Update app.py

app.py

@@ -1,59 +1,61 @@
 import streamlit as st
-from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
-import torch
-import easyocr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 from PIL import Image
-import fitz  # PyMuPDF
-
-# Load EasyOCR Reader
-reader = easyocr.Reader(['en'])
+import pytesseract
+import PyPDF2
+import pdfplumber
+import torch
 
-# Load ClinicalBERT Model
+# Load ClinicalBERT model for medical text analysis
 @st.cache_resource
 def load_clinicalbert():
-    model_name = "emilyalsentzer/Bio_ClinicalBERT"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForSequenceClassification.from_pretrained(model_name)
-    return pipeline("text-classification", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
+    tokenizer = AutoTokenizer.from_pretrained("emilyalsentzer/Bio_ClinicalBERT")
+    model = AutoModelForSequenceClassification.from_pretrained("emilyalsentzer/Bio_ClinicalBERT")
+    return pipeline("zero-shot-classification", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)
 
-clinicalbert_analyzer = load_clinicalbert()
+# Initialize ClinicalBERT classifier
+clinical_bert = load_clinicalbert()
 
-# OCR function using EasyOCR
+# OCR for Image using Tesseract
 def extract_text_from_image(image):
-    image = Image.open(image).convert('RGB')
-    result = reader.readtext(image, detail=0)
-    extracted_text = " ".join(result)
-    return extracted_text
+    return pytesseract.image_to_string(image)
 
-# PDF text extraction using PyMuPDF
+# Extract text from PDF using pdfplumber
 def extract_text_from_pdf(pdf_file):
     text = ""
-    with fitz.open(pdf_file) as pdf:
-        for page in pdf:
-            text += page.get_text()
+    with pdfplumber.open(pdf_file) as pdf:
+        for page in pdf.pages:
+            text += page.extract_text() or ""
     return text
 
-# Analysis function using ClinicalBERT
-def analyze_report(text):
-    # Define prompts for analysis
-    summary_prompt = f"Summarize the following medical report:\n{text}"
-    interpretation_prompt = f"Interpret the following lab results:\n{text}"
-    recommendation_prompt = f"Provide actionable recommendations based on this medical report:\n{text}"
+# Analyze and interpret the medical report using ClinicalBERT
+def analyze_medical_text(text):
+    # Summarize the extracted text
+    summary = clinical_bert(text, candidate_labels=["summary", "overview", "findings"], multi_label=False)['labels'][0]
 
-    # Use ClinicalBERT for text analysis
-    summary = clinicalbert_analyzer(summary_prompt)[0]['label']
-    interpretation = clinicalbert_analyzer(interpretation_prompt)[0]['label']
-    recommendations = clinicalbert_analyzer(recommendation_prompt)[0]['label']
+    # Provide detailed interpretation
+    interpretation = clinical_bert(
+        text,
+        candidate_labels=["normal", "abnormal", "urgent", "needs follow-up", "critical condition"],
+        multi_label=True
+    )
+
+    # Provide actionable recommendations
+    recommendations = clinical_bert(
+        text,
+        candidate_labels=["medication", "dietary change", "exercise", "follow-up with a doctor", "lifestyle change"],
+        multi_label=True
+    )
 
     return {
         "summary": summary,
-        "interpretation": interpretation,
-        "recommendations": recommendations
+        "interpretation": interpretation['labels'],
+        "recommendations": recommendations['labels']
     }
 
 # Streamlit UI
-st.title("Clinical Lab Report Analyzer")
-st.write("Upload your medical lab report (PDF/Image) to get a summary, interpretation, and actionable recommendations.")
+st.title("Medical Lab Report Analyzer with ClinicalBERT")
+st.write("Upload your medical lab report (PDF/Image) to get a summary and actionable insights using ClinicalBERT.")
 
 uploaded_file = st.file_uploader("Choose a PDF/Image file", type=["pdf", "png", "jpg", "jpeg"])
 
@@ -66,21 +68,24 @@ if uploaded_file:
             extracted_text = extract_text_from_pdf(uploaded_file)
     else:
         with st.spinner("Extracting text from Image..."):
-            extracted_text = extract_text_from_image(uploaded_file)
+            image = Image.open(uploaded_file)
+            extracted_text = extract_text_from_image(image)
 
     # Analyze the extracted text
-    if extracted_text:
-        with st.spinner("Analyzing the medical report using ClinicalBERT..."):
-            result = analyze_report(extracted_text)
-        
+    if extracted_text.strip():
+        with st.spinner("Analyzing report using ClinicalBERT..."):
+            result = analyze_medical_text(extracted_text)
+
         # Display the results
-        st.subheader("Summary")
+        st.subheader("Summary of the Report")
         st.write(result['summary'])
 
         st.subheader("Interpretation of Results")
-        st.write(result['interpretation'])
+        for label in result['interpretation']:
+            st.write(f"- {label.capitalize()}")
 
         st.subheader("Actionable Recommendations")
-        st.write(result['recommendations'])
+        for rec in result['recommendations']:
+            st.write(f"- {rec.capitalize()}")
     else:
         st.error("No text could be extracted. Please try with a different file.")