Update app.py

app.py

@@ -1,129 +1,129 @@
-from fastapi import FastAPI, UploadFile, File, HTTPException
-from fastapi.middleware.cors import CORSMiddleware
-import tensorflow as tf
-import numpy as np
-from PIL import Image
-import io
-import httpx
-
-app = FastAPI()
-
-# Enable CORS
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
-
-# Load the MRI detector model
-mri_detector_model = tf.keras.models.load_model('mri_detector.h5')
-
-# Class labels for MRI detector
-MRI_CLASS_LABELS = ["Brain MRI", "Not a Brain MRI"]
-
-# Dementia API endpoint
-DEMENTIA_API_URL = "https://arittrabag-dementia-backend.hf.space/analyze"
-
-def preprocess_image_for_mri_detection(image_bytes):
-    """
-    Preprocess image for MRI detection model
-    Based on the original preprocessing: resize to (224, 224) and normalize by /255.0
-    """
-    # Open image from bytes
-    img = Image.open(io.BytesIO(image_bytes))
-    
-    # Convert to RGB if needed
-    if img.mode != 'RGB':
-        img = img.convert('RGB')
-    
-    # Resize to model's expected input size (224, 224)
-    img = img.resize((224, 224))
-    
-    # Convert to numpy array and preprocess exactly like the original
-    img_array = np.array(img) / 255.0  # Normalize pixel values
-    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
-    
-    return img_array
-
-async def call_dementia_api(image_bytes):
-    """
-    Call the dementia detection API with the uploaded image
-    """
-    try:
-        async with httpx.AsyncClient(timeout=30.0) as client:
-            files = {"file": ("image.jpg", image_bytes, "image/jpeg")}
-            response = await client.post(DEMENTIA_API_URL, files=files)
-            response.raise_for_status()
-            return response.json()
-    except httpx.RequestError as e:
-        raise HTTPException(status_code=503, detail=f"Failed to connect to dementia API: {str(e)}")
-    except httpx.HTTPStatusError as e:
-        raise HTTPException(status_code=e.response.status_code, detail=f"Dementia API error: {e.response.text}")
-
-@app.get("/")
-async def root():
-    return {"message": "MRI Detector API - Upload an image to check if it's an MRI scan"}
-
-@app.post("/detect")
-async def detect_and_analyze(file: UploadFile = File(...)):
-    """
-    Main endpoint that:
-    1. Checks if uploaded image is an MRI
-    2. If MRI, calls dementia detection API
-    3. Returns combined results
-    """
-    # Validate file type
-    if not file.content_type or not file.content_type.startswith('image/'):
-        raise HTTPException(status_code=400, detail="File must be an image")
-    
-    # Read image file
-    contents = await file.read()
-    
-    try:
-        # Step 1: Check if image is MRI
-        img_array = preprocess_image_for_mri_detection(contents)
-        mri_predictions = mri_detector_model.predict(img_array)
-        
-        # Get MRI detection results
-        mri_confidences = mri_predictions[0].tolist()
-        predicted_class_idx = np.argmax(mri_confidences)
-        predicted_class = MRI_CLASS_LABELS[predicted_class_idx]
-        mri_confidence = float(mri_confidences[predicted_class_idx])
-        
-        # Create MRI confidence dictionary
-        mri_confidence_dict = {label: float(conf) for label, conf in zip(MRI_CLASS_LABELS, mri_confidences)}
-        
-        response = {
-            "isMRI": predicted_class == "Brain MRI",
-            "mriConfidence": mri_confidence,
-            "mriClassification": {
-                "predictedClass": predicted_class,
-                "confidences": mri_confidence_dict
-            }
-        }
-        
-        # Step 2: If it's an MRI, call dementia detection API
-        if predicted_class == "Brain MRI":
-            try:
-                dementia_results = await call_dementia_api(contents)
-                response["dementiaAnalysis"] = dementia_results
-                response["status"] = "analysis_complete"
-                response["message"] = "Image identified as Brain MRI scan. Dementia analysis completed."
-            except Exception as e:
-                response["status"] = "mri_detected_but_analysis_failed"
-                response["message"] = f"Image identified as Brain MRI scan, but dementia analysis failed: {str(e)}"
-                response["error"] = str(e)
-        else:
-            response["status"] = "not_mri"
-            response["message"] = f"Image identified as {predicted_class} with {mri_confidence*100:.1f}% confidence. Dementia analysis not performed as this is not a Brain MRI scan."
-        
-        return response
-        
-    except Exception as e:
-        raise HTTPException(status_code=500, detail=f"Error processing image: {str(e)}")
-
-@app.get("/health")
-async def health_check():
+from fastapi import FastAPI, UploadFile, File, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+import tensorflow as tf
+import numpy as np
+from PIL import Image
+import io
+import httpx
+
+app = FastAPI()
+
+# Enable CORS
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Load the MRI detector model
+mri_detector_model = tf.keras.models.load_model('mri_detector.h5')
+
+# Class labels for MRI detector
+MRI_CLASS_LABELS = ["Brain MRI", "Not a Brain MRI"]
+
+# Dementia API endpoint
+DEMENTIA_API_URL = "https://arittrabag-alzheimers-h4b.hf.space/analyze"
+
+def preprocess_image_for_mri_detection(image_bytes):
+    """
+    Preprocess image for MRI detection model
+    Based on the original preprocessing: resize to (224, 224) and normalize by /255.0
+    """
+    # Open image from bytes
+    img = Image.open(io.BytesIO(image_bytes))
+    
+    # Convert to RGB if needed
+    if img.mode != 'RGB':
+        img = img.convert('RGB')
+    
+    # Resize to model's expected input size (224, 224)
+    img = img.resize((224, 224))
+    
+    # Convert to numpy array and preprocess exactly like the original
+    img_array = np.array(img) / 255.0  # Normalize pixel values
+    img_array = np.expand_dims(img_array, axis=0)  # Add batch dimension
+    
+    return img_array
+
+async def call_dementia_api(image_bytes):
+    """
+    Call the dementia detection API with the uploaded image
+    """
+    try:
+        async with httpx.AsyncClient(timeout=30.0) as client:
+            files = {"file": ("image.jpg", image_bytes, "image/jpeg")}
+            response = await client.post(DEMENTIA_API_URL, files=files)
+            response.raise_for_status()
+            return response.json()
+    except httpx.RequestError as e:
+        raise HTTPException(status_code=503, detail=f"Failed to connect to dementia API: {str(e)}")
+    except httpx.HTTPStatusError as e:
+        raise HTTPException(status_code=e.response.status_code, detail=f"Dementia API error: {e.response.text}")
+
+@app.get("/")
+async def root():
+    return {"message": "MRI Detector API - Upload an image to check if it's an MRI scan"}
+
+@app.post("/detect")
+async def detect_and_analyze(file: UploadFile = File(...)):
+    """
+    Main endpoint that:
+    1. Checks if uploaded image is an MRI
+    2. If MRI, calls dementia detection API
+    3. Returns combined results
+    """
+    # Validate file type
+    if not file.content_type or not file.content_type.startswith('image/'):
+        raise HTTPException(status_code=400, detail="File must be an image")
+    
+    # Read image file
+    contents = await file.read()
+    
+    try:
+        # Step 1: Check if image is MRI
+        img_array = preprocess_image_for_mri_detection(contents)
+        mri_predictions = mri_detector_model.predict(img_array)
+        
+        # Get MRI detection results
+        mri_confidences = mri_predictions[0].tolist()
+        predicted_class_idx = np.argmax(mri_confidences)
+        predicted_class = MRI_CLASS_LABELS[predicted_class_idx]
+        mri_confidence = float(mri_confidences[predicted_class_idx])
+        
+        # Create MRI confidence dictionary
+        mri_confidence_dict = {label: float(conf) for label, conf in zip(MRI_CLASS_LABELS, mri_confidences)}
+        
+        response = {
+            "isMRI": predicted_class == "Brain MRI",
+            "mriConfidence": mri_confidence,
+            "mriClassification": {
+                "predictedClass": predicted_class,
+                "confidences": mri_confidence_dict
+            }
+        }
+        
+        # Step 2: If it's an MRI, call dementia detection API
+        if predicted_class == "Brain MRI":
+            try:
+                dementia_results = await call_dementia_api(contents)
+                response["dementiaAnalysis"] = dementia_results
+                response["status"] = "analysis_complete"
+                response["message"] = "Image identified as Brain MRI scan. Dementia analysis completed."
+            except Exception as e:
+                response["status"] = "mri_detected_but_analysis_failed"
+                response["message"] = f"Image identified as Brain MRI scan, but dementia analysis failed: {str(e)}"
+                response["error"] = str(e)
+        else:
+            response["status"] = "not_mri"
+            response["message"] = f"Image identified as {predicted_class} with {mri_confidence*100:.1f}% confidence. Dementia analysis not performed as this is not a Brain MRI scan."
+        
+        return response
+        
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error processing image: {str(e)}")
+
+@app.get("/health")
+async def health_check():
     return {"status": "healthy", "message": "MRI Detector API is running"}