enh: show github readme dynamically for data download instructions

filter_data_app.py

@@ -6,6 +6,7 @@ from upsetplot import UpSet
 import matplotlib.pyplot as plt
 import polars as pl
 from polars import col, lit
+import requests
 import seaborn as sns
 
 # Set page configuration
@@ -106,6 +107,12 @@ def main():
             with open("instructions.txt", "r") as file:
                 instructions = file.read()
             st.write(instructions)
+        with st.expander("Data Availability Instructions from GitHub"):
+            url = "https://raw.githubusercontent.com/ImagingDataCommons/CloudSegmentatorResults/main/README.md"
+            response = requests.get(url)
+            instructions = response.text
+            st.write(instructions)
+
         with st.sidebar:
             st.title("Filters")
 
@@ -373,7 +380,8 @@ def main():
 
     # Define the pages
     if page == "Summary":
-        st.markdown('''
+        with st.expander("Instructions to navigating the dashboard"):
+            st.write("""
         This page of the dashboard presents a summary of the following four rule-based checks applied to over 9.5 million segmentations 
         from TotalSegmentator(v1) on 125k+ NLST CT scans, displaying the percentage of segmentations passing each check 
         to highlight potential quality issues 
@@ -381,7 +389,17 @@ def main():
         - laterality (confirming correct left/right labeling)
         - connected components (verifying single, continuous regions)
         - minimum volume from voxel summation (filtering out artifacts smaller than 5mL)
-        ''')
+        
+        Sort the hueristics or search for bodyPart(s) using the options in the sidebar
+        """
+                     )
+
+        with st.expander("Data Availability Instructions from GitHub"):
+            url = "https://raw.githubusercontent.com/ImagingDataCommons/CloudSegmentatorResults/main/README.md"
+            response = requests.get(url)
+            instructions = response.text
+            st.write(instructions)
+  
         # Execute the SQL to get summary statistics
         summary_df = duckdb.query("""
             WITH Checks AS (

requirements.txt

@@ -3,6 +3,7 @@ matplotlib
 pandas
 polars
 pyarrow
+requests
 seaborn
 streamlit
 streamlit_extras