Publication:
Segmentation of femoral cartilage with a hybrid method combining voxel classification and active appearance models

dc.contributor.authorAlbayrak, Songül
dc.contributor.buuauthorÖztürk, Ceyda Nur
dc.contributor.departmentMühendislik Fakültesi
dc.contributor.departmentBilgisayar Mühendisliği Bölümü
dc.contributor.orcid0000-0001-9127-715X
dc.contributor.researcheridR-4412-2018
dc.contributor.scopusid56567596600
dc.date.accessioned2024-01-10T06:23:43Z
dc.date.available2024-01-10T06:23:43Z
dc.date.issued2018
dc.descriptionBu çalışma, 11-13, Ekim 2018 tarihlerinde Bari[İtalya]’da düzenlenen 3. International Conference on Biomedical Imaging, Signal Processing (ICBSP) Kongresi‘nde bildiri olarak sunulmuştur.
dc.description.abstractIn this paper a hybrid segmentation method was proposed for delineation of the femoral cartilage compartment in knee MR images. A formerly developed voxel classification-based segmentation system was combined with an active appearance model (AAM) based segmentation system with an aim to solve the oversegmentation problems of purely classification-based approaches. The voxel classification-based segmentation was achieved through region-growing of sampled voxels depending on one-versus-all classifiers that used approximate nearest neighbour algorithm. Before the appearance model construction, dense set of correspondences were determined on the surfaces of cartilage atlases in 10 training MR images through an iterative shape-context-based non-rigid registration approach. Then, the appearance models for femoral cartilage compartment was constructed either using all of 10 training atlases or grouping these atlases as large and small depending on the physical examination information of the participants. The experimental analyses involved a comparative evaluation of the accuracies of these different AAM-based segmentations both individually and in combination with the voxel classification-based segmentations in 23 testing MR images as well as assessment of the misclassifications of the former segmentation system. As a result, the correspondence finding procedure worked successfully on the training atlases, and the hybrid segmentations with grouped appearance models achieved the closest accuracies to those of the voxel classification-based segmentation. The hybrid segmentations with appearance models that depended on the patient-specific information were evaluated as the most likely method to improve the segmentation accuracies with removal of oversegmented cartilage compartments.
dc.description.sponsorshipUnited States Department of Health & Human Services National Institutes of Health (NIH) - USA - N01-AR-2-2258 - N01-AR-2-2259 - N01-AR-2-2260 - NO1-AR-2-2261 - N01-AR-2-2262
dc.description.sponsorshipMerck & Company
dc.description.sponsorshipNovartis
dc.description.sponsorshipGlaxoSmithKline
dc.description.sponsorshipPfizer
dc.identifier.citationÖztürk, C. N. ve Albayrak, S. (2018). ''Segmentation of femoral cartilage with a hybrid method combining voxel classification and active appearance models''. ACM International Conference Proceeding Series, 57-63.
dc.identifier.doihttps://doi.org/10.1145/3288200.3288208
dc.identifier.endpage63
dc.identifier.issn978-1-4503-6477-5
dc.identifier.scopus2-s2.0-85061029894
dc.identifier.startpage57
dc.identifier.urihttps://dl.acm.org/doi/10.1145/3288200.3288208
dc.identifier.urihttps://hdl.handle.net/11452/38922
dc.identifier.wos000515851000009
dc.indexed.wosCPCIS
dc.language.isoen
dc.publisherAssoc Computing Machinery
dc.relation.collaborationYurt içi
dc.relation.journalACM International Conference Proceeding Series
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi
dc.relation.tubitak116E151
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectComputer science
dc.subjectEngineering
dc.subjectRadiology, nuclear medicine & medical imaging
dc.subjectSegmentation
dc.subjectHigh-field MR images
dc.subjectKnee joint
dc.subjectArticular cartilage
dc.subjectOsteoarthritis
dc.subjectCorrespondence finding
dc.subjectActive appearance model
dc.subjectHybrid segmentation
dc.subjectImages
dc.subjectCartilage
dc.subjectImage recognition
dc.subjectLterative methods
dc.subjectJoints (anatomy)
dc.subjectMagnetic resonance imaging
dc.subjectMedical imaging
dc.subjectNearest neighbor search
dc.subjectPetroleum reservoir evaluation
dc.subjectActive appearance models
dc.subjectArticular cartilages
dc.subjectCorrespondence finding
dc.subjectHybrid segmentation
dc.subjectKnee joint
dc.subjectMR images
dc.subject.scopusKnee Osteoarthritis; Magnetic Resonance Imaging; Cartilage
dc.subject.wosComputer science, theory & methods
dc.subject.wosEngineering, biomedical
dc.subject.wosNuclear medicine & medical imaging
dc.titleSegmentation of femoral cartilage with a hybrid method combining voxel classification and active appearance models
dc.typeArticle
dspace.entity.typePublication
local.contributor.departmentMühendislik Fakültesi/Bilgisayar Mühendisliği Bölümü
local.indexed.atPubMed
local.indexed.atScopus

Files

License bundle

Now showing 1 - 1 of 1
Placeholder
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: