Segmentation of hip joint anatomy structures from radiographic images

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0201507" target="_blank" >RIV/00216305:26220/26:0201507 - isvavai.cz</a>
Result on the web
<a href="https://hdl.handle.net/11012/255319" target="_blank" >https://hdl.handle.net/11012/255319</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.13164/eeict.2025.68" target="_blank" >10.13164/eeict.2025.68</a>

Result language
angličtina
Original language name
Segmentation of hip joint anatomy structures from radiographic images
Original language description
This paper deals with the problem of a hip joint segmentation in radiographic images with the use of a deep learning approach. The paper is focused on training nnU-Net models and creating an original dataset that contains 150 radiographs, 100 training and 50 test images. There are six trained models, five from cross-validation training and one trained on all training data. All models are evaluated on the test dataset using the Dice score for individual labels and the combined mean Dice score for the image. The best-performing model was the model trained on all training images. The most challenging labels for segmentation were those representing the Kohler teardrop and ¨ the space between the femoral head, teardrop and acetabulum due to their size and variability observed across the dataset.
Czech name
—
Czech description
—

Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings II of the 31st Conference STUDENT EEICT 2025: Selected papers.
ISBN
978-80-214-6320-2
ISSN
—
e-ISSN
2788-1334
Number of pages
4
Pages from-to
68-71
Publisher name
Brno University of Technology
Place of publication
Brno
Event location
Brno
Event date
Apr 29, 2025
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)