Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning

• Published in: European radiology Vol. 29; no. 5; pp. 2207 - 2217
• Main Authors: Muehlematter, Urs J., Mannil, Manoj, Becker, Anton S., Vokinger, Kerstin N., Finkenstaedt, Tim, Osterhoff, Georg, Fischer, Michael A., Guggenberger, Roman
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.05.2019; Springer Nature B.V
• Subjects: Aged; Aged, 80 and over; Artificial intelligence; Bone Density; Case-Control Studies; Classification; Computed Tomography; Confidence intervals; Diagnostic Radiology; Diagnostic systems; Feature extraction; Female; Fractures; Fractures, Stress - diagnosis; Humans; Image detection; Imaging; Internal Medicine; Interventional Radiology; Learning algorithms; Lumbar Vertebrae - diagnostic imaging; Lumbar Vertebrae - injuries; Machine Learning; Male; Medical imaging; Medicine; Medicine & Public Health; Middle Aged; Neuroradiology; Osteoporosis; Patients; Radiology; Retrospective Studies; Risk analysis; ROC Curve; Source code; Spinal Fractures - diagnosis; Spine; Texture; Thoracic Vertebrae - diagnostic imaging; Thoracic Vertebrae - injuries; Tomography, X-Ray Computed - methods; Ultrasound; Vertebrae; Osteoporosis; Tomography, X-ray computed; Spine; Machine learning
• DOI: 10.1007/s00330-018-5846-8
• ISSN: 0938-7994; 1432-1084

Purpose To evaluate the diagnostic performance of bone texture analysis (TA) combined with machine learning (ML) algorithms in standard CT scans to identify patients with vertebrae at risk for insufficiency fractures. Materials and methods Standard CT scans of 58 patients with insufficiency fractures of the spine, performed between 2006 and 2013, were analyzed retrospectively. Every included patient had at least two CT scans. Intact vertebrae in a first scan that either fractured (“unstable”) or remained intact (“stable”) in the consecutive scan were manually segmented on mid-sagittal reformations. TA features for all vertebrae were extracted using open-source software (MaZda). In a paired control study, all vertebrae of the study cohort “cases” and matched controls were classified using ROC analysis of Hounsfield unit (HU) measurements and supervised ML techniques. In a within-subject vertebra comparison, vertebrae of the cases were classified into “unstable” and “stable” using identical techniques. Results One hundred twenty vertebrae were included. Classification of cases/controls using ROC analysis of HU measurements showed an AUC of 0.83 (95% confidence interval [CI], 0.77–0.88), and ML-based classification showed an AUC of 0.97 (CI, 0.97–0.98). Classification of unstable/stable vertebrae using ROC analysis showed an AUC of 0.52 (CI, 0.42–0.63), and ML-based classification showed an AUC of 0.64 (CI, 0.61–0.67). Conclusion TA combined with ML allows to identifying patients who will suffer from vertebral insufficiency fractures in standard CT scans with high accuracy. However, identification of single vertebra at risk remains challenging. Key Points • Bone texture analysis combined with machine learning allows to identify patients at risk for vertebral body insufficiency fractures on standard CT scans with high accuracy. • Compared to mere Hounsfield unit measurements on CT scans, application of bone texture analysis combined with machine learning improve fracture risk prediction. • This analysis has the potential to identify vertebrae at risk for insufficiency fracture and may thus increase diagnostic value of standard CT scans.