Artificial Intelligence in the Comparative Interpretation of Ultrasound and MRI DICOM Data for Endometriosis: A Commentary on Current Evidence, Interoperability Barriers and Research Priorities

Transvaginal ultrasound (TVUS) and pelvic magnetic resonance imaging (MRI) are both used, often in the same patient, to evaluate suspected endometriosis, and comparative diagnostic-accuracy studies indicate that the two modalities capture partly complementary information rather than one simply outperforming the other across all disease sites. Artificial intelligence (AI) has been applied with increasing frequency to endometriosis imaging, but a recent scoping review found that the evidence base remains concentrated in single-modality, single-centre, retrospective studies with internal validation only, and that models jointly using ultrasound and MRI DICOM data from the same patient are essentially absent from the published literature. This commentary summarizes what is empirically established about ultrasound-MRI comparison in endometriosis, what AI has and has not yet demonstrated, and the DICOM-level interoperability barriers that stand ahead of any same-patient multimodal AI system. Statements that extend beyond what cited sources report are explicitly flagged.