Accuracy of Cranial Shape Measurements Using Smartphones: A Prospective Study.

Abstract

Prospectively validate the accuracy of smartphone-based digital cranial measurements for the diagnosis and treatment of deformational plagiocephaly and/or brachycephaly (DPB), compared with calipers used in the standard of care. Bird's-eye-view head photos were captured via smartphone, and their heads were measured with hand calipers by an expert user. CI/CVAI/CVA were calculated from photos and caliper measurements, and from 3D photogrammetry of the head as ground truth. Digital and caliper measurements were compared against 3D-based ground truth using mean absolute error, Spearman correlation coefficient, and Bland-Altman method. Statistical significance between methods was assessed using Wilcoxon Rank-Sum test. 71 infants aged 2-11 months (20 female, 51 male) with DPB. The mean absolute errors for CI, CVAI, CVA were 1.63 ± 1.44, 1.45 ± 1.29, 2.38 ± 1.86 mm for smartphone, and 2.60 ± 1.96, 1.43 ± 1.22, 2.04 ± 1.81 mm for calipers, respectively. The correlation coefficients for CI, CVAI, CVA between smartphone and ground truth were 0.90, 0.94, 0.80 (p < 0.001), and 0.87, 0.93, 0.84 (p < 0.001) between calipers and ground truth, respectively. Bland-Altman results were (0.08, [-4.18, 4.34]), (-0.05, [-3.85, 3.76]), (-0.82, [-6.52, 4.87]) for smartphone, and (1.41, [-4.34, 7.15]), (0.28, [-3.37, 3.94]), (0.16, [-5.18, 5.49]) for caliper measurements respectively. Digital and caliper measurements were similar (p = 0.12) except for CI, where digital measurements were more accurate (p = 0.04). Smartphone-based cranial measurements have very high correlation with 3D-based ground truth, and they are comparable or superior to caliper measurements. Digital measurements can be performed in pediatric offices or from home to help with the early detection and treatment of DPB.