Performance evaluation of an AI-based application for opportunistic screening of thoraco-lumbar vertebral compression fractures

Congress:

ECR 2024

Poster Number:

C-11881

Type:

Scientific Exhibit

Keywords:

Artificial Intelligence, Bones, Musculoskeletal spine, CT, Computer Applications-Detection, diagnosis, Osteoporosis

Authors:

M. Quemeneur, P. Champsaur, A. Ayobi, C. Charlotte, S. Quenet, J. Kiewsky, M. Mahfoud, C. Avare, D. Guenoun

DOI:

10.26044/ecr2024/C-11881

DOI-Link:

https://dx.doi.org/10.26044/ecr2024/C-11881

References

[1] D. Alsoof, G. Anderson, C.L. McDonald, B. Basques, E. Kuris, A.H. Daniels, Diagnosis and Management of Vertebral Compression Fracture, Am. J. Med. 135 (2022) 815–821. https://doi.org/10.1016/j.amjmed.2022.02.035.

[2] H.-B. Sun, X.-S. Jing, G.-Q. Zhang, Y. Hai, Y.-Z. Liu, D.-C. Wang, Preliminary Study of Obese Patients with Chronic Obstructive Pulmonary Disease Suffering from Painful Osteoporotic Vertebral Compression Fracture Treated by Percutaneous Vertebroplasty in Improved Prone Position and Right Lateral Position, World Neurosurg. 130 (2019) e933–e940. https://doi.org/10.1016/j.wneu.2019.07.040.

[3] H.K. Genant, C.Y. Wu, C. van Kuijk, M.C. Nevitt, Vertebral fracture assessment using a semiquantitative technique, J. Bone Miner. Res. 8 (2009) 1137–1148. https://doi.org/10.1002/jbmr.5650080915.

[4] S.S. Yeap, S.C. Thambiah, S. Suppiah, S. Md-Said, G. Appannah, I.N. Samsudin, N. Zainuddin, S.Y. Zahari-Sham, F.L. Hew, Asymptomatic morphometric vertebral fractures and its associated factors: A cross-sectional study among adults in a selected urban area in Selangor, Malaysia, PLOS ONE 16 (2021) e0255069. https://doi.org/10.1371/journal.pone.0255069.

[5] A. Ameis, K. Randhawa, H. Yu, P. Côté, S. Haldeman, R. Chou, E.L. Hurwitz, M. Nordin, J.J. Wong, H.M. Shearer, A. Taylor-Vaisey, The Global Spine Care Initiative: a review of reviews and recommendations for the non-invasive management of acute osteoporotic vertebral compression fracture pain in low- and middle-income communities, Eur. Spine J. 27 (2018) 861–869. https://doi.org/10.1007/s00586-017-5273-6.

[6] M.T. Löffler, A. Jacob, A. Scharr, N. Sollmann, E. Burian, M. El Husseini, A. Sekuboyina, G. Tetteh, C. Zimmer, J. Gempt, T. Baum, J.S. Kirschke, Automatic opportunistic osteoporosis screening in routine CT: improved prediction of patients with prevalent vertebral fractures compared to DXA, Eur. Radiol. 31 (2021) 6069–6077. https://doi.org/10.1007/s00330-020-07655-2.

[7] P. Geusens, D.L. Kendler, A. Fahrleitner-Pammer, P. López-Romero, F. Marin, Distribution of Prevalent and Incident Vertebral Fractures and Their Association with Bone Mineral Density in Postmenopausal Women in the Teriparatide Versus Risedronate VERO Clinical Trial, Calcif. Tissue Int. 106 (2020) 646–654. https://doi.org/10.1007/s00223-020-00683-6.

[8] A. Valentinitsch, S. Trebeschi, J. Kaesmacher, C. Lorenz, M.T. Löffler, C. Zimmer, T. Baum, J.S. Kirschke, Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures, Osteoporos. Int. 30 (2019) 1275–1285. https://doi.org/10.1007/s00198-019-04910-1.

[9] D. Chettrit, T. Meir, H. Lebel, M. Orlovsky, R. Gordon, A. Akselrod-Ballin, A. Bar, 3D Convolutional Sequence to Sequence Model for Vertebral Compression Fractures Identification in CT, (2020). http://arxiv.org/abs/2010.03739 (accessed January 23, 2024).

[10] N. Tomita, Y.Y. Cheung, S. Hassanpour, Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans, Comput. Biol. Med. 98 (2018) 8–15. https://doi.org/10.1016/j.compbiomed.2018.05.011.

[11] M.T. Löffler, A. Jacob, A. Valentinitsch, A. Rienmüller, C. Zimmer, Y.-M. Ryang, T. Baum, J.S. Kirschke, Improved prediction of incident vertebral fractures using opportunistic QCT compared to DXA, Eur. Radiol. 29 (2019) 4980–4989. https://doi.org/10.1007/s00330-019-06018-w.

Fig 1: Example of a true positive (a) with a VCF at L1 (red arrow); a false...

Fig 2: Example of the algorithm’s vertebral labeling. The software names each...