Abstract
Pelvic ring disruptions result from blunt injury mechanisms and are often found in patients with multi-system trauma. To grade pelvic fracture severity in trauma victims based on whole-body CT, the Tile AO/OTA classification is frequently used. Due to the high volume of whole-body trauma CTs generated in busy trauma centers, an automated approach to Tile classification would provide substantial value, e. g., to prioritize the reading queue of the attending trauma radiologist. In such scenario, an automated method should perform grading based on a transparent process and based on interpretable features to enable interaction with human readers and lower their workload by offering insights from a first automated read of the scan. This paper introduces an automated yet interpretable pelvic trauma decision support system to assist radiologists in fracture detection and Tile grade classification. The method operates similarly to human interpretation of CT scans and first detects distinct pelvic fractures on CT with high specificity using a Faster-RCNN model that are then interpreted using a structural causal model based on clinical best practices to infer an initial Tile grade. The Bayesian causal model and finally, the object detector are then queried for likely co-occurring fractures that may have been rejected initially due to the highly specific operating point of the detector, resulting in an updated list of detected fractures and corresponding final Tile grade. Our method is transparent in that it provides finding location and type using the object detector, as well as information on important counterfactuals that would invalidate the system’s recommendation and achieves an AUC of 83.3%/85.1% for translational/rotational instability. Despite being designed for human-machine teaming, our approach does not compromise on performance compared to previous black-box approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Welcome to CausalNex’s API docs and tutorials! – causalnex 0.9.1 documentation (Feb 2021). https://causalnex.readthedocs.io/en/latest. Accessed 26 Feb 2021
Abbas, W., et al.: Lower leg bone fracture detection and classification using faster R-CNN for x-rays images. In: 2020 IEEE 23rd International Multitopic Conference (INMIC), pp. 1–6. IEEE (2020)
Ahmad, M.A., Eckert, C., Teredesai, A.: Interpretable machine learning in healthcare. In: Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, pp. 559–560 (2018)
Blum, A., Gillet, R., Urbaneja, A., Teixeira, P.G.: Automatic detection of rib fractures: are we there yet? EBioMedicine 63 (2021). https://doi.org/10.1016/j.ebiom.2020.103158
Burns, J.E., Yao, J., Summers, R.M.: Artificial intelligence in musculoskeletal imaging: a paradigm shift. J. Bone Miner. Res. 35(1), 28–35 (2020). https://doi.org/10.1002/jbmr.3849
Castro, D.C., Walker, I., Glocker, B.: Causality matters in medical imaging. Nat. Commun. 11(3673), 1–10 (2020). https://doi.org/10.1038/s41467-020-17478-w
Chang, C.H., Creager, E., Goldenberg, A., Duvenaud, D.: Explaining image classifiers by counterfactual generation. arXiv preprint arXiv:1807.08024 (2018)
Cheng, C.T., et al.: A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs. Nat. Commun. 12(1066), 1–10 (2021). https://doi.org/10.1038/s41467-021-21311-3
Coccolini, F., et al.: Pelvic trauma: WSES classification and guidelines. World J. Emerg. Surg. 12, 5 (2017). https://doi.org/10.1186/s13017-017-0117-6
Dreizin, D.: Commentary on multidetector CT in vascular injuries resulting from pelvic fractures. Radiographics 39(7), 2130–2133 (2019)
Dreizin, D., et al.: CT prediction model for major arterial injury after blunt pelvic ring disruption. Radiology 287(3), 1061–1069 (2018). https://doi.org/10.1148/radiol.2018170997
Dreizin, D., et al.: An automated deep learning method for tile AO/OTA pelvic fracture severity grading from trauma whole-body CT. J. Digit. Imaging 34(1), 53–65 (2021)
Dreizin, D., Munera, F.: Blunt polytrauma: evaluation with 64-section whole-body CT angiography. Radiographics 32(3), 609–631 (2012). https://pubs.rsna.org/doi/full/10.1148/rg.323115099
Dreizin, D., et al.: Can MDCT unmask instability in binder-stabilized pelvic ring disruptions? Am. J. Roentgenol. 207(6), 1244–1251 (2016). https://doi.org/10.2214/AJR.16.16630
Fong, R., Patrick, M., Vedaldi, A.: Understanding deep networks via extremal perturbations and smooth masks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 2950–2958 (2019)
Kalmet, P.H., et al.: Deep learning in fracture detection: a narrative review.Acta Orthop. 91(2), 215–220 (2020)
Lenis, D., Major, D., Wimmer, M., Berg, A., Sluiter, G., Bühler, K.: Domain aware medical image classifier interpretation by counterfactual impact analysis. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 315–325. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59710-8_31
McHugh, M.L.: Interrater reliability: the kappa statistic. Biochem. Med. (Zagreb). 22(3), 276 (2012). https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3900052
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Elsevier, Amsterdam (2014)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv (June 2015). https://arxiv.org/abs/1506.01497v3
Sato, Y., et al.: A computer-aided diagnosis system using artificial intelligence for hip fractures-multi-institutional joint development research. arXiv e-prints pp. arXiv-2003 (2020)
Schölkopf, B., et al.: Towards Causal Representation Learning. arXiv (February 2021). https://arxiv.org/abs/2102.11107v1
Tile, M.: Pelvic ring fractures: should they be fixed? J. Bone Joint Surg. Br. 70(1), 1–12 (1988). https://doi.org/10.1302/0301-620X.70B1.3276697
Tile, M.: Acute pelvic fractures: I. causation and classification. J. Am. Acad. Orthop. Surg. 4(3), 143–151 (1996). https://doi.org/10.5435/00124635-199605000-00004, https://pubmed.ncbi.nlm.nih.gov/10795049/
Tonekaboni, S., Joshi, S., McCradden, M.D., Goldenberg, A.: What clinicians want: contextualizing explainable machine learning for clinical end use. In: Machine Learning for Healthcare Conference, pp. 359–380. PMLR (2019)
Vaidya, R., Scott, A.N., Tonnos, F., Hudson, I., Martin, A.J., Sethi, A.: Patients with pelvic fractures from blunt trauma. what is the cause of mortality and when? Am. J. Surg. 211(3), 495–500 (2016). https://doi.org/10.1016/j.amjsurg.2015.08.038
Vaidya, R., Scott, A.N., Tonnos, F., Hudson, I., Sethi, A.: Patients with Pelvic Fractures from blunt trauma. what is the cause of mortality and when? Am. J. Surg. 211(3), 495–500 (2015). https://doi.org/10.1016/j.amjsurg.2015.08.038
Yahalomi, E., Chernofsky, M., Werman, M.: Detection of distal radius fractures trained by a small set of X-ray images and Faster R-CNN. arXiv (December 2018). https://arxiv.org/abs/1812.09025v1
Zingg, T., et al.: Interobserver reliability of the tile classification system for pelvic fractures among radiologists and surgeons. Eur. Radiol. 31(3), 1517–1525 (2021)
Acknowledgements
S.F. was supported by the ICL-TUM Joint Academy for Doctoral (JADS) program. D.D. was funded by NIH K08 EB027141-01A1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zapaishchykova, A., Dreizin, D., Li, Z., Wu, J.Y., Faghihroohi, S., Unberath, M. (2021). An Interpretable Approach to Automated Severity Scoring in Pelvic Trauma. In: de Bruijne, M., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021. MICCAI 2021. Lecture Notes in Computer Science(), vol 12903. Springer, Cham. https://doi.org/10.1007/978-3-030-87199-4_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-87199-4_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87198-7
Online ISBN: 978-3-030-87199-4
eBook Packages: Computer ScienceComputer Science (R0)