Show simple item record

dc.contributor.authorHansen, Stine
dc.contributor.authorKuttner, Samuel
dc.contributor.authorKampffmeyer, Michael
dc.contributor.authorMarkussen, Tom-Vegard
dc.contributor.authorSundset, Rune
dc.contributor.authorØen, Silje Kjærnes
dc.contributor.authorEikenes, Live
dc.contributor.authorJenssen, Robert
dc.date.accessioned2020-12-10T10:15:19Z
dc.date.available2020-12-10T10:15:19Z
dc.date.issued2020-11-29
dc.description.abstractTumor segmentation is a crucial but difficult task in treatment planning and follow-up of cancerous patients. The challenge of automating the tumor segmentation has recently received a lot of attention, but the potential of utilizing hybrid positron emission tomography (PET)/magnetic resonance imaging (MRI), a novel and promising imaging modality in oncology, is still under-explored. Recent approaches have either relied on manual user input and/or performed the segmentation patient-by-patient, whereas a fully unsupervised segmentation framework that exploits the available information from all patients is still lacking.<p> <p>We present an unsupervised across-patients supervoxel-based clustering framework for lung tumor segmentation in hybrid PET/MRI. The method consists of two steps: First, each patient is represented by a set of PET/ MRI supervoxel-features. Then the data points from all patients are transformed and clustered on a population level into tumor and non-tumor supervoxels. The proposed framework is tested on the scans of 18 non-small cell lung cancer patients with a total of 19 tumors and evaluated with respect to manual delineations provided by clinicians. Experiments study the performance of several commonly used clustering algorithms within the framework and provide analysis of (i) the effect of tumor size, (ii) the segmentation errors, (iii) the benefit of across-patient clustering, and (iv) the noise robustness.<p> <p>The proposed framework detected 15 out of 19 tumors in an unsupervised manner. Moreover, performance increased considerably by segmenting across patients, with the mean dice score increasing from <b>0.169 ± 0.295</b> (patient-by-patient) to <b>0.470 ± 0.308</b> (across-patients). Results demonstrate that both spectral clustering and Manhattan hierarchical clustering have the potential to segment tumors in PET/MRI with a low number of missed tumors and a low number of false-positives, but that spectral clustering seems to be more robust to noise.en_US
dc.identifier.citationHansen S, Kuttner S, Kampffmeyer MC, Markussen T, Sundset R, Øen SK, Eikenes L, Jenssen R. Unsupervised supervoxel-based lung tumor segmentation across patient scans in hybrid PET/MRI. Expert systems with applications. 2020en_US
dc.identifier.cristinIDFRIDAID 1857761
dc.identifier.doi10.1016/j.eswa.2020.114244
dc.identifier.issn0957-4174
dc.identifier.issn1873-6793
dc.identifier.urihttps://hdl.handle.net/10037/20049
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.relation.ispartofHansen, S. (2022). Leveraging Supervoxels for Medical Image Volume Segmentation With Limited Supervision. (Doctoral thesis). <a href=https://hdl.handle.net/10037/27613>https://hdl.handle.net/10037/27613</a>.
dc.relation.journalExpert systems with applications
dc.relation.projectIDinfo:eu-repo/grantAgreement/RCN/IKTPLUSS/303514/Norway/Interpretable Deep Learning from Electronic Health Records under Learning Constraints//en_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2020 The Author(s)en_US
dc.subjectVDP::Technology: 500en_US
dc.subjectVDP::Teknologi: 500en_US
dc.titleUnsupervised supervoxel-based lung tumor segmentation across patient scans in hybrid PET/MRIen_US
dc.type.versionpublishedVersionen_US
dc.typeJournal articleen_US
dc.typeTidsskriftartikkelen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record