Evaluation of an artificial intelligence system for diagnosing scaphoid fracture on direct radiography

被引:43
|
作者
Ozkaya, Emre [1 ]
Topal, Fatih Esad [1 ]
Bulut, Tugrul [2 ]
Gursoy, Merve [3 ]
Ozuysal, Mustafa [4 ]
Karakaya, Zeynep [1 ]
机构
[1] Izmir Katip Celebi Univ, Ataturk Training & Res Hosp, Dept Emergency Med, Izmir, Turkey
[2] Izmir Katip Celebi Univ, Ataturk Training & Res Hosp, Dept Orthopaed & Traumatol, Basin Sitesi Karabaglar, Izmir, Turkey
[3] Izmir Democracy Univ, Fac Med, Dept Radiol, Izmir, Turkey
[4] Izmir Inst Technol, Dept Comp Engn, Izmir, Turkey
关键词
Scaphoid; Fracture; Deep learning; Artificial intelligence; Radiography; WRIST; MRI; INJURIES; COST;
D O I
10.1007/s00068-020-01468-0
中图分类号
R4 [临床医学];
学科分类号
1002 ; 100602 ;
摘要
Purpose The aim of this study is to determine the diagnostic performance of artificial intelligence with the use of convolutional neural networks (CNN) for detecting scaphoid fractures on anteroposterior wrist radiographs. The performance of the deep learning algorithm was also compared with that of the emergency department (ED) physician and two orthopaedic specialists (less experienced and experienced in the hand surgery). Methods A total 390 patients with AP wrist radiographs were included in the study. The presence/absence of the fracture on radiographs was confirmed via CT. The diagnostic performance of the CNN, ED physician and two orthopaedic specialists (less experienced and experienced) as measured by AUC, sensitivity, specificity, F-Score and Youden index, to detect scaphoid fractures was evaluated and compared between the groups. Results The CNN had 76% sensitivity and 92% specificity, 0.840 AUC, 0.680 Youden index and 0.826Fscore values in identifying scaphoid fractures. The experienced orthopaedic specialist had the best diagnostic performance according to AUC. While CNN's performance was similar to a less experienced orthopaedic specialist, it was better than the ED physician. Conclusion The deep learning algorithm has the potential to be used for diagnosing scaphoid fractures on radiographs. Artificial intelligence can be useful for scaphoid fracture diagnosis particularly in the absence of an experienced orthopedist or hand surgeon.
引用
收藏
页码:585 / 592
页数:8
相关论文
共 50 条
  • [41] Validity Evaluation for the Data Used for Artificial Intelligence System
    Son, Han Seong
    INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1, 2020, 1037 : 362 - 369
  • [42] The evaluation of an artificial intelligence system for estrus detection in sows
    Verhoeven, Steven
    Chantziaras, Ilias
    Bernaerdt, Elise
    Loicq, Michel
    Verhoeven, Ludo
    Maes, Dominiek
    PORCINE HEALTH MANAGEMENT, 2023, 9 (01)
  • [43] Enhanced artificial intelligence system for diagnosing and predicting breast cancer using deep learning
    Alfifi M.
    Alrahhal M.S.
    Bataineh S.
    Mezher M.
    International Journal of Advanced Computer Science and Applications, 2020, 11 (07): : 498 - 513
  • [44] Enhanced Artificial Intelligence System for Diagnosing and Predicting Breast Cancer using Deep Learning
    Alfifi, Mona
    Alrahhal, Mohamad Shady
    Bataineh, Samir
    Mezher, Mohammad
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2020, 11 (07) : 498 - 513
  • [45] Artificial intelligence in diagnostic imaging: impact on the radiography profession
    Hardy, Maryann
    Harvey, Hugh
    BRITISH JOURNAL OF RADIOLOGY, 2020, 93 (1108):
  • [46] The impact of artificial intelligence on radiography as a profession: A narrative review
    Al-Naser, Yousif Ahmed
    JOURNAL OF MEDICAL IMAGING AND RADIATION SCIENCES, 2023, 54 (01) : 162 - 166
  • [47] Developing a Recognition System for Diagnosing Melanoma Skin Lesions Using Artificial Intelligence Algorithms
    Alsaade, Fawaz Waselallah
    Aldhyani, Theyazn H. H.
    Al-Adhaileh, Mosleh Hmoud
    COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2021, 2021
  • [48] Efficacy of Digestive Endoscope Based on Artificial Intelligence System in Diagnosing Early Esophageal Carcinoma
    Zhao, Zhentao
    Li, Meng
    Liu, Ping
    Yu, Jingfang
    Zhao, Hua
    COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2022, 2022
  • [49] Suboptimal Chest Radiography and Artificial Intelligence: The Problem and the Solution
    Dasegowda, Giridhar
    Kalra, Mannudeep K.
    Abi-Ghanem, Alain S.
    Arru, Chiara D.
    Bernardo, Monica
    Saba, Luca
    Segota, Doris
    Tabrizi, Zhale
    Viswamitra, Sanjaya
    Kaviani, Parisa
    Karout, Lina
    Dreyer, Keith J.
    DIAGNOSTICS, 2023, 13 (03)
  • [50] Artificial Intelligence in Orthopedic Radiography Analysis: A Narrative Review
    Chen, Kenneth
    Stotter, Christoph
    Klestil, Thomas
    Nehrer, Stefan
    DIAGNOSTICS, 2022, 12 (09)