Three-Dimensional Modelling and Artificial Intelligence in The Comprehensive Assessment of Medication-Related Osteonecrosis of The Jaw

Abstract

Objective. To assess the clinical significance of a digital algorithm for personalized diagnostic and surgical planning in patients with medication-related osteonecrosis of the jaw (MRONJ), based on cone-beam computed tomography (CBCT), 3D modelling, radiomic analysis, and artificial intelligence (AI).

Materials and methods. A recalculated summary dataset comprising 164 patients was prepared, with patients equally allocated to a digital-planning group and a comparison group (82 patients each). The digital-planning group underwent clinical assessment, CBCT, segmentation and 3D reconstruction in 3D Slicer, PyRadiomics analysis, and decision-support assessment. Follow-up examinations were performed at 1, 3, 6, and 12 months.

Results. Staging accuracy with the digital approach was 93,9%, compared with 81,7% under standard care. According to the source data, the diagnostic classification model had a sensitivity of 93,9%, specificity of 91,5%, accuracy of 92,7%, and an AUC of 0.958; the adverse-outcome prediction model had an accuracy of 92,9% and an AUC of 0.963. The estimated rates of complete lesion removal at the first operation were 77/82 versus 67/82; extension of the surgical procedure was required in 4/82 versus 14/82. Mean operative time was 58.4±11.2 versus 73.8±14.6 minutes, and blood loss was 74.3±28.5 versus 108.6±39.7 mL. The source data reported 12-month recurrence-free rates of 91.4% versus 78.9%.

Conclusion. Digital preoperative planning may improve assessment of MRONJ extent, increase concordance between the planned and actual procedure, and support risk stratification.

Keywords:

MRONJ, ation-related osteonecrosis of the jaw, CBCT

References

Ruggiero S. L., Dodson T. B., Aghaloo T. et al. American Association of Oral and Maxillofacial Surgeons’ Position Paper on Medication-Related Osteonecrosis of the Jaws — 2022 Update // Journal of Oral and Maxillofacial Surgery. 2022. Vol. 80, No. 5. P. 920–943.

Yarom N., Shapiro C. L., Peterson D. E. et al. Medication-Related Osteonecrosis of the Jaw: MASCC/ISOO/ASCO Clinical Practice Guideline // Journal of Clinical Oncology. 2019. Vol. 37, No. 25. P. 2270–2290.

Nicolatou-Galitis O., Schiødt M., Mendes R. A. et al. Medication-related osteonecrosis of the jaw: definition and best practice for prevention, diagnosis, and treatment // Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology. 2019. Vol. 127, No. 2. P. 117–135.

Khan A. A., Morrison A., Hanley D. A. et al. Diagnosis and management of osteonecrosis of the jaw: a systematic review and international consensus // Journal of Bone and Mineral Research. 2015. Vol. 30, No. 1. P. 3–23.

Campisi G., Mauceri R., Bertoldo F. et al. Medication-related osteonecrosis of jaws: Italian Consensus Update 2020 // International Journal of Environmental Research and Public Health. 2020. Vol. 17. Article 5998.

Fedorov A., Beichel R., Kalpathy-Cramer J. et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network // Magnetic Resonance Imaging. 2012. Vol. 30, No. 9. P. 1323–1341.

van Griethuysen J. J. M., Fedorov A., Parmar C. et al. Computational Radiomics System to Decode the Radiographic Phenotype // Cancer Research. 2017. Vol. 77, No. 21. P. e104–e107.

Zwanenburg A., Vallières M., Abdalah M. A. et al. The Image Biomarker Standardization Initiative: standardized quantitative radiomics for high-throughput image-based phenotyping // Radiology. 2020. Vol. 295, No. 2. P. 328–338.

Pedregosa F., Varoquaux G., Gramfort A. et al. Scikit-learn: Machine Learning in Python // Journal of Machine Learning Research. 2011. Vol. 12. P. 2825–2830.

Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016. P. 785–794.

Collins G. S., Reitsma J. B., Altman D. G., Moons K. G. M. Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD): the TRIPOD statement // Annals of Internal Medicine. 2015. Vol. 162, No. 1. P. 55–63.

Hosmer D. W., Lemeshow S., Sturdivant R. X. Applied Logistic Regression. 3rd ed. Hoboken: John Wiley & Sons; 2013.

Slade G. D. Derivation and validation of a short-form oral health impact profile // Community Dentistry and Oral Epidemiology. 1997. Vol. 25, No. 4. P. 284–290.