Journal of the Korean Society of Radiology (대한영상의학회지)

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

Diagnosis of Rib Fracture Using Artificial Intelligence on Chest CT Images of Patients with Chest Trauma

외상 환자의 흉부 CT에서 인공지능을 이용한 갈비뼈 골절 진단

  • Li Kaike (Department of Radiology, Shandong Provincial Qianfoshan Hospital) ;
  • Riel Castro-Zunti (Department of Electrical and Computer Engineering, University of Saskatchewan) ;
  • Seok-Beom Ko (Department of Electrical and Computer Engineering, University of Saskatchewan) ;
  • Gong Yong Jin (Department of Radiology, Research Institute of Clinical Medicine, Biomedical Research Institute of Jeonbuk National University Hospital, Jeonbuk National University Medical School, Institute of Medical Science)
  • ;
  • ;
  • 고석범 (서스캐처원 대학교 전기컴퓨터공학과) ;
  • 진공용 (전북대학교 의과대학 전북대학교병원 임상의학연구소-의생명연구원 영상의학과)
  • Received : 2023.08.12
  • Accepted : 2023.12.25
  • Published : 2024.07.01
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose To determine the pros and cons of an artificial intelligence (AI) model developed to diagnose acute rib fractures in chest CT images of patients with chest trauma. Materials and Methods A total of 1209 chest CT images (acute rib fracture [n = 1159], normal [n = 50]) were selected among patients with chest trauma. Among 1159 acute rib fracture CT images, 9 were randomly selected for AI model training. 150 acute rib fracture CT images and 50 normal ones were tested, and the remaining 1000 acute rib fracture CT images was internally verified. We investigated the diagnostic accuracy and errors of AI model for the presence and location of acute rib fractures. Results Sensitivity, specificity, positive and negative predictive values, and accuracy for diagnosing acute rib fractures in chest CT images were 93.3%, 94%, 97.9%, 82.5%, and 95.6% respectively. However, the accuracy of the location of acute rib fractures was low at 76% (760/1000). The cause of error in the diagnosis of acute rib fracture seemed to be a result of considering the scapula or clavicle that were in the same position (66%) or some ribs that were not recognized (34%). Conclusion The AI model for diagnosing acute rib fractures showed high accuracy in detecting the presence of acute rib fractures, but diagnosis of the exact location of rib fractures was limited.

목적 외상 환자 흉부 CT에서 급성 갈비뼈 골절을 진단하기 위해 개발된 인공지능의 장단점에 대해서 알아보고자 하였다. 대상과 방법 외상으로 응급실에 내원했던 환자들 중 급성 갈비뼈 골절(n = 1159) 또는 정상(n = 50)으로 진단된 1209명의 흉부 CT를 무작위로 선택하였다. 이 중 9명의 급성 갈비뼈 골절 흉부 CT로 인공지능 모델 개발과 훈련을 했으며, 150명의 갈비뼈 골절 흉부 CT와 50명의 정상 흉부 CT로 테스트를 하였고, 나머지 1000명의 급성 갈비뼈 골절 흉부 CT로 내부 검증을 하였다. 급성 갈비뼈 골절에 대한 인공지능 모델의 골절의 유무와 위치에 대한 진단적 정확성과 오류에 대해서 알아보았다. 결과 개발된 인공지능 모델을 테스트 결과 급성 갈비뼈 골절 유무에 대한 민감도, 특이도, 양성예측도, 음성예측도, 정확도는 각각 93.3%, 94%, 97.9%, 82.5%, 95.6%였다. 내부 검증을 했을 때 급성 갈비뼈 골절 유무에 대한 정확도는 96%로 상승되었다. 그러나 급성 갈비뼈 골절 위치의 정확도는 76% (760/1000)로 낮았으며, 그 원인으로는 같은 위치에 있는 견갑골이나 쇄골을 갈비뼈로 잘못 인식(66%) 하거나 일부 갈비뼈를 인식하지 못하는 경우(34%)가 많았다. 결론 급성 갈비뼈 골절 진단을 위한 인공지능 모델이 급성 갈비뼈 골절의 유무 진단에는 높은 정확도를 보였지만 갈비뼈 골절의 정확한 위치를 진단하는 데는 제한점이 있었다.

Keywords

Acknowledgement

This paper was supported by the Song Ho Young Research Fund of Jeonbuk National University Medical School in 2022.

References

  1. Baiu I, Spain D. Rib fractures. JAMA 2019;321:1836
  2. 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
  3. Peek J, Ochen Y, Saillant N, Groenwold RHH, Leenen LPH, Uribe-Leitz T, et al. Traumatic rib fractures: a marker of severe injury. A nationwide study using the National Trauma Data Bank. Trauma Surg Acute Care Open 2020;5:e000441
  4. Wu M, Chai Z, Qian G, Lin H, Wang Q, Wang L, et al. Development and evaluation of a deep learning algorithm for rib segmentation and fracture detection from multicenter chest CT images. Radiol Artif Intell 2021;3:e200248
  5. Fernholm R, Pukk Harenstam K, Wachtler C, Nilsson GH, Holzmann MJ, Carlsson AC. Diagnostic errors reported in primary healthcare and emergency departments: a retrospective and descriptive cohort study of 4830 reported cases of preventable harm in Sweden. Eur J Gen Pract 2019;25:128-135
  6. Jin L, Yang J, Kuang K, Ni B, Gao Y, Sun Y, et al. Deep-learning-assisted detection and segmentation of rib fractures from CT scans: development and validation of FracNet. EBioMedicine 2020;62:103106
  7. Oren O, Gersh BJ, Bhatt DL. Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints. Lancet Digit Health 2020;2:e486-e488
  8. Abd-Elnaim MK, El-Minshawy A, Osman MA, Ahmed MM. Plating versus wiring for fixation of traumatic rib and sternal fractures. J Egypt Soc Cardio-Thorac Surg 2017;25:356-361
  9. 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
  10. Stawicki SP, Grossman MD, Hoey BA, Miller DL, Reed JF 3rd. Rib fractures in the elderly: a marker of injury severity. J Am Geriatr Soc 2004;52:805-808
  11. Dankerl P, Seuss H, Ellmann S, Cavallaro A, Uder M, Hammon M. Evaluation of rib fractures on a single-in-plane image reformation of the rib cage in CT examinations. Acad Radiol 2017;24:153-159
  12. Pesapane F, Codari M, Sardanelli F. Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine. Eur Radiol Exp 2018;2:35
  13. 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
  14. Weikert T, Noordtzij LA, Bremerich J, Stieltjes B, Parmar V, Cyriac J, et al. Assessment of a deep learning algorithm for the detection of rib fractures on whole-body trauma computed tomography. Korean J Radiol 2020;21:891-899
  15. Yao L, Guan X, Song X, Tan Y, Wang C, Jin C, et al. Rib fracture detection system based on deep learning. Sci Rep 2021;11:23513
  16. Zhou QQ, Wang J, Tang W, Hu ZC, Xia ZY, Li XS, et al. Automatic detection and classification of rib fractures on thoracic CT using convolutional neural network: accuracy and feasibility. Korean J Radiol 2020;21:869-879
  17. Talbot BS, Gange CP Jr, Chaturvedi A, Klionsky N, Hobbs SK, Chaturvedi A. Traumatic rib injury: patterns, imaging pitfalls, complications, and treatment. Radiographics 2017;37:628-651
  18. Olczak J, Fahlberg N, Maki A, Razavian AS, Jilert A, Stark A, et al. Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop 2017;88:581-586
  19. Castro-Zunti R, Chae KJ, Choi Y, Jin GY, Ko SB. Assessing the speed-accuracy trade-offs of popular convolutional neural networks for single-crop rib fracture classification. Comput Med Imaging Graph 2021;91:101937
  20. Yang C, Wang J, Xu J, Huang C, Liu F, Sun W, et al. Development and assessment of deep learning system for the location and classification of rib fractures via computed tomography. Eur J Radiol 2022;154:110434