A Deep Learning-Based Framework for Automatic Determination of Developmental Dysplasia of the Hip from Graf Angles

Basit Öğe Kaydı
dc.contributor.authorTasolar, Sevgi
dc.contributor.authorGunen, Mehmet Akif
dc.contributor.authorSigirci, Ahmet
dc.contributor.authorTasolar, Hakan
dc.date.accessioned2026-04-04T13:37:30Z
dc.date.available2026-04-04T13:37:30Z
dc.date.issued2026
dc.departmentİnönü Üniversitesi
dc.description.abstractDevelopmental dysplasia of the hip (DDH) is a common neonatal condition that necessitates early diagnosis to ensure effective treatment. The traditional Graf method, while widely used for evaluating infant hips via ultrasound, is limited by operator dependency and measurement variability. This research has proposed a framework using deep learning network, morphological operation and local maxima method to diagnose DDH in newborns using ultrasound images. The method utilizes DeepLabv3 + for image segmentation, evaluating multiple backbone architectures (ResNet50, InceptionResNetV2, MobilenetV2, and Xception) to identify the region of interest accurately. Local maxima method was used to determine the extremum points of the line defining the Graf angles. Denoising filters, including mean, median, and Wiener, are applied to determine local maxima points accurately. The evaluation comprises two stages: first, assessing the performance of DeepLabv3 + backbones in producing masks for Graf angles determination, and second, comparing the angles obtained through proposed framework with those determined by expert radiologists. Comparative analysis demonstrates that MobileNetV2 (94.64 accuracy, 86.99 Cohen's kappa, 94.31 F-score) surpasses other models in segmentation accuracy and measurement reliability. This conclusion is backed by key performance metrics such as accuracy, IoU, PSNR, F-score, SSIM, Cohen's kappa, as well as by the intraclass correlation coefficient and Bland-Altman analyses. The proposed framework shows considerable promise in automating hip ultrasound analysis for DDH diagnosis, minimizing operator dependency while enhancing measurement consistency.
dc.description.sponsorshipInonu University Scientific Research and Project unit [TSA-2024-3644]
dc.description.sponsorshipOur study is supported by the Inonu University Scientific Research and Project unit (TSA-2024-3644).
dc.identifier.doi10.1007/s10278-025-01518-2
dc.identifier.endpage264
dc.identifier.issn2948-2925
dc.identifier.issn2948-2933
dc.identifier.issue1
dc.identifier.orcid0000-0001-5164-375X
dc.identifier.orcid0000-0002-1249-7240
dc.identifier.orcid0000-0002-9836-6814
dc.identifier.orcid0000-0001-9221-0002
dc.identifier.orcid0009-0002-7051-4464
dc.identifier.pmid40325325
dc.identifier.scopus2-s2.0-105030600899
dc.identifier.scopusqualityN/A
dc.identifier.startpage250
dc.identifier.urihttps://doi.org/10.1007/s10278-025-01518-2
dc.identifier.urihttps://hdl.handle.net/11616/109871
dc.identifier.volume39
dc.identifier.wosWOS:001481359500001
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakPubMed
dc.language.isoen
dc.publisherSpringer
dc.relation.ispartofJournal of Imaging Informatics in Medicine
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250329
dc.subjectDeepLabv3+
dc.subjectGraf Angle
dc.subjectSegmentation
dc.subjectLocal maxima
dc.titleA Deep Learning-Based Framework for Automatic Determination of Developmental Dysplasia of the Hip from Graf Angles
dc.typeArticle

Dosyalar

Koleksiyon

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