Update app.py

app.py

@@ -16,7 +16,48 @@ def calculate_tia(t1, a1, t2, a2):
     return result
 
 with gr.Blocks() as demo:
-    gr.Markdown("# Lu-177 Dosimetry Tool\nEstimate Time-Integrated Activity (TIA) from Two SPECT Time Points using Mono-Exponential Modeling.")
+    gr.Markdown("#gr.Markdown("""
+---
+
+### ℹ️ **What Is This Tool?**
+
+This free, open-source web application is designed to calculate **Time-Integrated Activity (TIA)** for patients undergoing **Lutetium-177 PSMA therapy** in metastatic prostate cancer. It uses only two post-treatment SPECT imaging time points to produce accurate, personalized dosimetry in resource-constrained settings.
+
+The tool relies on a simplified yet clinically validated mathematical model (mono-exponential washout), commonly used for organs with regular clearance kinetics such as kidneys or PSMA-positive tumors.
+
+---
+
+### ⚙️ **How Does It Work?**
+
+You simply enter:
+- Two imaging time points (in hours)
+- Measured activity for each point (in MBq)
+
+The tool automatically:
+- Fits the time–activity curve (TAC) using exponential modeling  
+- Calculates the washout rate (_k_), initial activity (_A₀_), and total time-integrated activity (_TIA = A₀ / k_)  
+- Displays results instantly and clearly  
+
+---
+
+### 🧠 **Scientific Basis**
+
+This method applies the following model:
+
+> **A(t) = A₀ · exp(–k · t)**  
+> **TIA = A₀ / k**
+
+Where:
+- _A(t)_ is the activity at time _t_  
+- _A₀_ is the estimated initial activity  
+- _k_ is the washout rate (clearance constant)  
+- _TIA_ is the integrated activity over time used to estimate absorbed radiation dose
+
+This model is suitable for organs and lesions that exhibit predictable biological clearance and helps support practical dosimetry protocols in clinical or academic environments.
+
+---
+""")
+.")
     
     with gr.Row():
         t1 = gr.Number(label="Time Point 1 (hours)", value=20)