EUVIMEDEUVIMED entdecken
Open Access

Deep learning-based detection of primary bone tumors around the knee joint on radiographs: a multicenter study

Danyang Xu, Bing Li, Weixiang Liu, Dan Wei, Xiaowu Long, Tanyu Huang, Hongxin Lin, Kangyang Cao, Shaonan Zhong, Jingjing Shao, Bingsheng Huang, Xian-Fen Diao und 1 weitere

Quantitative Imaging in Medicine and Surgery · 2024-08 · 14 (8) · 5420-5433

DOI: 10.21037/qims-23-1743 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Quantitative Imaging in Medicine and Surgery, 2024-08. Verfasst von Danyang Xu und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China. Die Arbeit wurde bisher 20-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Most primary bone tumors are often found in the bone around the knee joint. However, the detection of primary bone tumors on radiographs can be challenging for the inexperienced or junior radiologist. This study aimed to develop a deep learning (DL) model for the detection of primary bone tumors around the knee joint on radiographs.

Methods

From four tertiary referral centers, we recruited 687 patients diagnosed with bone tumors (including osteosarcoma, chondrosarcoma, giant cell tumor of bone, bone cyst, enchondroma, fibrous dysplasia, etc.; 417 males, 270 females; mean age 22.8±13.2 years) by postoperative pathology or clinical imaging/follow-up, and 1,988 participants with normal bone radiographs (1,152 males, 836 females; mean age 27.9±12.2 years). The dataset was split into a training set for model development, an internal independent and an external test set for model validation. The trained model located bone tumor lesions and then detected tumor patients. Receiver operating characteristic curves and Cohen's kappa coefficient were used for evaluating detection performance. We compared the model's detection performance with that of two junior radiologists in the internal test set using permutation tests.

Results

The DL model correctly localized 94.5% and 92.9% bone tumors on radiographs in the internal and external test set, respectively. An accuracy of 0.964/0.920, and an area under the receiver operating characteristic curve (AUC) of 0.981/0.990 in DL detection of bone tumor patients were for the internal and external test set, respectively. Cohen's kappa coefficient of the model in the internal test set was significantly higher than that of the two junior radiologists with 4 and 3 years of experience in musculoskeletal radiology (Model vs. Reader A, 0.927 vs. 0.777, P

Schlagwörter

Stichwörter der Autor:innen

Bone neoplasmsdeep learning (DL)knee jointradiography

Autor:innen und Institutionen

  • Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China.
  • Medical AI Lab, School of Biomedical Engineering, Health Science Centre, Shenzhen University, Shenzhen, China.
  • National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, Medical School, Shenzhen University, Shenzhen, China.
  • Department of Radiology, Huiya Hospital of The First Affiliated Hospital, Sun Yat-sen University, Huizhou, China.
  • Department of Radiology, Yunfu People's Hospital, Yunfu, China.
  • Department of Radiology, The Second People's Hospital of Huizhou, Huizhou, China.

Zitieren

APA

Xu, D., Li, B., Liu, W., Wei, D., Long, X., Huang, T., Lin, H., Cao, K., Zhong, S., Shao, J., Huang, B., Diao, X. F., & Gao, Z. (2024). Deep learning-based detection of primary bone tumors around the knee joint on radiographs: a multicenter study. Quantitative Imaging in Medicine and Surgery, 14(8), 5420-5433. https://doi.org/10.21037/qims-23-1743

Vancouver

Xu D, Li B, Liu W, Wei D, Long X, Huang T, et al. Deep learning-based detection of primary bone tumors around the knee joint on radiographs: a multicenter study. Quantitative Imaging in Medicine and Surgery. 2024;14(8):5420-5433. doi:10.21037/qims-23-1743

BibTeX
@article{Xu2024,
  author = {Xu, Danyang and Li, Bing and Liu, Weixiang and Wei, Dan and Long, Xiaowu and Huang, Tanyu and Lin, Hongxin and Cao, Kangyang and Zhong, Shaonan and Shao, Jingjing and Huang, Bingsheng and Diao, Xian-Fen and Gao, Zhenhua},
  title = {Deep learning-based detection of primary bone tumors around the knee joint on radiographs: a multicenter study},
  journal = {Quantitative Imaging in Medicine and Surgery},
  year = {2024},
  volume = {14},
  number = {8},
  pages = {5420--5433},
  doi = {10.21037/qims-23-1743}
}
Kostenlos starten →