Artificial intelligence to automatically measure glenoid inclination, humeral alignment, and the lateralization and distalization shoulder angles on postoperative radiographs after reverse shoulder arthroplasty

Simple item page
dc.catalogadoryvc
dc.contributor.authorLinjun, Yang
dc.contributor.authorDe Marinis Acle, Rodrigo Ignacio
dc.contributor.authorYu, Kristin
dc.contributor.authorMarigi, Erick
dc.contributor.authorOeding, Jacob F.
dc.contributor.authorSperling, John W.
dc.contributor.authorSánchez-Sotelo, Joaquín
dc.date.accessioned2024-07-18T20:39:55Z
dc.date.available2024-07-18T20:39:55Z
dc.date.issued2024
dc.description.abstractBackground: Radiographic evaluation of the implant configuration after reverse shoulderarthroplasty (RSA) is time-consuming and subject to interobserver disagreement. The finalconfiguration is a combination of implant features and surgical execution. Artificial intel ligence (AI) algorithms have been shown to perform accurate and efficient analysis ofimages. The purpose of this study was to develop an AI algorithm to automatically measureglenosphere inclination, humeral component inclination, and the lateralization and dis talization shoulder angles (DSAs) on postoperative anteroposterior radiographs after RSA.Methods: The Digital Imaging and Communications in Medicine files corresponding topostoperative anteroposterior radiographs obtained after implantation of 143 RSAs wereretrieved and used in this study. Four angles were analyzed: (1) glenoid inclination angle(GIA, between the central fixation feature of the glenoid and the floor of the supraspinatusfossa), (2) humeral alignment angle (HAA, between the long axis of the humeral shaft and aperpendicular to the metallic bearing of the prosthesis), (3) DSA, and (4) lateralizationshoulder angle (LSA). A UNet segmentation model was trained to segment bony and implant elements using manually segmented training (n ¼ 89) and validation (n ¼ 22) images. Then, an image-processingebased pipeline was developed to measure all 4 angles using AI-segmented images. Measures performed by 3 physician observers and the AI algorithm were then completed in 32 additional images. The agreements among human observers and between observers and the AI algorithm were evaluated using intraclass correlation coefficients (ICCs) and absolute differences in degree. Results: The ICCs (95% confidence interval) for manual measurements of LSA, DSA, GIA, and HAA were 0.79 (0.55, 0.90), 0.90 (0.80, 0.95), 0.96 (0.93, 0.98), and 0.99 (0.97, 0.99), respectively. The AI algorithm measured the 32 images in the test set in less than 2 minutes. The agreement between observers and the AI algorithm was lowest when measuring the LSA for observer 2, with an ICC of 0.77 (0.52, 0.89), and an absolute difference in degrees (median [interquartile range]) of 5 (4). Better agreements were found between the AI measurements and the average manual measurements: absolute differences in degree for LSA, DSA, GIA, and HAA were 3 (5), 2 (3), 2 (2), and 2 (1), respectively; ICCs for LSA, DSA, GIA, and HAA were 0.89 (0.79, 0.95), 0.96 (0.93, 0.98), 0.85 (0.68, 0.93), and 0.98 (0.95, 0.99), respectively. Conclusion: The AI algorithm developed in this study can automatically measure the GIA, HAA, LSA, and DSA on postoperative anteroposterior radiographs obtained after implantation on RSA.
dc.fechaingreso.objetodigital2024-07-18
dc.format.extent10 páginas
dc.fuente.origenORCID
dc.identifier.doi10.1053/j.sart.2024.05.002
dc.identifier.urihttps://doi.org/10.1053/j.sart.2024.05.002
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/87134
dc.information.autorucEscuela de Medicina; De Marinis Acle, Rodrigo Ignacio; 0000-0003-1888-8928; 237996
dc.language.isoen
dc.nota.accesocontenido parcial
dc.publisherElsevier Inc.
dc.rightsacceso restringido
dc.subjectReverse shoulder arthroplasty
dc.subjectArtificial intelligence
dc.subjectGlenoid inclination
dc.subjectNeck-shaft angle
dc.subjectOverall lateralization
dc.subjectDistalization
dc.subject.ddc610
dc.subject.deweyMedicina y saludes_ES
dc.subject.ods03 Good health and well-being
dc.subject.odspa03 Salud y bienestar
dc.titleArtificial intelligence to automatically measure glenoid inclination, humeral alignment, and the lateralization and distalization shoulder angles on postoperative radiographs after reverse shoulder arthroplasty
dc.typeartículo
sipa.codpersvinculados237996
sipa.trazabilidadORCID;2024-07-15
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Artificial intelligence to automatically measure.pdf
Size:
121.62 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas