Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288641018> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4288641018 abstract "Automatic segmentation of pathological shoulder muscles in patients with musculo-skeletal diseases is a challenging task due to the huge variability in muscle shape, size, location, texture and injury. A reliable fully-automated segmentation method from magnetic resonance images could greatly help clinicians to plan therapeutic interventions and predict interventional outcomes while eliminating time consuming manual segmentation efforts. The purpose of this work is three-fold. First, we investigate the feasibility of pathological shoulder muscle segmentation using deep learning techniques, given a very limited amount of available annotated pediatric data. Second, we address the learning transferability from healthy to pathological data by comparing different learning schemes in terms of model generalizability. Third, extended versions of deep convolutional encoder-decoder architectures using encoders pre-trained on non-medical data are proposed to improve the segmentation accuracy. Methodological aspects are evaluated in a leave-one-out fashion on a dataset of 24 shoulder examinations from patients with obstetrical brachial plexus palsy and focus on 4 different muscles including deltoid as well as infraspinatus, supraspinatus and subscapularis from the rotator cuff. The most relevant segmentation model is partially pre-trained on ImageNet and jointly exploits inter-patient healthy and pathological annotated data. Its performance reaches Dice scores of 82.4%, 82.0%, 71.0% and 82.8% for deltoid, infraspinatus, supraspinatus and subscapularis muscles. Absolute surface estimation errors are all below 83mm$^2$ except for supraspinatus with 134.6mm$^2$. These contributions offer new perspectives for force inference in the context of musculo-skeletal disorder management." @default.
- W4288641018 created "2022-07-30" @default.
- W4288641018 creator A5012042510 @default.
- W4288641018 creator A5040529738 @default.
- W4288641018 creator A5052536540 @default.
- W4288641018 creator A5056838963 @default.
- W4288641018 creator A5080093371 @default.
- W4288641018 date "2019-01-06" @default.
- W4288641018 modified "2023-10-14" @default.
- W4288641018 title "Healthy versus pathological learning transferability in shoulder muscle MRI segmentation using deep convolutional encoder-decoders" @default.
- W4288641018 doi "https://doi.org/10.48550/arxiv.1901.01620" @default.
- W4288641018 hasPublicationYear "2019" @default.
- W4288641018 type Work @default.
- W4288641018 citedByCount "0" @default.
- W4288641018 crossrefType "posted-content" @default.
- W4288641018 hasAuthorship W4288641018A5012042510 @default.
- W4288641018 hasAuthorship W4288641018A5040529738 @default.
- W4288641018 hasAuthorship W4288641018A5052536540 @default.
- W4288641018 hasAuthorship W4288641018A5056838963 @default.
- W4288641018 hasAuthorship W4288641018A5080093371 @default.
- W4288641018 hasBestOaLocation W42886410181 @default.
- W4288641018 hasConcept C105702510 @default.
- W4288641018 hasConcept C108583219 @default.
- W4288641018 hasConcept C126838900 @default.
- W4288641018 hasConcept C137711082 @default.
- W4288641018 hasConcept C151730666 @default.
- W4288641018 hasConcept C153180895 @default.
- W4288641018 hasConcept C154945302 @default.
- W4288641018 hasConcept C2776511800 @default.
- W4288641018 hasConcept C2779343474 @default.
- W4288641018 hasConcept C41008148 @default.
- W4288641018 hasConcept C71924100 @default.
- W4288641018 hasConcept C81363708 @default.
- W4288641018 hasConcept C86803240 @default.
- W4288641018 hasConcept C89600930 @default.
- W4288641018 hasConcept C99508421 @default.
- W4288641018 hasConceptScore W4288641018C105702510 @default.
- W4288641018 hasConceptScore W4288641018C108583219 @default.
- W4288641018 hasConceptScore W4288641018C126838900 @default.
- W4288641018 hasConceptScore W4288641018C137711082 @default.
- W4288641018 hasConceptScore W4288641018C151730666 @default.
- W4288641018 hasConceptScore W4288641018C153180895 @default.
- W4288641018 hasConceptScore W4288641018C154945302 @default.
- W4288641018 hasConceptScore W4288641018C2776511800 @default.
- W4288641018 hasConceptScore W4288641018C2779343474 @default.
- W4288641018 hasConceptScore W4288641018C41008148 @default.
- W4288641018 hasConceptScore W4288641018C71924100 @default.
- W4288641018 hasConceptScore W4288641018C81363708 @default.
- W4288641018 hasConceptScore W4288641018C86803240 @default.
- W4288641018 hasConceptScore W4288641018C89600930 @default.
- W4288641018 hasConceptScore W4288641018C99508421 @default.
- W4288641018 hasLocation W42886410181 @default.
- W4288641018 hasLocation W42886410182 @default.
- W4288641018 hasLocation W42886410183 @default.
- W4288641018 hasOpenAccess W4288641018 @default.
- W4288641018 hasPrimaryLocation W42886410181 @default.
- W4288641018 hasRelatedWork W2732542196 @default.
- W4288641018 hasRelatedWork W2738221750 @default.
- W4288641018 hasRelatedWork W2795209768 @default.
- W4288641018 hasRelatedWork W3102253946 @default.
- W4288641018 hasRelatedWork W3144574764 @default.
- W4288641018 hasRelatedWork W3156786002 @default.
- W4288641018 hasRelatedWork W4226289457 @default.
- W4288641018 hasRelatedWork W4293211451 @default.
- W4288641018 hasRelatedWork W4308191152 @default.
- W4288641018 hasRelatedWork W564581980 @default.
- W4288641018 isParatext "false" @default.
- W4288641018 isRetracted "false" @default.
- W4288641018 workType "article" @default.