Update app.py

app.py

@@ -1,12 +1,76 @@
-import pytesseract
-import subprocess
 import streamlit as st
+import pdfplumber
+import pytesseract
+from PIL import Image
+from transformers import pipeline
+import re
+
+# Ensure Tesseract-OCR is properly configured (Uncomment & update path if needed)
+# pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
+
+# Load pre-trained Hugging Face models
+summarizer = pipeline("summarization", model="t5-small")
+medical_qa = pipeline("question-answering", model="deepset/bert-base-cased-squad2")
+
+# Function to extract text from PDF
+def extract_text_from_pdf(pdf_file):
+    with pdfplumber.open(pdf_file) as pdf:
+        text = "\n".join(page.extract_text() for page in pdf.pages if page.extract_text())
+    return text if text else "No text found in PDF."
+
+# Function to extract text from images (JPG, PNG)
+def extract_text_from_image(image_file):
+    image = Image.open(image_file)
+    text = pytesseract.image_to_string(image)
+    return text.strip() if text else "No text found in Image."
+
+# Function to summarize medical report
+def summarize_report(text):
+    if len(text) > 500:  # Handle long text
+        text = text[:500]  
+    summary = summarizer(text, max_length=150, min_length=50, do_sample=False)
+    return summary[0]['summary_text']
+
+# Function to find medical terms dynamically using regex
+def extract_medical_terms(text):
+    words = re.findall(r'\b[A-Z][a-z]+(?:[ -][A-Z][a-z]+)*\b', text)
+    return list(set(words))
+
+# Function to explain medical terms
+def explain_term(term):
+    context = "Hypercholesterolemia is a condition with high cholesterol in the blood. Atherosclerosis refers to artery narrowing due to fat buildup."
+    response = medical_qa(question=f"What is {term}?", context=context)
+    return response["answer"]
+
+# Streamlit UI
+st.title("🩺 AI Medical Report Analyzer")
+st.write("Upload a medical **PDF or Image (JPG, PNG)** to get a summarized report with term explanations.")
+
+uploaded_file = st.file_uploader("Upload a PDF or Image", type=["pdf", "jpg", "png"])
+
+if uploaded_file:
+    file_type = uploaded_file.type
+
+    if file_type == "application/pdf":
+        text = extract_text_from_pdf(uploaded_file)
+        st.subheader("📜 Extracted Text from PDF:")
+    elif file_type in ["image/png", "image/jpeg"]:
+        text = extract_text_from_image(uploaded_file)
+        st.subheader("🖼️ Extracted Text from Image:")
+
+    st.text_area("Report Content:", text, height=200)
 
-# Check if Tesseract is installed
-tesseract_path = subprocess.run(["which", "tesseract"], capture_output=True, text=True).stdout.strip()
+    if st.button("Generate AI Summary"):
+        summary = summarize_report(text)
+        st.subheader("📑 AI-Generated Summary:")
+        st.markdown(f"**{summary}**")
 
-if not tesseract_path:
-    st.error("Tesseract is not installed. Make sure 'apt.txt' contains 'tesseract-ocr'.")
-else:
-    st.success(f"Tesseract is installed at: {tesseract_path}")
-    pytesseract.pytesseract.tesseract_cmd = tesseract_path
+    if st.button("Explain Medical Terms"):
+        terms = extract_medical_terms(text)
+        if terms:
+            st.subheader("📖 Medical Term Explanations:")
+            for term in terms[:5]:  # Limit to 5 terms for efficiency
+                explanation = explain_term(term)
+                st.markdown(f"**{term}:** {explanation}")
+        else:
+            st.write("No medical terms detected.")