Interobserver Variability of Hip Dysplasia Indices on Sweep Ultrasound for Novices, Experts, and Artificial Intelligence

Abstract

Background: Ultrasound for developmental dysplasia of the hip (DDH) is challenging for nonexperts to perform and interpret. Recording "sweep" images allows more complete hip assessment, suitable for automation by artificial intelligence (AI), but reliability has not been established. We assessed agreement between readers of varying experience and a commercial AI algorithm, in DDH detection from infant hip ultrasound sweeps. Methods: We selected a full spectrum of poor-to-excellent quality images and normal to severe dysplasia, in 240 hips (120 single 2-dimensional images, 120 sweeps). For 12 readers (radiologists, sonographers, clinicians and researchers; 3 were DDH subspecialists), and a ultrasound-FDA-cleared AI software package (Medo Hip), we calculated interobserver reliability for alpha angle measurements by intraclass correlation coefficient (ICC 2,1 ) and for DDH classification by Randolph Kappa. Results: Alpha angle reliability was high for AI versus subspecialists (ICC = 0.87 for sweeps, 0.90 for single images). For DDH diagnosis from sweeps, agreement was high between subspecialists (kappa = 0.72), and moderate for nonsubspecialists (0.54) and AI (0.47). Agreement was higher for single images (kappa = 0.80, 0.66, 0.49). AI reliability deteriorated more than human readers for the poorest-quality images. The agreement of radiologists and clinicians with the accepted standard, while still high, was significantly poorer for sweeps than 2D images (P < 0.05). Conclusions: In a challenging exercise representing the wide spectrum of image quality and reader experience seen in realworld hip ultrasound, agreement on DDH diagnosis from easily obtained sweeps was only slightly lower than from single images, likely because of the additional step of selecting the best image. AI performed similarly to a nonsubspecialist human reader but was more affected by low-quality images.

Artificial intelligence, machine learning and deep learning in musculoskeletal imaging: Current applications

“…Artificial intelligence has also been exploited to automatically detect pediatric wrist fractures by 3D ultrasound 27 . Children presenting to an emergency department with unilateral upper extremity injury to the wrist region were scanned either on the affected and unaffected limb, and radiographs of the symptomatic limb were used as reference.…”

“…Commercially developed AI algorithms can be used to detect developmental dysplasia of the hip in infants. Ghasseminia et al assessed agreement between readers with different level of experience after selecting a full spectrum of poor‐to‐excellent quality images in 240 hips with normal to severe dysplasia 27 . AI performed similarly to a non‐subspecialist human reader but was more affected by low‐quality images, since the reliability deteriorated more than human readers for the poorest‐quality images.…”

“…Also in this case, the AUC was 0.86 to distinguish between healthy and disease. On the other hand, the neural network that was developed to score the four Doppler classes achieved an average per class accuracy of 75.0%.Artificial intelligence has also been exploited to automatically detect pediatric wrist fractures by 3D ultrasound 27. Children presenting to an emergency department with unilateral upper extremity injury to the wrist region were scanned either on the affected and unaffected limb, and radiographs of the symptomatic limb were used as reference.…”

Study Film and Television Postproduction and Innovation Strategy Based on an Artificial Intelligence Algorithm

“…en, the auxiliary scheme uses the roulette strategy to judge the best scheme, gives corresponding weights, and makes greedy judgments around it to produce the 1/2 scheme. Finally, we give up the film and television works that do not meet the threshold scheme and judge the film and television works in other directions as shown by Ghasseminia et al [16].…”

Feasibility of hip dysplasia screening in primary care clinics via AI-augmented point-of-care ultrasound.

“…Developmental dysplasia of the hip (DDH) leads to premature hip arthritis [1,2]. Screening is desirable because DDH is relatively common (incidence 1-3% of infants), it can be detected using a noninvasive tool (ultrasound, US), and effective treatment exists (Pavlik abduction harness) [3,4].…”