Use of Deep Learning Models in the Diagnosis of Proptosis Through Orbital Magnetic Resonance Imaging

18 April 2026 : Clinical Research

Uğur Kesimal^{ABCDEF 1*}, Habip Eser Akkaya^{ABCDEF 2}, Önder Polat^{ABCDEF 1}, Murat Sağlam^{ABCDEF 1}

DOI: 10.12659/MSM.951157

Med Sci Monit 2026; 32:e951157

Authors information Article notes Copyright and License information

Introduction Material and Methods Results Discussion Conclusions References

Related articles Order reprints Share article Share by email

View HTML version

Table 1 Mean diagnostic performance metrics with standard deviations across 5-fold cross-validation.

	DenseNet121	DenseNet169	DenseNet264	ResNet50
Accuracy (%)	95.01±1.27	93.10±2.29	91.96±3.59	89.26±4.80
AUC (%)	98.64±0.43	98.28±0.87	98.00±1.66	96.16±2.28
Sensitivity (%)	92.70±2.59	90.83±2.87	93.14±3.69	88.13±8.99
Specificity (%)	96.92±1.05	95.38±2.92	90.77±4.38	90.39±7.32
All values indicate percentage. AUC – area under the receiver operating characteristic curve.

Back to the Article