Upload 2 files

train_efficientnetb0_finetuned.py

@@ -0,0 +1,142 @@
+import os
+import urllib.request
+import numpy as np
+import tensorflow as tf
+from tensorflow.keras.preprocessing import image
+from tensorflow.keras.applications.efficientnet import preprocess_input
+import gradio as gr
+import cv2
+
+MODEL_PATH = "efficientnetb0_finetuned_brain_mri.h5"
+
+# Direct download URL from your Hugging Face Repository
+MODEL_URL = "https://huggingface.co/starpreeda/BrainTumorTest/resolve/main/efficientnetb0_finetuned_brain_mri.h5"
+
+def load_brain_mri_model():
+    """Download model weights if not locally available and load Keras model."""
+    if not os.path.exists(MODEL_PATH):
+        print("Downloading model weights from Hugging Face Repository...")
+        try:
+            urllib.request.urlretrieve(MODEL_URL, MODEL_PATH)
+            print("Model weights downloaded successfully!")
+        except Exception as e:
+            print(f"Error downloading model: {e}")
+            print("Attempting to load from local working directory...")
+    
+    return tf.keras.models.load_model(MODEL_PATH)
+
+# Load the model into memory
+model = load_brain_mri_model()
+
+CLASS_MAPPING = {
+    'glioma': {
+        'name': 'Glioma Tumor',
+        'desc': 'A type of tumor that originates in the glial cells supporting the brain and spinal cord.'
+    },
+    'meningioma': {
+        'name': 'Meningioma Tumor',
+        'desc': 'A tumor arising from the meninges — the protective membranes surrounding the brain and spinal cord.'
+    },
+    'notumor': {
+        'name': 'No Tumor Detected',
+        'desc': 'The provided MRI scan shows no clear evidence or signs of brain tumor tissue.'
+    },
+    'pituitary': {
+        'name': 'Pituitary Tumor',
+        'desc': 'An abnormal growth located in the pituitary gland at the base of the brain, which can affect hormone levels.'
+    }
+}
+
+CLASS_NAMES = ['glioma', 'meningioma', 'notumor', 'pituitary']
+
+def predict_mri(input_img):
+    """Preprocess input image, predict tumor category, and return summary HTML and confidence breakdown."""
+    if input_img is None:
+        return "<h3 style='color:#d93025;'>Please upload a valid Brain MRI scan image.</h3>", {}
+    
+
+    img_resized = cv2.resize(input_img, (224, 224))
+    img_array = image.img_to_array(img_resized)
+    img_batch = np.expand_dims(img_array, axis=0)
+    
+
+    img_preprocessed = preprocess_input(img_batch)
+    
+ 
+    predictions = model.predict(img_preprocessed)[0]
+    
+
+    confidences = {}
+    for idx, class_key in enumerate(CLASS_NAMES):
+        label_text = CLASS_MAPPING[class_key]['name']
+        confidences[label_text] = float(predictions[idx])
+    
+    
+    top_idx = np.argmax(predictions)
+    top_key = CLASS_NAMES[top_idx]
+    top_confidence = predictions[top_idx] * 100
+    info = CLASS_MAPPING[top_key]
+    
+ 
+    summary_html = f"""
+    <div style="background-color: #f8f9fa; border-left: 6px solid #1a73e8; padding: 18px; border-radius: 8px; margin-top: 10px;">
+        <h3 style="color: #1a73e8; margin-top: 0;">Diagnostic Classification Summary</h3>
+        
+        <p style="font-size: 20px; font-weight: bold; margin-bottom: 8px;">
+            Predicted Class: <span style="color: #d93025;">{info['name']}</span>
+        </p>
+        <p style="font-size: 16px; font-weight: bold; color: #3c4043;">
+            Confidence Score: <span style="font-size: 20px; color: #188038;">{top_confidence:.2f}%</span>
+        </p>
+        
+        <hr style="border: 0.5px solid #dadce0; margin: 12px 0;">
+        
+        <div style="background-color: #ffffff; padding: 12px; border-radius: 6px; border: 1px solid #e0e0e0;">
+            <p style="margin: 4px 0; font-size: 14px; color: #5f6368;"><b>Clinical Note:</b> {info['desc']}</p>
+        </div>
+    </div>
+    """
+    
+    return summary_html, confidences
+
+# ====================================================
+# 4. Gradio User Interface (Full English)
+# ====================================================
+with gr.Blocks(title="Brain Tumor MRI Classification", theme=gr.themes.Soft()) as demo:
+    
+    gr.Markdown(
+        """
+        # 🧠 Brain Tumor MRI Classification System
+        ### Fine-Tuned EfficientNetB0 Deep Learning Model
+        
+        Upload a Brain MRI scan to analyze and classify potential tumor types (*Glioma, Meningioma, Pituitary, or No Tumor*).
+        """
+    )
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            image_input = gr.Image(type="numpy", label="Upload Brain MRI Image")
+            submit_btn = gr.Button("🔍 Analyze MRI Scan", variant="primary", size="lg")
+            
+            gr.Markdown(
+                """
+                ---
+                ⚠️ **Medical Disclaimer:**
+                This AI application is designed strictly for educational, demonstration, and preliminary research purposes. It should **not** be used as a primary diagnostic tool or as a substitute for professional evaluation by a licensed radiologist or healthcare provider.
+                """
+            )
+            
+        with gr.Column(scale=1):
+            result_output = gr.HTML(label="Classification Result")
+            label_output = gr.Label(num_top_classes=4, label="Class Probability Distribution")
+            
+    # Event Listener
+    submit_btn.click(
+        fn=predict_mri,
+        inputs=[image_input],
+        outputs=[result_output, label_output]
+    )
+
+
+if __name__ == "__main__":
+    demo.launch(share=True)