Korean Journal of Radiology

  • 제21권7호
  • /
  • Pages.891-899
  • /
  • 2020
  • /
  • 1229-6929(pISSN)
  • /
  • 2005-8330(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

Assessment of a Deep Learning Algorithm for the Detection of Rib Fractures on Whole-Body Trauma Computed Tomography

  • Thomas Weikert (Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel) ;
  • Luca Andre Noordtzij (Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel) ;
  • Jens Bremerich (Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel) ;
  • Bram Stieltjes (Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel) ;
  • Victor Parmar (Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel) ;
  • Joshy Cyriac (Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel) ;
  • Gregor Sommer (Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel) ;
  • Alexander Walter Sauter (Clinic of Radiology and Nuclear Medicine, University Hospital Basel, University of Basel)
  • 투고 : 2019.09.01
  • 심사 : 2020.02.19
  • 발행 : 2020.07.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. Materials and Methods: We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). Results: All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. Conclusion: We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

키워드

과제정보

We acknowledge the provision of the rib fracture detection algorithm prototype by Aidoc Medical (Tel Aviv, Israel).

참고문헌

  1. Sirmali M, Turut H, Topcu S, Gulhan E, Yazici U, Kaya S, et al. A comprehensive analysis of traumatic rib fractures: morbidity, mortality and management. Eur J Cardiothorac Surg 2003;24:133-138  https://doi.org/10.1016/S1010-7940(03)00256-2
  2. Sokolovskaya E, Shinde T, Ruchman RB, Kwak AJ, Lu S, Shariff YK, et al. The effect of faster reporting speed for imaging studies on the number of misses and interpretation errors: a pilot study. J Am Coll Radiol 2015;12:683-688  https://doi.org/10.1016/j.jacr.2015.03.040
  3. Park SH, Song HH, Han JH, Park JM, Lee EJ, Park SM, et al. Effect of noise on the detection of rib fractures by residents. Invest Radiol 1994;29:54-58  https://doi.org/10.1097/00004424-199401000-00009
  4. Berbaum KS, Franken EA, Dorfman DD, Rooholamini SA, Coffman CE, Cornell SH, et al. Time course of satisfaction of search. Invest Radiol 1991;26:640-648  https://doi.org/10.1097/00004424-199107000-00003
  5. Banaste N, Caurier B, Bratan F, Bergerot JF, Thomson V, Millet I. Whole-body CT in patients with multiple traumas: factors leading to missed injury. Radiology 2018;289:374-383  https://doi.org/10.1148/radiol.2018180492
  6. Cho SH, Sung YM, Kim MS. Missed rib fractures on evaluation of initial chest CT for trauma patients: pattern analysis and diagnostic value of coronal multiplanar reconstruction images with multidetector row CT. Br J Radiol 2012;85:e845-e850  https://doi.org/10.1259/bjr/28575455
  7. Mayberry JC, Schipper PH. Traumatic rib fracture: conservative therapy or surgical fixation?. In: Ferguson M, ed. Difficult decisions in thoracic surgery. London: Springer, 2011:489-493 
  8. Lu MS, Huang YK, Liu YH, Liu HP, Kao CL. Delayed pneumothorax complicating minor rib fracture after chest trauma. Am J Emerg Med 2008;26:551-554  https://doi.org/10.1016/j.ajem.2007.08.022
  9. Ho SW, Teng YH, Yang SF, Yeh HW, Wang YH, Chou MC, et al. Risk of pneumonia in patients with isolated minor rib fractures: a nationwide cohort study. BMJ Open 2017;7:e013029 
  10. Tanaka H, Yukioka T, Yamaguti Y, Shimizu S, Goto H, Matsuda H, et al. Surgical stabilization of internal pneumatic stabilization? A prospective randomized study of management of severe flail chest patients. J Trauma 2002;52:727-732; discussion 732  https://doi.org/10.1097/00005373-200204000-00020
  11. Bemelman M, de Kruijf MW, van Baal M, Leenen L. Rib fractures: to fix or not to fix? An evidence-based algorithm. Korean J Thorac Cardiovasc Surg 2017;50:229-234  https://doi.org/10.5090/kjtcs.2017.50.4.229
  12. de Jong MB, Kokke MC, Hietbrink F, Leenen LPH. Surgical management of rib fractures: strategies and literature review. Scand J Surg 2014;103:120-125  https://doi.org/10.1177/1457496914531928
  13. Murphy CE , Raja AS, Baumann BM, Medak AJ, Langdorf MI, Nishijima DK, et al. Rib fracture diagnosis in the Panscan era. Ann Emerg Med 2017;70:904-909  https://doi.org/10.1016/j.annemergmed.2017.04.011
  14. Ringl H, Lazar M, Topker M, Woitek R, Prosch H, Asenbaum U, et al. The ribs unfolded-a CT visualization algorithm for fast detection of rib fractures: effect on sensitivity and specificity in trauma patients. Eur Radiol 2015;25:1865-1874  https://doi.org/10.1007/s00330-015-3598-2
  15. Lee JG, Jun S, Cho YW, Lee H, Kim GB, Seo JB, et al. Deep learning in medical imaging: general overview. Korean J Radiol 2017;18:570-584  https://doi.org/10.3348/kjr.2017.18.4.570
  16. Mannil M, von Spiczak J, Manka R, Alkadhi H. Texture analysis and machine learning for detecting myocardial infarction in noncontrast low-dose computed tomography: unveiling the invisible. Invest Radiol 2018;53:338-343  https://doi.org/10.1097/RLI.0000000000000448
  17. Prevedello LM, Erdal BS, Ryu JL, Little KJ, Demirer M, Qian S, et al. Automated critical test findings identification and online notification system using artificial intelligence in imaging. Radiology 2017;285:923-931  https://doi.org/10.1148/radiol.2017162664
  18. Winkel DJ, Heye T, Weikert TJ, Boll DT, Stieltjes B. Evaluation of an AI-based detection software for acute findings in abdominal computed tomography scans: toward an automated work list prioritization of routine CT examinations. Invest Radiol 2019;54:55-59  https://doi.org/10.1097/RLI.0000000000000509
  19. Alkadi R, Taher F, El-baz A, Werghi N. A deep learning-based approach for the detection and localization of prostate cancer in T2 magnetic resonance images. J Digital Imaging 2019;32:793-807  https://doi.org/10.1007/s10278-018-0160-1
  20. Kooi T, Litjens G, van Ginneken B, Gubern-Merida A, Sanchez CI, Mann R, et al. Large scale deep learning for computer aided detection of mammographic lesions. Med Image Anal 2017;35:303-312  https://doi.org/10.1016/j.media.2016.07.007
  21. Cicero M, Bilbily A, Colak E, Dowdell T, Gray B, Perampaladas K, et al. Training and validating a deep convolutional neural network for computer-aided detection and classification of abnormalities on frontal chest radiographs. Invest Radiol 2017;52:281-287  https://doi.org/10.1097/RLI.0000000000000341
  22. Yahalomi E, Chernofsky M, Werman M. Detection of distal radius fractures trained by a small set of X-ray images and faster R-CNN. In: Arai K, Bhatia R, Kapoor S, eds. Intelligent computing. Cham: Springer, 2019:971-981 
  23. Thian YL, Li Y, Jagmohan P, Sia D, Chan VEY, Tan RT. Convolutional neural networks for automated fracture detection and localization on wrist radiographs. Radiol Artif Intell 2019;1:e180001 
  24. Kim DH, MacKinnon T. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clin Radiol 2018;73:439-445  https://doi.org/10.1016/j.crad.2017.11.015
  25. Starosolski ZA, Kan H, Annapragada AV. CNN-based radiographic acute tibial fracture detection in the setting of open growth plates. bioRxiv, 2019. Available at: https://doi.org/10.1101/506154. Accessed August 25, 2019 
  26. Kitamura G, Chung CY, Moore BE. Ankle fracture detection utilizing a convolutional neural network ensemble implemented with a small sample, de novo training, and multiview incorporation. J Digit Imaging 2019;32:672-677  https://doi.org/10.1007/s10278-018-0167-7
  27. Lindsey R, Daluiski A, Chopra S, Lachapelle A, Mozer M, Sicular S, et al. Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci U S A 2018;115:11591-11596  https://doi.org/10.1073/pnas.1806905115
  28. Burns JE, Yao J, Munoz H, Summers RM. Automated detection, localization, and classification of traumatic vertebral body fractures in the thoracic and lumbar spine at CT. Radiology 2016;278:64-73  https://doi.org/10.1148/radiol.2015142346
  29. Bar A, Wolf L, Amitai OB, Toledano E, Elnekave E. Compression fractures detection on CT. Medical Imaging 2017: Computer-Aided Diagnosis 2017;10134:1013440 
  30. Chilamkurthy S, Ghosh R, Tanamala S, Biviji M, Campeau NG, Venugopal VK, et al. Development and validation of deep learning algorithms for detection of critical findings in head CT scans [updated April 2018]. Cornell University, 2018. Available at: https://arxiv.org/abs/1803.05854. Accessed August 25, 2019 
  31. Yan L, Chuan X, Xia C, Wang S, Chen K. Deep learning for automatic detection of fractures on chest CT scans after blunt trauma (number: B-0566). ECR 2019 (European Congress of Radiology);2019 February 27-March 3;Vienna, Austria 
  32. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Cornell University, 2015. Available at: https://arxiv.org/abs/1512.03385. Accessed August 25, 2019 
  33. Sergeev A, Del Balso M. Horovod: fast and easy distributed deep learning in TensorFlow [updated February 2018]. Cornell University, 2018. Available at: https://arxiv.org/abs/1802.05799. Accessed August 25, 2019 
  34. Talbot BS, Gange CP, Chaturvedi A, Klionsky N, Hobbs SK, Chaturvedi A. Traumatic rib injury: patterns, imaging pitfalls, complications, and treatment. Radiographics 2017;37:628-651  https://doi.org/10.1148/rg.2017160100
  35. Park HA. An introduction to logistic regression: from basic concepts to interpretation with particular attention to nursing domain. J Korean Acad Nurs 2013;43:154-164  https://doi.org/10.4040/jkan.2013.43.2.154
  36. Battle CE, Hutchings H, Evans PA. Risk factors that predict mortality in patients with blunt chest wall trauma: a systematic review and meta-analysis. Injury 2012;43:8-17 https://doi.org/10.1016/j.injury.2011.01.004