Background: Cleft lip repair presents complex surgical challenges requiring precise preoperative planning. Emerging computer vision technologies powered by artificial intelligence (AI) may support more consistent and accurate surgical assessments. This systematic review defines the scope, methods, and performance of computer vision for preoperative soft-tissue landmarking in cleft lip repair. Methods: Articles were retrieved from Medline and Embase. Inclusion criteria encompassed studies using computer vision techniques for automated soft-tissue analysis before cleft. The selected studies were appraised based on their scope, design, and performance. Results: Six studies were eligible for inclusion. The included studies used convolutional neural networks (CNNs), generative adversarial networks (GANs), and 3D shape analysis to guide surgical marking, cleft severity scoring, and symmetry assessment. Most models demonstrated high accuracy and efficiency compared with manual methods, showing promise for computer vision as a virtual conduit of surgical expertise. Conclusion: Computer vision offers strong potential to standardise and improve preoperative cleft lip planning. Future integration into surgical workflows must prioritise ethical design, validation, transparency, and equity of access.
Munns et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: