diff --git a/README.md b/README.md
index 9ca11f0c57e57778d74709771d13091255fde74e..a496cfeba0b255daf36036f0418e6664c15df572 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-# Nf-as-a-metric-for-quantifying-and-improving-super-resolution-microscopy-image-reconstruction
+# the-naturalness-factor-in-generative-deep-learning-models-of-super-resolution-microscopy
 We trained a Conditional **Variational Diffusion Model (CVDM)** (G. Della Maggiora, 2023) using the **BioSR dataset** (Qiao & Li, 2020) (DOI: 10.6084/m9.figshare.13264793.v9). To evaluate if the model can generate natural images similar to the ground truth, we assessed the **Naturalness Factor**(Gong, Y., & Sbalzarini, I. F. 2014) at two stages: prior learning (before training) and post-processing (after applying the model's output enhancements). 
 
 The implementation of CVDM can be found on the GitHub page (G. Della Maggiora, L. A. Croquevielle, N. Deshpande, H. Horsley, T. Heinis, A. Yaki-movich, Conditional variational diffusion models, https://github.com/casus/cvdm)2023.