EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Shoulder Bone Segmentation with DeepLab and U-Net

Michael Carl, Kaustubh Lall, Darren Pai, Eric Chang, Sheronda Statum, Anja Brau, Christine B Chung, Maggie Fung, Won C Bae

Osteology · 11.06.2024 · 4 (2) · 98-110

DOI: 10.3390/osteology4020008 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Osteology, online erschienen am 11.06.2024. Verfasst von Michael Carl und 8 weiteren Autor:innen. Beteiligte Einrichtung: General Electric Healthcare, Menlo Park, CA. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CSRD VA, NIAMS NIH HHS, National Institute of Arthritis and Musculoskeletal and Skin Diseases of the National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Evaluation of the 3D bone morphology of the glenohumeral joint is necessary for pre-surgical planning. Zero echo time (ZTE) magnetic resonance imaging (MRI) provides excellent bone contrast and can potentially be used in the place of computed tomography. Segmentation of the shoulder anatomy, particularly the humeral head and the acetabulum, is needed for the detailed assessment of each anatomy and for pre-surgical preparation. In this study, we compared the performance of two popular deep learning models based on Google’s DeepLab and U-Net to perform automated segmentation on ZTE MRI of human shoulders. Axial ZTE images of normal shoulders (n = 31) acquired at 3-Tesla were annotated for training with DeepLab and 2D U-Net, and the trained model was validated with testing data (n = 13). While both models showed visually satisfactory results for segmenting the humeral bone, U-Net slightly over-estimated while DeepLab under-estimated the segmented area compared to the ground truth. Testing accuracy quantified by Dice score was significantly higher (p < 0.05) for U-Net (88%) than DeepLab (81%) for the humeral segmentation. We have also implemented the U-Net model onto an MRI console for push-button DL segmentation processing. Although this is an early work with limitations, our approach has the potential to improve shoulder MR evaluation hindered by manual post-processing and may provide clinical benefit for quickly visualizing bones of the glenohumeral joint.

Schlagwörter

Stichwörter der Autor:innen

DeepLabMRIU-NetZTEglenohumeralglenoidhumeral headimage processing

Autor:innen und Institutionen

  • General Electric Healthcare, Menlo Park, CA.
  • Dept. of Electrical and Computer Engineering, University of California-San Diego, CA.
  • Canyon Crest Academy, San Diego, CA.
  • Dept. of Radiology, VA San Diego Healthcare System, San Diego, CA.
  • Dept. of Radiology, University of California-San Diego, La Jolla, CA.

Förderung

  • CSRD VA
  • NIAMS NIH HHS
  • National Institute of Arthritis and Musculoskeletal and Skin Diseases of the National Institutes of Health
  • General Electric Healthcare

Zitieren

APA

Carl, M., Lall, K., Pai, D., Chang, E., Statum, S., Brau, A., Chung, C. B., Fung, M., & Bae, W. C. (2024). Shoulder Bone Segmentation with DeepLab and U-Net. Osteology, 4(2), 98-110. https://doi.org/10.3390/osteology4020008

Vancouver

Carl M, Lall K, Pai D, Chang E, Statum S, Brau A, et al. Shoulder Bone Segmentation with DeepLab and U-Net. Osteology. 2024;4(2):98-110. doi:10.3390/osteology4020008

BibTeX
@article{Carl2024,
  author = {Carl, Michael and Lall, Kaustubh and Pai, Darren and Chang, Eric and Statum, Sheronda and Brau, Anja and Chung, Christine B and Fung, Maggie and Bae, Won C},
  title = {Shoulder Bone Segmentation with DeepLab and U-Net},
  journal = {Osteology},
  year = {2024},
  volume = {4},
  number = {2},
  pages = {98--110},
  doi = {10.3390/osteology4020008}
}
Kostenlos starten →