Automatic Diagnosis of Fracture using Deep Learning and External Validation: A Systematic Review and Meta-Analysis


  • Irfan Khatik Bharati Vidyapeeth Deemed to be University (Yashwantrao Mohite College, Pune, India) Pune-411038, India
  • Sachin Kadam Bharati Vidyapeeth Deemed to be University (Institute of Management and Entrepreneurship Development) Pune-411038, India
  • Milind Gayakwad Bharati Vidyapeeth Deemed to be University (College of Engineering) Pune-411043, India
  • Rahul Joshi Symbiosis Institute of Technology Pune, Symbiosis International (Deemed University), Pune, India
  • Ketan Kotecha Symbiosis Institute of Technology Pune, Symbiosis International (Deemed University), Pune, India


CNN, deep learning, External Validation, fracture


Deep learning is a hot area for automatically diagnosing X-rays for bone fractures.  Scientists are constantly working on improving clinical practices by exploring new methods. Identifying the fracture, especially hidden, using an automated method is still challenging. Very less external validation on the already studied method is available. This systematic review investigates where current artificial intelligence research stands in assisting radiologists with the correct diagnosis of bone fracture and what are the future directions.

 The hybrid approach model is necessary for images collected from the ImageNet Dataset or the Hospital's Radiology department. The processing using the variants of CNN helps in acquiring adequate accuracy for detecting the fracture in the bone in the X-ray image. X-Ray images have been taken, and the output is compared with the pre-trained dataset from ImageNet like InceptionV3, Resnet50, and VGG16.

A systematic review was performed on PubMed and Google Scholar for the studies published between 2019 and 2023. We have included ten articles for the study. These articles are thoroughly analysed and compared for factors like Accuracy, dataset, bone types, etc. External validation is also analysed for each study.

Research in detecting bone fractures through deep learning is continuously increasing. The deep learning model is a good aid in assisting radiologists and clinicians in detecting fractures. Various studies have been performed on bones, but most still need more external validation and heterogeneous data.


Download data is not yet available.


Yang, S. & Yin, B. & Cao, W. & Feng, C. & Fan, G. & He, S.. (2020). Diagnostic accuracy of deep learning in orthopaedic fractures: a systematic review and meta-analysis. Clinical Radiology. 75. 10.1016/j.crad.2020.05.021.

Bone Jt Open 2021;2-10:879–885

Shelmerdine, Susan & White, Richard & Liu, Hantao & Arthurs, Owen & Sebire, Neil. (2022). Artificial intelligence for radiological paediatric fracture assessment: a systematic review. Insights into Imaging. 13. 10.1186/s13244-022-01234-3.

Khatik, I. (2017). “A study of various bone fracture detection techniques”. International Journal of Engineering and Computer Science, 6(5), 21418-21423

Rashid, T.; Zia, M.S.; Najam-ur-Rehman; Meraj, T.; Rauf, H.T.; Kadry, S. A Minority Class Balanced Approach Using the DCNN-LSTM Method to Detect Human Wrist Fracture. Life 2023, 13, 133.

Wu J, Liu N, Li X, Fan Q, Li Z, Shang J, Wang F, Chen B, Shen Y, Cao P, Liu Z, Li M, Qian J, Yang J, Sun Q. Convolutional neural network for detecting rib fractures on chest radiographs: a feasibility study. BMC Med Imaging. 2023 Jan 30;23(1):18. doi: 10.1186/s12880-023-00975-x. PMID: 36717773; PMCID: PMC9885575.

Groot OQ, Bongers MER, Ogink PT, Senders JT, Karhade AV, Bramer JAM, Verlaan JJ, Schwab JH. Does Artificial Intelligence Outperform Natural Intelligence in Interpreting Musculoskeletal Radiological Studies? A Systematic Review. Clin Orthop Relat Res. 2020 Dec;478(12):2751-2764. doi: 10.1097/CORR.0000000000001360. PMID: 32740477; PMCID: PMC7899420.

Yao L, Guan X, Song X, Tan Y, Wang C, Jin C, Chen M, Wang H, Zhang M. Rib fracture detection system based on deep learning. Sci Rep. 2021 Dec 6;11(1):23513. Doi: 10.1038/s41598-021-03002-7. PMID: 34873241; PMCID: PMC8648839.

Anderson PG, Baum GL, Keathley N, Sicular S, Venkatesh S, Sharma A, Daluiski A, Potter H, Hotchkiss R, Lindsey RV, Jones RM. Deep Learning Assistance Closes the Accuracy Gap in Fracture Detection Across Clinician Types. Clin Orthop Relat Res. 2023 Mar 1;481(3):580-588. doi: 10.1097/CORR.0000000000002385. Epub 2022 Sep 9. PMID: 36083847; PMCID: PMC9928835.

Abbas, Waseem & Adnan, Syed & Javid, Dr & Ahmad, Wakeel. (2021). Analysis OF Tibia-Fibula Bone Fracture Using Deep Learning Technique Of X-Ray Images. International Journal for Multiscale Computational Engineering. 19. 10.1615/IntJMultCompEng.2021036137.

Anis, Shazia & Lai, Khin Wee & Chuah, Joon Huang & Ali, Muhammad & Mohafez, Hamidreza & Hadizadeh, Maryam & Ding, Yan & Chao, Ong. (2020). An Overview of Deep Learning Approaches in Chest Radiograph. IEEE Access. 8. 182347 - 182354. 10.1109/ACCESS.2020.3028390.

Bae J, Yu S, Oh J, Kim TH, Chung JH, Byun H, Yoon MS, Ahn C, Lee DK. External Validation of Deep Learning Algorithm for Detecting and Visualizing Femoral Neck Fracture Including Displaced and Non-displaced Fracture on Plain X-ray. J Digit Imaging. 2021 Oct;34(5):1099-1109. doi: 10.1007/s10278-021-00499-2. Epub 2021 Aug 11. PMID: 34379216; PMCID: PMC8554912.

Oliveira E Carmo L, van den Merkhof A, Olczak J, Gordon M, Jutte PC, Jaarsma RL, IJpma FFA, Doornberg JN, Prijs J; Machine Learning Consortium. There are increasing convolutional neural networks for fracture recognition and classification in orthopaedics: are these externally validated and ready for clinical application? Bone Jt Open. 2021 Oct;2(10):879-885. doi: 10.1302/2633-1462.210.BJO-2021-0133. PMID: 34669518; PMCID: PMC8558452.

Oakden-Rayner L, Gale W, Bonham TA, Lungren MP, Carneiro G, Bradley AP, Palmer LJ. Validation and algorithmic audit of a deep learning system for detecting proximal femoral fractures in patients in the emergency department: a diagnostic accuracy study. Lancet Digit Health. 2022 May;4(5):e351-e358. doi: 10.1016/S2589-7500(22)00004-8. Epub 2022 Apr 5. PMID: 35396184.

Huhtanen JT, Nyman M, Doncenco D, Hamedian M, Kawalya D, Salminen L, Sequeiros RB, Koskinen SK, Pudas TK, Kajander S, Niemi P, Hirvonen J, Aronen HJ, Jafaritadi M. Deep learning accurately classifies elbow joint effusion in adult and pediatric radiographs. Sci Rep. 2022 Jul 12;12(1):11803. doi: 10.1038/s41598-022-16154-x. PMID: 35821056; PMCID: PMC9276721.

Ukai K, Rahman R, Yagi N, Hayashi K, Maruo A, Muratsu H, Kobashi S. Detecting pelvic fracture on 3D-CT using deep convolutional neural networks with multi-orientated slab images. Sci Rep. 2021 Jun 3;11(1):11716. doi: 10.1038/s41598-021-91144-z. PMID: 34083655; PMCID: PMC8175387.

Veronica S, Sathiaseelan JGR (2023) Classification of Long-Bone Fractures Using Modified Faster RCNN for X-Ray Images. Indian Journal of Science and Technology 16(1): 56-65. 10.17485/IJST/v16i1.1690

Anttila TT, Karjalainen TV, Mäkelä TO, Waris EM, Lindfors NC, Leminen MM, Ryhänen JO. Detecting Distal Radius Fractures Using a Segmentation-Based Deep Learning Model. J Digit Imaging. 2023 Apr;36(2):679-687. doi: 10.1007/s10278-022-00741-5. Epub 2022 Dec 21. PMID: 36542269; PMCID: PMC10039




How to Cite

Khatik, I. ., Kadam, S. ., Gayakwad, M. ., Joshi, R. ., & Kotecha, K. . (2024). Automatic Diagnosis of Fracture using Deep Learning and External Validation: A Systematic Review and Meta-Analysis. International Journal of Intelligent Systems and Applications in Engineering, 12(16s), 41–48. Retrieved from



Research Article

Most read articles by the same author(s)