TMS-Net: A segmentation network coupled with a run-time quality control method for robust cardiac image segmentation

Basit Öğe Kaydı
dc.authorid0000-0001-8808-2714
dc.contributor.authorUslu, Fatmatuelzehra
dc.contributor.authorBharath, Anil A.
dc.date.accessioned2026-02-12T21:04:52Z
dc.date.available2026-02-12T21:04:52Z
dc.date.issued2023
dc.departmentBursa Teknik Üniversitesi
dc.description.abstractRecently, deep networks have shown impressive performance for the segmentation of cardiac Magnetic Resonance Imaging (MRI) images. However, their achievement is proving slow to transition to widespread use in medical clinics because of robustness issues leading to low trust of clinicians to their results. Predicting run-time quality of segmentation masks can be useful to warn clinicians against poor results. Despite its importance, there are few studies on this problem. To address this gap, we propose a quality control method based on the agreement across decoders of a multi-view network, TMS-Net, measured by the cosine similarity. The network takes three view inputs resliced from the same 3D image along different axes. Different from previous multi-view networks, TMS-Net has a single encoder and three decoders, leading to better noise robustness, segmentation performance and run-time quality estimation in our experiments on the segmentation of the left atrium on STACOM 2013 and STACOM 2018 challenge datasets. We also present a way to generate poor segmentation masks by using noisy images generated with engineered noise and Rician noise to simulate undertraining, high anisotropy and poor imaging settings problems. Our run-time quality estimation method show a good classification of poor and good quality segmentation masks with an AUC reaching to 0.97 on STACOM 2018. We believe that TMS-Net and our run-time quality estimation method has a high potential to increase the thrust of clinicians to automatic image analysis tools.
dc.description.sponsorshipBursa Technical University Scientific Research Projects Units; [211N043]
dc.description.sponsorshipAcknowledgement This work is financially supported by Bursa Technical University Scientific Research Projects Units, with the project number of 211N043.
dc.identifier.doi10.1016/j.compbiomed.2022.106422
dc.identifier.issn0010-4825
dc.identifier.issn1879-0534
dc.identifier.pmid36535210
dc.identifier.scopus2-s2.0-85144381408
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.compbiomed.2022.106422
dc.identifier.urihttps://hdl.handle.net/20.500.12885/6691
dc.identifier.volume152
dc.identifier.wosWOS:000906520100001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherPergamon-Elsevier Science Ltd
dc.relation.ispartofComputers in Biology and Medicine
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WoS_20260212
dc.subjectRobust image segmentation
dc.subjectTrustworthiness
dc.subjectCardiac image analysis
dc.subjectEngineered noise
dc.subjectRician noise
dc.titleTMS-Net: A segmentation network coupled with a run-time quality control method for robust cardiac image segmentation
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
PubMed İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu