Update app.py

app.py

@@ -31,13 +31,10 @@ st.sidebar.write("""
 ### Background
 Cervical cancer is a significant health issue that profoundly impacts women's lives, making awareness and education crucial. 
 It is a leading cause of cancer-related morbidity and mortality among women globally. 
-Understanding the importance of regular screenings and vaccinations can empower individuals to take proactive steps in prevention. 
-Additionally, raising awareness about the signs and symptoms of cervical cancer fosters early detection, which is vital for effective treatment. 
-Through community support and education, we can work together to reduce the burden of this disease and promote healthier futures for women everywhere.
+Understanding the importance of regular screenings and vaccinations is vital for effective treatment. 
 
 ### The Problem
-Cervical cancer poses a significant risk to women's health, emphasizing the urgent need for early detection to prevent its progression. 
-Current methods like the Pap smear test can be slow and labor-intensive, prompting researchers to develop classification models to assist medical professionals. 
+Current methods in early detection like the Pap smear test can be slow and labor-intensive, prompting researchers to develop classification models to assist medical professionals. 
 However, many of these models face challenges with image segmentation, particularly in cases of overlapping cells. 
 This prototype seeks to improve upon existing machine learning models by incorporating the U-Net architecture, designed for precise image segmentation, to enhance the identification of cancerous cells in cervical samples, ultimately facilitating faster and more accurate diagnoses.
 """)