Tooth Instance Segmentation on Panoramic Dental Radiographs Using U-Nets and Morphological Processing

Basit Öğe Kaydı
dc.contributor.authorHelli, Selahattin Serdar
dc.contributor.authorHamamcı, Andaç
dc.date.accessioned2023-04-10T20:29:28Z
dc.date.available2023-04-10T20:29:28Z
dc.date.issued2022
dc.departmentRektörlük, Rektörlüğe Bağlı Birimler, Düzce Üniversitesi Dergilerien_US
dc.description.abstractAutomatic teeth segmentation in panoramic x-ray images is an important research subject of the image analysis in dentistry. In this study, we propose a post-processing stage to obtain a segmentation map in which the objects in the image are separated, and apply this technique to tooth instance segmentation with U-Net network. The post-processing consists of grayscale morphological and filtering operations, which are applied to the sigmoid output of the network before binarization. A dice overlap score of 95.4±0.3% is obtained in overall teeth segmentation. The proposed post-processing stages reduce the mean error of tooth count to 6.15%, whereas the error without post-processing is 26.81%. The performances of both segmentation and tooth counting are the highest in the literature, to our knowledge. Moreover, this is achieved by using a relatively small training dataset, which consists of 105 images. Although the aim in this study is to segment tooth instances, the presented method is applicable to similar problems in other domains, such as separating the cell instances.en_US
dc.identifier.doi10.29130/dubited.950568
dc.identifier.endpage50en_US
dc.identifier.issn2148-2446
dc.identifier.issue1en_US
dc.identifier.startpage39en_US
dc.identifier.trdizinid1123384en_US
dc.identifier.urihttp://doi.org/10.29130/dubited.950568
dc.identifier.urihttps://search.trdizin.gov.tr/yayin/detay/1123384
dc.identifier.urihttps://hdl.handle.net/20.500.12684/11874
dc.identifier.volume10en_US
dc.indekslendigikaynakTR-Dizinen_US
dc.language.isoenen_US
dc.relation.ispartofDüzce Üniversitesi Bilim ve Teknoloji Dergisi
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectDentalen_US
dc.subjectPanoramicen_US
dc.subjectSegmentationen_US
dc.subjectInstance Segmentationen_US
dc.subjectCountingen_US
dc.subjectU-net Dişen_US
dc.subjectPanoramiken_US
dc.subjectBölütlemeen_US
dc.subjectÖrnek bölütlemeen_US
dc.subjectSaymaen_US
dc.subjectU-Neten_US
dc.titleTooth Instance Segmentation on Panoramic Dental Radiographs Using U-Nets and Morphological Processingen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
11874.pdf
Boyut:
1018.95 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

TR-Dizin İndeksli Yayınlar Koleksiyonu
Düzce Üniversitesi Bilim ve Teknoloji Dergisi Koleksiyonu