Update README.md

README.md

@@ -33,10 +33,10 @@ It takes 256×256 px patches as input and outputs per-cell contours, centroids,
 The full pipeline consists of three steps:
 
 ```
-┌──────────────┐     ┌──────────────┐     ┌──────────────────┐
-│ 1. Normalize │ ──→ │ 2. Patchify  │ ──→ │ 3. Inference     │
-│  (Reinhard)  │     │ (256px, 64ov)│     │ (Cell Detection) │
-└──────────────┘     └──────────────┘     └──────────────────┘
+┌───────────────┐      ┌────────────────┐     ┌──────────────────┐
+│ 1. Normalize │ ──→  │ 2. Patchify  │ ──→  │ 3. Inference   │
+│  (Reinhard)  │      │(256px, 64ov) │     │(Cell Detection) │
+└───────────────┘      └────────────────┘     └──────────────────┘
     SVS / TIF            PNG patches        Masks + Centroids
 ```
 
@@ -166,7 +166,7 @@ If you use HNE2Cell in your research, please cite:
 
 ```bibtex
 @misc{hne2cell,
-  title={HNE2Cell: Cell Detection and Classification from H&E Whole-Slide Images},
+  title={Spatial transcriptomics–supervised deep learning enables single-cell mapping of tumor immune architecture from routine histology},
   year={2025},
   url={https://huggingface.co/roobee79/HNE2Cell}
 }