import cv2 import numpy as np import pandas as pd import gradio as gr from skimage import measure, morphology from skimage.segmentation import watershed import matplotlib.pyplot as plt from datetime import datetime import logging def apply_color_transformation(image, transform_type): """Apply different color transformations to the image""" if len(image.shape) == 3: image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR) if transform_type == "Original": return cv2.cvtColor(image, cv2.COLOR_BGR2RGB) elif transform_type == "Grayscale": return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) elif transform_type == "Binary": gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) _, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY) return binary elif transform_type == "CLAHE": gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8,8)) return clahe.apply(gray) return image def process_image(image, transform_type): """Process uploaded image and extract cell features""" if image is None: return None, None, None, None try: # Store original image for color transformations original_image = image.copy() # Convert to BGR if needed if len(image.shape) == 3: image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR) # Basic preprocessing gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8,8)) enhanced = clahe.apply(gray) blurred = cv2.medianBlur(enhanced, 5) # Thresholding _, binary = cv2.threshold(blurred, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) # Noise removal and cell separation kernel = np.ones((3,3), np.uint8) opening = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel, iterations=2) # Sure background area sure_bg = cv2.dilate(opening, kernel, iterations=3) # Finding sure foreground area dist_transform = cv2.distanceTransform(opening, cv2.DIST_L2, 5) _, sure_fg = cv2.threshold(dist_transform, 0.5 * dist_transform.max(), 255, 0) sure_fg = sure_fg.astype(np.uint8) # Finding unknown region unknown = cv2.subtract(sure_bg, sure_fg) # Marker labelling _, markers = cv2.connectedComponents(sure_fg) markers = markers + 1 markers[unknown == 255] = 0 # Apply watershed markers = cv2.watershed(image, markers) # Extract features features = [] for region in measure.regionprops(markers): if region.area >= 50: # Filter small regions features.append({ 'label': region.label, 'area': region.area, 'perimeter': region.perimeter, 'circularity': (4 * np.pi * region.area) / (region.perimeter ** 2) if region.perimeter > 0 else 0, 'mean_intensity': region.mean_intensity, 'centroid_x': region.centroid[1], 'centroid_y': region.centroid[0] }) # Create visualization timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S") vis_img = image.copy() # Draw contours contours = measure.find_contours(markers, 0.5) for contour in contours: coords = np.array(contour).astype(int) coords = coords[:, [1, 0]] # Swap x and y coordinates coords = coords.reshape((-1, 1, 2)) cv2.polylines(vis_img, [coords], True, (0, 255, 0), 2) # Add cell labels and measurements for feature in features: x = int(feature['centroid_x']) y = int(feature['centroid_y']) # White outline cv2.putText(vis_img, str(feature['label']), (x, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255,255,255), 2) # Red text cv2.putText(vis_img, str(feature['label']), (x, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0,0,255), 1) # Add timestamp cv2.putText(vis_img, f"Analyzed: {timestamp}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,255), 2) # Create plots plt.style.use('seaborn') fig, axes = plt.subplots(2, 2, figsize=(15, 12)) fig.suptitle('Cell Analysis Results', fontsize=16, y=0.95) df = pd.DataFrame(features) if not df.empty: # Distribution plots df['area'].hist(ax=axes[0,0], bins=20, color='skyblue', edgecolor='black') axes[0,0].set_title('Cell Size Distribution') axes[0,0].set_xlabel('Area') axes[0,0].set_ylabel('Count') df['circularity'].hist(ax=axes[0,1], bins=20, color='lightgreen', edgecolor='black') axes[0,1].set_title('Circularity Distribution') axes[0,1].set_xlabel('Circularity') axes[0,1].set_ylabel('Count') # Scatter plots axes[1,0].scatter(df['circularity'], df['mean_intensity'], alpha=0.6, c='purple') axes[1,0].set_title('Circularity vs Intensity') axes[1,0].set_xlabel('Circularity') axes[1,0].set_ylabel('Mean Intensity') # Box plot df.boxplot(column=['area', 'circularity'], ax=axes[1,1]) axes[1,1].set_title('Feature Distributions') else: for ax in axes.flat: ax.text(0.5, 0.5, 'No cells detected', ha='center', va='center') plt.tight_layout() # Apply color transformation transformed_image = apply_color_transformation(original_image, transform_type) return ( cv2.cvtColor(vis_img, cv2.COLOR_BGR2RGB), transformed_image, fig, df ) except Exception as e: print(f"Error processing image: {str(e)}") return None, None, None, None # Create Gradio interface with gr.Blocks(title="Advanced Cell Analysis Tool", theme=gr.themes.Soft()) as demo: gr.Markdown(""" # 🔬 Advanced Bioengineering Cell Analysis Tool ## Features - 🔍 Automated cell detection and measurement - 📊 Comprehensive statistical analysis - 🎨 Multiple visualization options - 📥 Downloadable results ## Author - **Muhammad Ibrahim Qasmi** - [LinkedIn](https://www.linkedin.com/in/muhammad-ibrahim-qasmi-9876a1297/) """) with gr.Row(): with gr.Column(scale=1): input_image = gr.Image( label="Upload Image", type="numpy" ) transform_type = gr.Dropdown( choices=["Original", "Grayscale", "Binary", "CLAHE"], value="Original", label="Image Transform" ) analyze_btn = gr.Button( "Analyze Image", variant="primary", size="lg" ) with gr.Column(scale=2): with gr.Tabs(): with gr.Tab("Analysis Results"): output_image = gr.Image( label="Detected Cells" ) gr.Markdown("*Green contours show detected cells, red numbers are cell IDs*") with gr.Tab("Image Transformations"): transformed_image = gr.Image( label="Transformed Image" ) gr.Markdown("*Select different transformations from the dropdown menu*") with gr.Tab("Statistics"): output_plot = gr.Plot( label="Statistical Analysis" ) gr.Markdown("*Hover over plots for detailed values*") with gr.Tab("Data"): output_table = gr.DataFrame( label="Cell Features" ) analyze_btn.click( fn=process_image, inputs=[input_image, transform_type], outputs=[output_image, transformed_image, output_plot, output_table] ) # Launch the demo if __name__ == "__main__": demo.launch()