Evaluating Specialized CNN Architectures for Hip Implant Loosening Detection on Radiographic Images

Basit Öğe Kaydı
dc.contributor.authorGogus, Emre
dc.contributor.authorYılmaz, Atınç
dc.date.accessioned2026-01-31T15:04:31Z
dc.date.available2026-01-31T15:04:31Z
dc.date.issued2025
dc.departmentİstanbul Beykent Üniversitesi
dc.description3rd Cognitive Models and Artificial Intelligence Conference, AICCONF 2025 -- 2025-06-13 through 2025-06-14 -- Prague -- 210372
dc.description.abstractThis study presents a deep learning approach for detecting cases of aseptic loosening from radiographic images in patients that have undergone hip arthroplasty surgery. Aseptic loosening is a leading cause of implant failure and typically requires manual evaluation by orthopedic surgeons, which can be tedious and error prone. To address this challenge, two specialized convolutional neural network (CNN) architectures, EfficientNetB3 and VGG19, as well as a standard CNN architecture were applied to the task. The three architectures were trained on a publicly available dataset obtained from the Kaggle platform, consisting of 206 anteroposterior radiographic images. The validation performances of the models were compared using the metrics of accuracy, precision, recall, F1-score, and area under receiver operating characteristic curve (AUC). VGG19 architecture achieved superior performance to the other two architectures across all metrics, attaining the highest validation accuracy of 88% and the highest AUC value of 0.91; this was followed by EfficientNetB3 and then the standard CNN. The findings demonstrated the potential of specialized pre-trained CNN architectures, leveraging transfer learning paradigm, in improving the reliability of radiographic analysis, enhancing early diagnosis, and improving patient outcomes in orthopedic radiology. © 2025 IEEE.
dc.identifier.doi10.1109/AICCONF64766.2025.11064300
dc.identifier.isbn9798331509699
dc.identifier.scopus2-s2.0-105012239780
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/AICCONF64766.2025.11064300
dc.identifier.urihttps://hdl.handle.net/20.500.12662/10574
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_Scopus_20260128
dc.subjectaseptic loosening
dc.subjectconvolutional neural networks
dc.subjectdeep learning
dc.subjecthip arthroplasty
dc.subjecthip implant
dc.subjectmedical imaging
dc.subjecttransfer learning
dc.titleEvaluating Specialized CNN Architectures for Hip Implant Loosening Detection on Radiographic Images
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu