Automated measurements of interscrew angles in vertebral body tethering patients with deep learning

BACKGROUND CONTEXT

Vertebral body tethering is the most popular nonfusion treatment for adolescent idiopathic scoliosis. The effect of the tether cord on the spine can be segmentally assessed by comparing the angle between two adjacent screws (interscrew angle) over time. Tether breakage has historically been assessed radiographically by a change in adjacent interscrew angle by greater than 5° between two sets of imaging. A threshold for growth modulation has not yet been established in the literature. These angle measurements are time consuming and prone to interobserver variability.

PURPOSE

The purpose of this study was to develop an automated deep learning algorithm for measuring the interscrew angle following VBT surgery.

STUDY DESIGN/SETTING

Single institution analysis of medical images.

PATIENT SAMPLE

We analyzed 229 standing or bending AP or PA radiographs from 100 patients who had undergone VBT at our institution.

OUTCOME MEASURES

Physiologic Measures: An image processing algorithm was used to measure interscrew angles.

METHODS

A total of 229 standing or bending AP or PA radiographs from 100 VBT patients with vertebral body tethers were identified. Vertebral body screws were segmented by hand for all images and interscrew angles measured manually for 60 of the included images. A U-Net deep learning model was developed to automatically segment the vertebral body screws. Screw label maps were used to develop and tune an image processing algorithm which measures interscrew angles. Finally, the completed model and algorithm pipeline was tested on a 30-image test set. Dice score and absolute error were used to measure performance.

RESULTS

Inter- and Intra-rater reliability for manual angle measurements were assessed with ICC and were both 0.99. The segmentation model Dice score against manually segmented ground truth across the 30-image test set was 0.96. The average interscrew angle absolute error between the algorithm and manually measured ground truth was 0.66° and ranged from 0° to 2.67° in non-overlapping screws (N=206). The primary modes of failure for the model were overlapping screws on a right thoracic/left lumbar construct with two screws in one vertebra and overexposed images. An algorithm step which determines whether an overlapping screw was present correctly identified all overlapping screws, with no false positives.

CONCLUSION

We developed and validated an algorithm which measures interscrew angles for radiographs of vertebral body tether patients with an accuracy of within 1° for the majority of interscrew angles. The algorithm can process five images per second on a standard computer, leading to substantial time savings. This algorithm may be used for rapid processing of large radiographic databases of tether patients and could enable more rigorous definitions of growth modulation and cord breakage to be established.

Is there a correlation between the change in the interscrew angle of the eight-plate and the delta joint orientation angles?

Objectives

It is known that the screws of the eight-plate hemiepiphysiodesis construct diverge as growth occurs through the physis. Our objective was to investigate whether there is a correlation between the amount of change of the joint orientation angle (JOA) and that of the interscrew angle (ISA) of the eight-plate hemiepiphysiodesis construct before and after correction.

Patients and methods

After the institutional review board approval, medical charts and X-rays of all patients operated for either genu valgum or genu varum with eight-plate hemiepiphysiodesis were analyzed retrospectively. All consecutive patients at various ages with miscellaneous diagnoses were included. JOA and ISA were measured before and after correction. After review of the X-rays, statistical analyses were performed which included Pearson correlation coefficient and regression analyses.

Results

There were 53 segments of 30 patients included in the study. Eighteen were males, and 12 were females. Mean age at surgery was 9.1 (range 3–17). Mean follow-up time was 21.5 (range, 7–46) months. The diagnoses were diverse. A strong correlation was found between the delta JOA (d-JOA) and delta ISA (d-ISA) of the eight-plate hemiepiphysiodesis construct (r = 0.759 (0.615–0.854, 95%CI), p < 0.001). This correlation was independent of the age and gender of the patient.

Conclusions

There is a strong correlation between the d-ISA and the d-JOA. The d-ISA follows the d-JOA at a predictable amount through formulas which regression analysis yielded. This study confirms the clinical observation of the diverging angle between the screws is in correlation with the correction of the JOA.

Level of evidence

Level IV, Therapeutic study.