Artificial Intelligence Automation of Proptosis Measurement: An Indicator for Pediatric Orbital Abscess Surgery

Abstract

Introduction: To evaluate the ability of artificial intelligence (AI) software to quantify proptosis for identifying patients who need surgical drainage.

Methods: We pursued a retrospective study including 56 subjects with a clinical diagnosis of subperiosteal orbital abscess (SPOA) secondary to sinusitis at a tertiary pediatric hospital from 2002 to 2016. AI computer software was developed to perform 3D visualization and quantitative assessment of proptosis from computed tomography (CT) images acquired at the time of hospital admission. The AI software automatically computed linear and volume metrics of proptosis to provide more practice-consistent and informative measures. Two experienced physicians independently measured proptosis using the interzygomatic line method on axial CT images. The AI software and physician proptosis assessments were evaluated for association with eventual treatment procedures as standalone markers and in combination with the standard predictors.

Results: To treat the SPOA, 31 of 56 (55%) children underwent surgical intervention, including 18 early surgeries (performed within 24 h of admission), and 25 (45%) were managed medically. The physician measurements of proptosis were strongly correlated (Spearman r = 0.89, 95% CI 0.82-0.93) with 95% limits of agreement of ± 1.8 mm. The AI linear measurement was on average 1.2 mm larger (p = 0.007) and only moderately correlated with the average physicians' measurements (r = 0.53, 95% CI 0.31-0.69). Increased proptosis of both AI volumetric and linear measurements were moderately predictive of surgery (AUCs of 0.79, 95% CI 0.68-0.91, and 0.78, 95% CI 0.65-0.90, respectively) with the average physician measurement being poorly to fairly predictive (AUC of 0.70, 95% CI 0.56-0.84). The AI proptosis measures were also significantly greater in the early as compared to the late surgery groups (p = 0.02, and p = 0.04, respectively). The surgical and medical groups showed a substantial difference in the abscess volume (p < 0.001).

Conclusion: AI proptosis measures significantly differed from physician assessments and showed a good overall ability to predict the eventual treatment. The volumetric AI proptosis measurement significantly improved the ability to predict the likelihood of surgery compared to abscess volume alone. Further studies are needed to better characterize and incorporate the AI proptosis measurements for assisting in clinical decision-making.

Keywords: Automation; Computed tomography (CT); Orbital cellulitis; Proptosis; Subperiosteal orbital abscess.

Fig. 1

Axial CT image of a representative subject with left-sided proptosis, periorbital edema, ethmoid sinusitis, and trace medial subperiosteal abscess. Physician measurement of relative proptosis by measuring the posterior globe perpendicular from the interzygomatic line

Fig. 2

Automated identification of orbital abscess (a), globe (b), and postseptal region (c) and their visualization (d, e)

Fig. 3

Proptosis assessment by artificial intelligence (AI) software. a Original CT image, b “d” is the farthest 3D distance from the globe’s anterior surface to the intersection plane between the globe and the postseptal region. c “D” is the diameter of the globe. The AI software linear proptosis measurement is defined as the difference between “d” of each eye. The AI volume measurement of proptosis is defined as the volume of the globe beyond the postseptal region, with the relative volume of proptosis calculated as the volume difference between each eye

Fig. 4

Bland–Altman plot of the difference between by the average of the proptosis measurements of two physicians (the 95% limits of agreement are ± 1.8 mm, based on the standard deviation of the difference of 0.9 mm)

Fig. 5

ROC curve for discriminating between the medical and surgical groups on the basis of the abscess volume, AI volumetric proptosis, and their linear combination (model)