added file

app.py

@@ -0,0 +1,93 @@
+import streamlit as st
+from idc_index import index
+from pathlib import Path
+import pydicom
+import pandas as pd
+import pyarrow as pa
+import pyarrow.parquet as pq
+from tempfile import TemporaryDirectory
+import os
+from pathlib import Path
+import polars
+import pydicom.datadict as dd
+import shutil
+
+
+# Main Streamlit app code
+st.title("DICOM Classification Demo")
+st.write("Select IDC data to download, extract images and metadata, and perform inference using three pre-trained models")
+
+# Fetch IDC index
+client = index.IDCClient()
+index_df = client.index
+
+# Option to choose IDC data
+st.subheader("Choose IDC Data to Process")
+collection_ids = index_df["collection_id"].unique()
+selected_collection_id = st.selectbox("Select Collection ID", collection_ids)
+
+# Filter dataframe based on selected collection_id
+df_filtered_by_collection = index_df[index_df["collection_id"] == selected_collection_id]
+
+patients = df_filtered_by_collection["PatientID"].unique()
+selected_patient_id = st.selectbox("Select Patient ID", patients)
+
+# Filter dataframe based on selected patient_id
+df_filtered_by_patient = df_filtered_by_collection[df_filtered_by_collection["PatientID"] == selected_patient_id]
+
+modalities = df_filtered_by_patient["Modality"].unique()
+selected_modality = st.selectbox("Select Modality", modalities)
+
+# Filter dataframe based on selected modality
+df_filtered_by_modality = df_filtered_by_patient[df_filtered_by_patient["Modality"] == selected_modality]
+
+studies = df_filtered_by_modality["StudyInstanceUID"].unique()
+selected_study = st.selectbox("Select Study", studies)
+
+# Filter dataframe based on selected study
+df_filtered_by_study = df_filtered_by_modality[df_filtered_by_modality["StudyInstanceUID"] == selected_study]
+
+series = df_filtered_by_study["SeriesInstanceUID"].unique()
+selected_series = st.selectbox("Select Series", series)
+
+
+# Button to process IDC data
+if st.button("Process IDC data"):
+    # Fetch data from IDC based on selection
+    selection = index_df[
+        (index_df["SeriesInstanceUID"] == selected_series)
+    ]
+
+    series_instance_uids = selection["SeriesInstanceUID"].tolist()
+
+    #    with TemporaryDirectory() as temp_dir:
+    download_errors = []
+    #input_dir = os.path.join(temp_dir, "input_data")
+    input_dir=Path("input_data/")
+    if input_dir.exists():
+        shutil.rmtree(input_dir)
+    os.makedirs(input_dir, exist_ok=True)
+
+    try:
+        client.download_from_selection(seriesInstanceUID=series_instance_uids, downloadDir=input_dir)
+    except Exception as e:
+        download_errors.append(f"Error downloading data: {str(e)}")
+
+    if download_errors:
+        st.error("\n".join(download_errors))
+    else:
+        st.success("Data downloaded successfully.")
+
+    # Process downloaded DICOM data
+    dicom_files = [str(file) for file in input_dir.glob('**/*.dcm')]
+    # parquet_file = 'dcm2parquet_output.parquet'
+    # save_dicom_header_to_parquet(dicom_files, parquet_file)
+
+    st.success("Processing complete.")
+    # with open(parquet_file, "rb") as f:
+    #     st.download_button(
+    #         label="Download the metadata parquet file",
+    #         data=f,
+    #         file_name="dcm2parquet_output.parquet",
+    #         mime="application/parquet"
+    #     )