Dizin Artroskopik Anatomisi ve Portaller Soner KOÇAK Abdülkadir YALÇINKAYA Menisküs Yırtıklarına Yaklaşım Nihat Demirhan DEMİRKIRAN Ramadan ÖZMANEVRA Süleyman Kaan ÖNER Menisküs Transplantasyonu ve Skafoldlar Erdem ATEŞ Artroskopik Kıkırdak Tedavileri- Mozaikplasti Kemal ŞİBAR Primer Ön Çapraz Bağ Rekonstrüksiyonu Günbay Noyan DİRLİK Arka Çapraz Bağ Rekonstrüksiyonu Fatih GÜNAYDIN Medial Kollateral Ligament ve Posteromedial Köşe Yaralanmalar Volkan ÖZEL Diz Artroskopisi Komplikasyonları Mehmet Yiğit GÖKMEN Revizyon Ön Çapraz Bağ Rekonstrüksiyonu Mustafa Çağlar KIR Pediatrik Ön Çapraz Bağ Rekonstrüksiyonu Öner KILINÇ Sert Dizde Artroskopik Gevşetme İdris DEMİRTAŞ
Background/Objectives: Artificial intelligence (AI) may support rotator cuff MRI interpretation; however, its performance relative to clinicians at different experience levels remains uncertain. We compared a locked YOLO11m-based model with prespecified orthopaedic physician panels using arthroscopy as the reference standard. Methods: This retrospective single-centre study included a separate 300-patient model-development dataset and an arthroscopy-referenced reader cohort of 258 patients (60 intact cuffs, 86 partial-thickness tears, and 112 full-thickness tears). Twelve blinded physicians were assigned to four three-reader experience panels, and panel diagnoses were defined by a two-of-three majority. Paired accuracy comparisons used exact McNemar tests with Holm adjustment. Results: AI achieved 0.841 overall accuracy (95% CI, 0.792–0.881). The senior-specialist panel had numerically higher accuracy (0.911), but the difference from AI was not statistically significant after adjustment (Holm p = 0.060); the junior-specialist panel also did not differ from AI (0.822; Holm p = 0.649). AI showed higher paired accuracy than the senior-resident (0.729; Holm p = 0.005) and junior-resident panels (0.671; Holm p < 0.001). Partial-thickness tears had the lowest AI sensitivity (0.709). Conclusions: In this restricted-cine, three-category benchmark, AI outperformed both resident panels, whereas neither specialist panel comparison reached the adjusted significance threshold. These findings do not establish equivalence to specialists or benefit from AI-assisted reading.