app.py

import streamlit as st
from PIL import Image
import pytesseract
import pandas as pd
import re


def extract_text(image):
    """
    Extract text from the image using Tesseract.
    """
    return pytesseract.image_to_string(image)


def clean_and_parse_extracted_text(raw_text):
    """
    Parse and clean the raw text to extract structured data.
    """
    # Split the text into lines and clean up
    lines = raw_text.split("\n")
    lines = [line.strip() for line in lines if line.strip()]

    # Identify and extract rows with valid components
    data = []
    for line in lines:
        # Match rows containing numeric ranges and values
        match = re.match(
            r"^(.*?)(\d+(\.\d+)?)(\s*-?\s*\d+(\.\d+)?\s*-?\s*\d+(\.\d+)?)?\s*([a-zA-Z/%]+)?\s*(H|L|Normal)?$",
            line,
        )
        if match:
            component = match.group(1).strip()
            value = float(match.group(2))
            range_match = match.group(4)
            if range_match:
                ranges = re.findall(r"[\d.]+", range_match)
                min_val = float(ranges[0]) if len(ranges) > 0 else None
                max_val = float(ranges[1]) if len(ranges) > 1 else None
            else:
                min_val = None
                max_val = None
            unit = match.group(7)
            flag = "Normal"  # Default flag

            # Determine the flag based on value and range
            if min_val is not None and max_val is not None:
                if value < min_val:
                    flag = "L"
                elif value > max_val:
                    flag = "H"

            # Only append the data if the flag is abnormal (L or H)
            if flag != "Normal":
                data.append([component, value, min_val, max_val, unit, flag])

    # Create a DataFrame
    df = pd.DataFrame(data, columns=["Component", "Your Value", "Min", "Max", "Units", "Flag"])

    # Fix misspellings and inconsistencies (if any known issues exist)
    correction_map = {
        "emoglobin": "Hemoglobin",
        "ematocrit": "Hematocrit",
        "% Platelet Count": "Platelet Count",
        "ymphocyte %": "Lymphocyte %",
        "L Differential Type Automated": "Differential Type",
    }
    df["Component"] = df["Component"].replace(correction_map)

    return df


def display_results(df):
    """
    Display the flagged abnormalities in a table format.
    """
    st.dataframe(df, use_container_width=True)


# Streamlit app
st.title("Blood Report Analyzer")
st.write("Upload an image of a blood test report to analyze.")

uploaded_file = st.file_uploader("Upload Image", type=["png", "jpg", "jpeg"])

if uploaded_file is not None:
    try:
        # Load the image
        image = Image.open(uploaded_file)

        # Display the uploaded image
        st.image(image, caption="Uploaded Image", use_container_width=True)

        # Extract text from the image
        extracted_text = extract_text(image)

        # Parse the extracted text into a structured format
        parsed_data = clean_and_parse_extracted_text(extracted_text)

        # Display the structured data (only abnormalities)
        st.subheader("Flagged Abnormalities")
        display_results(parsed_data)

    except Exception as e:
        st.error(f"An error occurred: {e}")