59 113

Cited 0 times in

Automatic segmentation of inconstant fractured fragments for tibia/fibula from CT images using deep learning

Authors
 Hyeonjoo Kim  ;  Young Dae Jeon  ;  Ki Bong Park  ;  Hayeong Cha  ;  Moo-Sub Kim  ;  Juyeon You  ;  Se-Won Lee  ;  Seung-Han Shin  ;  Yang-Guk Chung  ;  Sung Bin Kang  ;  Won Seuk Jang  ;  Do-Kun Yoon 
Citation
 SCIENTIFIC REPORTS, Vol.13(1) : 20431, 2023-11 
Journal Title
SCIENTIFIC REPORTS
Issue Date
2023-11
MeSH
Deep Learning* ; Fibula / diagnostic imaging ; Image Processing, Computer-Assisted / methods ; Imaging, Three-Dimensional / methods ; Tibia / diagnostic imaging ; Tomography, X-Ray Computed* / methods
Abstract
Orthopaedic surgeons need to correctly identify bone fragments using 2D/3D CT images before trauma surgery. Advances in deep learning technology provide good insights into trauma surgery over manual diagnosis. This study demonstrates the application of the DeepLab v3+ -based deep learning model for the automatic segmentation of fragments of the fractured tibia and fibula from CT images and the results of the evaluation of the performance of the automatic segmentation. The deep learning model, which was trained using over 11 million images, showed good performance with a global accuracy of 98.92%, a weighted intersection over the union of 0.9841, and a mean boundary F1 score of 0.8921. Moreover, deep learning performed 5-8 times faster than the experts' recognition performed manually, which is comparatively inefficient, with almost the same significance. This study will play an important role in preoperative surgical planning for trauma surgery with convenience and speed.
Files in This Item:
T202306856.pdf Download
DOI
10.1038/s41598-023-47706-4
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Medical Engineering (의학공학교실) > 1. Journal Papers
Yonsei Authors
Chang, Won Seok(장원석) ORCID logo https://orcid.org/0000-0002-4925-3549
URI
https://ir.ymlib.yonsei.ac.kr/handle/22282913/197636
사서에게 알리기
  feedback

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse

Links