app.py

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"
    #     )