Update app.py

app.py

@@ -1,24 +1,53 @@
+import streamlit as st
 import easyocr
-import requests
-from transformers import AutoModelForTokenClassification, AutoTokenizer
-from transformers import pipeline
+from transformers import AutoModelForTokenClassification, AutoTokenizer, pipeline
+from PIL import Image
+import numpy as np
 
-# Initialize EasyOCR for text extraction from medical report image
+# Initialize EasyOCR for text extraction
 reader = easyocr.Reader(['en'])
 
+# Load ClinicalBERT for NER (Named Entity Recognition)
+model_name = "emilyalsentzer/Bio_ClinicalBERT"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForTokenClassification.from_pretrained(model_name)
+nlp = pipeline("ner", model=model, tokenizer=tokenizer)
+
+# Mock function for validating test results
+def validate_medical_value(test_name, test_value):
+    reference_ranges = {
+        "Blood Pressure": (90, 120),  # Example range: systolic
+        "Glucose": (70, 100),  # Normal range for glucose in mg/dL
+    }
+    
+    if test_name in reference_ranges:
+        min_range, max_range = reference_ranges[test_name]
+        if test_value < min_range:
+            return f"{test_name} is low."
+        elif test_value > max_range:
+            return f"{test_name} is high."
+        else:
+            return f"{test_name} is within the normal range."
+    else:
+        return f"{test_name} range is unknown."
+
 # Function to extract text from image
-def extract_text_from_image(image_path):
-    result = reader.readtext(image_path)
+def extract_text_from_image(image):
+    result = reader.readtext(image)
     text = ' '.join([item[1] for item in result])
     return text
 
-# Load Med7 model for medical NER (Named Entity Recognition)
-model_name = "jeff1evesque/med7"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForTokenClassification.from_pretrained(model_name)
-
-# Initialize the NER pipeline with Med7 model
-nlp = pipeline("ner", model=model, tokenizer=tokenizer)
+# Function to check image clarity (basic approach using edge detection)
+def check_image_clarity(image):
+    # Convert image to grayscale
+    gray_image = image.convert("L")
+    image_np = np.array(gray_image)
+    
+    # Simple edge detection (Laplacian method)
+    laplacian_var = cv2.Laplacian(image_np, cv2.CV_64F).var()
+    
+    # Threshold for determining clarity
+    return laplacian_var > 100  # This threshold can be adjusted
 
 # Function to extract medical entities (test results) from text
 def extract_medical_values(text):
@@ -26,53 +55,52 @@ def extract_medical_values(text):
     medical_data = {}
     
     for entity in entities:
-        if entity['entity_group'] == 'LAB_RESULT':  # Change based on Med7's NER labels
+        if entity['entity_group'] in ['LAB_RESULT', 'DISEASE', 'MEDICATION']:  # Modify based on actual labels
             medical_data[entity['word']] = entity['score']
     
     return medical_data
 
-# Function to check the values with LabTestAPI or similar API
-def validate_medical_value(test_name, test_value):
-    # Example of API call (replace with actual API)
-    api_url = "https://api.labtestapi.com/get_reference_range"
-    params = {
-        "test_name": test_name,
-        "value": test_value
-    }
-    response = requests.get(api_url, params=params)
-    if response.status_code == 200:
-        result = response.json()
-        return result['normal_range']
-    else:
-        return None
-
 # Function to analyze medical report
-def analyze_report(image_path):
-    # Step 1: Extract text from the medical report image
-    text = extract_text_from_image(image_path)
+def analyze_report(image):
+    # Step 1: Check image clarity
+    if not check_image_clarity(image):
+        return "Image is unclear, please upload a clearer image."
+    
+    # Step 2: Extract text from the medical report image
+    text = extract_text_from_image(image)
     
-    # Step 2: Extract medical values using Med7
+    # Step 3: Extract medical values using ClinicalBERT
     medical_values = extract_medical_values(text)
     
     analysis_results = []
     
     for test_name, test_value in medical_values.items():
-        # Step 3: Validate test value against normal range
-        normal_range = validate_medical_value(test_name, test_value)
-        if normal_range:
-            if test_value < normal_range[0]:
-                analysis_results.append(f"{test_name} is low. Consider consulting a doctor.")
-            elif test_value > normal_range[1]:
-                analysis_results.append(f"{test_name} is high. Consult a doctor.")
-            else:
-                analysis_results.append(f"{test_name} is within the normal range.")
-        else:
-            analysis_results.append(f"Could not validate {test_name}.")
+        # Step 4: Validate test value against normal range
+        validation_result = validate_medical_value(test_name, test_value)
+        analysis_results.append(validation_result)
     
     return analysis_results
 
-# Example Usage
-image_path = "path_to_medical_report_image.png"
-analysis = analyze_report(image_path)
-for result in analysis:
-    print(result)
+# Streamlit UI
+st.title("Medical Report Analyzer")
+st.write("Upload your medical report image to analyze the test results.")
+
+# Upload the image
+uploaded_image = st.file_uploader("Upload Image", type=["jpg", "png", "jpeg"])
+
+if uploaded_image is not None:
+    # Open the uploaded image
+    image = Image.open(uploaded_image)
+    
+    # Show image for verification
+    st.image(image, caption="Uploaded Medical Report", use_column_width=True)
+    
+    # Analyze the report
+    analysis_results = analyze_report(image)
+    
+    # Display results
+    if isinstance(analysis_results, list):
+        for result in analysis_results:
+            st.write(result)
+    else:
+        st.write(analysis_results)