
- W4383472743 hasConcept C2779522080 @default.
- W4383472743 hasConcept C2780226545 @default.
- W4383472743 hasConcept C41008148 @default.
- W4383472743 hasConcept C71924100 @default.
- W4383472743 hasConceptScore W4383472743C126838900 @default.
- W4383472743 hasConceptScore W4383472743C142724271 @default.
- W4383472743 hasConceptScore W4383472743C143409427 @default.
- W4383472743 hasConceptScore W4383472743C143753070 @default.
- W4383472743 hasConceptScore W4383472743C154945302 @default.
- W4383472743 hasConceptScore W4383472743C2779522080 @default.
- W4383472743 hasConceptScore W4383472743C2780226545 @default.
- W4383472743 hasConceptScore W4383472743C41008148 @default.
- W4383472743 hasConceptScore W4383472743C71924100 @default.
- W4383472743 hasLocation W43834727431 @default.
- W4383472743 hasOpenAccess W4383472743 @default.
- W4383472743 hasPrimaryLocation W43834727431 @default.
- W4383472743 hasRelatedWork W2019231036 @default.
- W4383472743 hasRelatedWork W2093708693 @default.
- W4383472743 hasRelatedWork W2155867211 @default.
- W4383472743 hasRelatedWork W2158469081 @default.
- W4383472743 hasRelatedWork W2798310738 @default.
- W4383472743 hasRelatedWork W3032760841 @default.
- W4383472743 hasRelatedWork W3170934895 @default.
- W4383472743 hasRelatedWork W4306849910 @default.
- W4383472743 hasRelatedWork W4360810369 @default.
- W4383472743 hasRelatedWork W2093182991 @default.
- W4383472743 isParatext "false" @default.
- W4383472743 isRetracted "false" @default.
- W4383472743 workType "article" @default.