Update app.py

app.py

@@ -1,78 +1,45 @@
 import streamlit as st
-import torch
-from transformers import AutoTokenizer, pipeline
-from pdf2image import convert_from_path
-import pytesseract
+from PyPDF2 import PdfReader
+from transformers import pipeline
 from PIL import Image
-import os
-import io
-from typing import List, Tuple
 
-# Initialize models and tokenizer
-text_model_name = "peteparker456/medical_diagnosis_llama2"
+# Load Hugging Face model
+model = pipeline("text-classification", model="medicalai/ClinicalBERT")
 
-# Load the vision and text models
-text_model = pipeline("text-generation", model=text_model_name)
-
-pytesseract.pytesseract.tesseract_cmd = r'/usr/bin/tesseract'  # Path to Tesseract executable
-
-# Streamlit UI
-st.title("Medical Lab Report Analyzer")
-st.write(
-    "Upload an image or PDF file of a medical lab report to get an interpretation, actionable recommendations, and additional insights."
-)
-
-# Upload the image or PDF file
-uploaded_file = st.file_uploader(
-    "Upload Image or PDF", type=["jpg", "jpeg", "png", "pdf"]
-)
-
-def extract_text_from_image(image: Image.Image) -> str:
-    return pytesseract.image_to_string(image)
-
-def extract_text_from_pdf(pdf_path: str) -> str:
-    images = convert_from_path(pdf_path)
+def extract_text_from_pdf(pdf_file):
+    reader = PdfReader(pdf_file)
     text = ""
-    for img in images:
-        text += extract_text_from_image(img)
+    for page in reader.pages:
+        text += page.extract_text()
     return text
 
-def generate_insights(text: str) -> List[Tuple[str, str]]:
-    """Get interpretations and recommendations from the text."""
-    # Create a dummy input for the text model
-    output_text = text_model(text, max_length=1000)[0]["generated_text"]
-
-    return [
-        ("Report Interpretation", output_text),
-        ("Actionable Recommendations", "Consult your physician for further tests if the values are abnormal."),
-        ("Additional Insights", "Regular check-ups can help monitor and maintain healthy levels.")
-    ]
-
-# Process the uploaded file
-if uploaded_file:
-    file_type = uploaded_file.type
-    file_name = uploaded_file.name
-    st.write(f"Uploaded File: {file_name}")
+def get_lab_report_interpretation(text):
+    result = model(text)
+    return result[0]['label']
 
-    if file_type == "application/pdf":
-        with open("temp.pdf", "wb") as f:
-            f.write(uploaded_file.getvalue())
-        extracted_text = extract_text_from_pdf("temp.pdf")
-        os.remove("temp.pdf")
-    else:  # For image files
-        image = Image.open(io.BytesIO(uploaded_file.getvalue()))
-        extracted_text = extract_text_from_image(image)
+def process_image(image_file):
+    img = Image.open(image_file)
+    return img
 
-    if extracted_text.strip():
-        st.subheader("Extracted Text from Report")
-        st.text_area("Lab Report Text", extracted_text, height=200)
-
-        # Get lab report interpretation and recommendations
-        st.subheader("Analysis & Insights")
-        insights = generate_insights(extracted_text)
+# Streamlit UI
+st.title("Medical Lab Report Analyzer")
 
-        for title, insight in insights:
-            st.markdown(f"### {title}")
-            st.write(insight)
-    else:
-        st.error("No text found in the uploaded file. Please try another file.")
+# Upload image and PDF
+uploaded_pdf = st.file_uploader("Upload your PDF Medical Lab Report", type="pdf")
+uploaded_image = st.file_uploader("Upload Image of Medical Report", type="jpg png jpeg")
+
+if uploaded_pdf is not None:
+    st.subheader("Extracted Text from PDF:")
+    pdf_text = extract_text_from_pdf(uploaded_pdf)
+    st.write(pdf_text)
+    
+    st.subheader("Lab Report Interpretation:")
+    interpretation = get_lab_report_interpretation(pdf_text)
+    st.write(interpretation)
+
+elif uploaded_image is not None:
+    st.image(process_image(uploaded_image), caption="Uploaded Image", use_column_width=True)
+    st.warning("For text extraction from image, please upload a PDF.")
+    
+else:
+    st.info("Please upload a medical PDF or image for analysis.")