\n A simple and clear notebook for identifying copy-move forgeries in biomedical images using semantic segmentation.\n
\n\n Build a segmentation model capable of locating duplicated regions within scientific figures.\n
\n\n\n The images vary in size and forged areas are small, demanding careful preprocessing and strong augmentations.\n
\n\n\n Provide a clean, beginner-friendly baseline for detecting manipulations with pixel-level precision.\n
\nThis section runs the full training loop for the U-Net forgery detection model. Key steps include:
\n\nhistory to track metrics over epochs.best_model_wts) based on validation Dice score.EarlyStopping to halt training if validation performance does not improve.train_one_epoch and validate using validate.ReduceLROnPlateau scheduler.history into a DataFrame and visualize:\n This ensures structured monitoring, automatic checkpointing, and performance evaluation for optimal model training.
\n","metadata":{}},{"cell_type":"code","source":"history = defaultdict(list)\nbest_dice = 0.0\nbest_model_wts = copy.deepcopy(model.state_dict())\n\nearly_stopping = EarlyStopping(\n patience=CONFIG['early_stopping_patience'],\n mode='max', \n delta=0.001\n)\n\ntraining_start_time = time.time()\n\nprint(f\"Starting training for {CONFIG['epochs']} epochs...\")\nprint(f\"Training samples: {len(train_dataset)}\")\nprint(f\"Validation samples: {len(val_dataset)}\")\nprint(f\"Device: {device}\")\nprint(\"=\"*80)\nprint(\"\\n\")\n\n\nfor epoch in range(1, CONFIG['epochs'] + 1):\n epoch_start_time = time.time()\n \n print(f\"\\n{'='*80}\")\n print(f\"EPOCH {epoch}/{CONFIG['epochs']}\")\n print(f\"{'='*80}\")\n \n train_metrics = train_one_epoch(\n model=model,\n dataloader=train_loader,\n criterion=criterion,\n optimizer=optimizer,\n device=device,\n epoch=epoch\n )\n \n val_metrics = validate(\n model=model,\n dataloader=val_loader,\n criterion=criterion,\n device=device,\n epoch=epoch\n )\n \n scheduler.step(val_metrics['loss'])\n \n current_lr = optimizer.param_groups[0]['lr']\n \n epoch_time = time.time() - epoch_start_time\n \n print(f\"\\n{'='*80}\")\n print(f\"EPOCH {epoch} SUMMARY\")\n print(f\"{'='*80}\")\n print(f\"Time: {epoch_time:.2f}s | LR: {current_lr:.2e}\")\n print(f\"\\nTrain Metrics:\")\n print(f\" Loss: {train_metrics['loss']:.4f} | BCE: {train_metrics['bce_loss']:.4f} | Dice Loss: {train_metrics['dice_loss']:.4f}\")\n print(f\" Dice Score: {train_metrics['dice_score']:.4f} | IoU: {train_metrics['iou']:.4f}\")\n print(f\"\\nValidation Metrics:\")\n print(f\" Loss: {val_metrics['loss']:.4f} | BCE: {val_metrics['bce_loss']:.4f} | Dice Loss: {val_metrics['dice_loss']:.4f}\")\n print(f\" Dice Score: {val_metrics['dice_score']:.4f} | IoU: {val_metrics['iou']:.4f}\")\n \n history['epoch'].append(epoch)\n history['lr'].append(current_lr)\n history['train_loss'].append(train_metrics['loss'])\n history['train_dice'].append(train_metrics['dice_score'])\n history['train_iou'].append(train_metrics['iou'])\n history['val_loss'].append(val_metrics['loss'])\n history['val_dice'].append(val_metrics['dice_score'])\n history['val_iou'].append(val_metrics['iou'])\n \n if val_metrics['dice_score'] > best_dice:\n best_dice = val_metrics['dice_score']\n best_model_wts = copy.deepcopy(model.state_dict())\n \n checkpoint_path = os.path.join(\n CONFIG['checkpoint_dir'],\n f'best_model_epoch{epoch}_dice{best_dice:.4f}.pth'\n )\n torch.save({\n 'epoch': epoch,\n 'model_state_dict': model.state_dict(),\n 'optimizer_state_dict': optimizer.state_dict(),\n 'scheduler_state_dict': scheduler.state_dict(),\n 'best_dice': best_dice,\n 'val_metrics': val_metrics,\n }, checkpoint_path)\n \n print(f\"\\n🎯 New best model saved! Dice: {best_dice:.4f}\")\n print(f\" Saved to: {checkpoint_path}\")\n \n if early_stopping(val_metrics['dice_score']):\n print(f\"\\n Early stopping triggered after {epoch} epochs\")\n print(f\" No improvement for {CONFIG['early_stopping_patience']} epochs\")\n break\n \n print(f\"{'='*80}\\n\")\n\n\n\ntraining_time = time.time() - training_start_time\n\nprint(\"\\n\")\nprint(\"=\"*80)\nprint(\"TRAINING COMPLETED!\")\nprint(\"=\"*80)\nprint(f\"Total training time: {training_time/60:.2f} minutes\")\nprint(f\"Best validation Dice score: {best_dice:.4f}\")\nprint(f\"Total epochs trained: {len(history['epoch'])}\")\nprint(\"=\"*80)\nprint(\"\\n\")\n\n\nmodel.load_state_dict(best_model_wts)\nprint(\"✓ Best model weights loaded into model\")\nprint(\"\\n\")\n\n\nhistory_df = pd.DataFrame(history)\n\nfig, axes = plt.subplots(2, 3, figsize=(20, 12))\nfig.suptitle('Training History', fontsize=16, fontweight='bold')\n\naxes[0, 0].plot(history_df['epoch'], history_df['train_loss'], \n label='Train Loss', marker='o', linewidth=2)\naxes[0, 0].plot(history_df['epoch'], history_df['val_loss'], \n label='Val Loss', marker='s', linewidth=2)\naxes[0, 0].set_xlabel('Epoch')\naxes[0, 0].set_ylabel('Loss')\naxes[0, 0].set_title('Loss Curve')\naxes[0, 0].legend()\naxes[0, 0].grid(True, alpha=0.3)\n\naxes[0, 1].plot(history_df['epoch'], history_df['train_dice'], \n label='Train Dice', marker='o', linewidth=2, color='green')\naxes[0, 1].plot(history_df['epoch'], history_df['val_dice'], \n label='Val Dice', marker='s', linewidth=2, color='orange')\naxes[0, 1].set_xlabel('Epoch')\naxes[0, 1].set_ylabel('Dice Score')\naxes[0, 1].set_title('Dice Score Curve')\naxes[0, 1].legend()\naxes[0, 1].grid(True, alpha=0.3)\n\naxes[0, 2].plot(history_df['epoch'], history_df['train_iou'], \n label='Train IoU', marker='o', linewidth=2, color='purple')\naxes[0, 2].plot(history_df['epoch'], history_df['val_iou'], \n label='Val IoU', marker='s', linewidth=2, color='brown')\naxes[0, 2].set_xlabel('Epoch')\naxes[0, 2].set_ylabel('IoU Score')\naxes[0, 2].set_title('IoU Score Curve')\naxes[0, 2].legend()\naxes[0, 2].grid(True, alpha=0.3)\n\naxes[1, 0].plot(history_df['epoch'], history_df['lr'], \n marker='o', linewidth=2, color='red')\naxes[1, 0].set_xlabel('Epoch')\naxes[1, 0].set_ylabel('Learning Rate')\naxes[1, 0].set_title('Learning Rate Schedule')\naxes[1, 0].set_yscale('log')\naxes[1, 0].grid(True, alpha=0.3)\n\n\naxes[1, 1].scatter(history_df['train_loss'], history_df['val_loss'], \n c=history_df['epoch'], cmap='viridis', s=100, alpha=0.6)\naxes[1, 1].plot([history_df['train_loss'].min(), history_df['train_loss'].max()],\n [history_df['train_loss'].min(), history_df['train_loss'].max()],\n 'r--', linewidth=2, label='Perfect fit')\naxes[1, 1].set_xlabel('Train Loss')\naxes[1, 1].set_ylabel('Val Loss')\naxes[1, 1].set_title('Train vs Val Loss')\naxes[1, 1].legend()\naxes[1, 1].grid(True, alpha=0.3)\n\naxes[1, 2].scatter(history_df['train_dice'], history_df['val_dice'], \n c=history_df['epoch'], cmap='viridis', s=100, alpha=0.6)\naxes[1, 2].plot([history_df['train_dice'].min(), history_df['train_dice'].max()],\n [history_df['train_dice'].min(), history_df['train_dice'].max()],\n 'r--', linewidth=2, label='Perfect fit')\naxes[1, 2].set_xlabel('Train Dice')\naxes[1, 2].set_ylabel('Val Dice')\naxes[1, 2].set_title('Train vs Val Dice')\naxes[1, 2].legend()\naxes[1, 2].grid(True, alpha=0.3)\n\nplt.tight_layout()\nplt.show()\n\nprint(\"✓ Training curves plotted\")\nprint(\"\\n\")\n\n\n\nbest_epoch_idx = history_df['val_dice'].idxmax()\nbest_epoch_data = history_df.iloc[best_epoch_idx]\n\nprint(f\"\\nBest Epoch: {int(best_epoch_data['epoch'])}\")\nprint(f\"\\nMetrics at Best Epoch:\")\nprint(f\" Train Loss: {best_epoch_data['train_loss']:.4f}\")\nprint(f\" Val Loss: {best_epoch_data['val_loss']:.4f}\")\nprint(f\" Train Dice: {best_epoch_data['train_dice']:.4f}\")\nprint(f\" Val Dice: {best_epoch_data['val_dice']:.4f}\")\nprint(f\" Train IoU: {best_epoch_data['train_iou']:.4f}\")\nprint(f\" Val IoU: {best_epoch_data['val_iou']:.4f}\")\nprint(f\" Learning Rate: {best_epoch_data['lr']:.2e}\")\n\n# Check for overfitting\ndice_gap = best_epoch_data['train_dice'] - best_epoch_data['val_dice']\nloss_gap = best_epoch_data['val_loss'] - best_epoch_data['train_loss']\n\nprint(f\"\\nOverfitting Analysis:\")\nprint(f\" Dice gap (Train - Val): {dice_gap:.4f}\")\nprint(f\" Loss gap (Val - Train): {loss_gap:.4f}\")\n\nif dice_gap > 0.1:\n print(\" ⚠️ Warning: Significant overfitting detected (Dice gap > 0.1)\")\nelif dice_gap > 0.05:\n print(\" ⚡ Moderate overfitting (Dice gap > 0.05)\")\nelse:\n print(\" ✓ Good generalization (Dice gap < 0.05)\")\n\nprint(\"\\n\")\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T12:58:02.700540Z","iopub.execute_input":"2025-10-26T12:58:02.700824Z","iopub.status.idle":"2025-10-26T13:02:59.772313Z","shell.execute_reply.started":"2025-10-26T12:58:02.700803Z","shell.execute_reply":"2025-10-26T13:02:59.771462Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Validation","metadata":{}},{"cell_type":"code","source":"def predict_batch(model, images, device, threshold=0.5):\n model.eval()\n with torch.no_grad():\n outputs = model(images.to(device))\n predictions = torch.sigmoid(outputs)\n binary_predictions = (predictions > threshold).float()\n return predictions, binary_predictions\n\ndef visualize_predictions(model, dataloader, device, n_samples=6, threshold=0.5):\n \n model.eval()\n \n fig, axes = plt.subplots(n_samples, 4, figsize=(20, 5*n_samples))\n fig.suptitle(f'Validation Predictions (Threshold: {threshold})', \n fontsize=16, fontweight='bold')\n \n batch = next(iter(dataloader))\n images = batch['image'][:n_samples].to(device)\n masks = batch['mask'][:n_samples]\n labels = batch['label'][:n_samples]\n \n with torch.no_grad():\n outputs = model(images)\n predictions = torch.sigmoid(outputs)\n binary_preds = (predictions > threshold).float()\n \n def denormalize(img):\n mean = torch.tensor([0.485, 0.456, 0.406]).view(3, 1, 1).to(img.device)\n std = torch.tensor([0.229, 0.224, 0.225]).view(3, 1, 1).to(img.device)\n return torch.clamp(img * std + mean, 0, 1)\n \n for i in range(n_samples):\n img = denormalize(images[i]).cpu().permute(1, 2, 0).numpy()\n axes[i, 0].imshow(img)\n axes[i, 0].set_title(f'Image (Label: {labels[i].item():.0f})')\n axes[i, 0].axis('off')\n \n gt_mask = masks[i, 0].cpu().numpy()\n axes[i, 1].imshow(gt_mask, cmap='hot', vmin=0, vmax=1)\n axes[i, 1].set_title('Ground Truth Mask')\n axes[i, 1].axis('off')\n \n pred_prob = predictions[i, 0].cpu().numpy()\n axes[i, 2].imshow(pred_prob, cmap='hot', vmin=0, vmax=1)\n axes[i, 2].set_title(f'Predicted (Prob)\\nMax: {pred_prob.max():.3f}')\n axes[i, 2].axis('off')\n \n pred_binary = binary_preds[i, 0].cpu().numpy()\n axes[i, 3].imshow(pred_binary, cmap='hot', vmin=0, vmax=1)\n \n # Calculate metrics for this sample\n dice = dice_coefficient(\n outputs[i:i+1], \n masks[i:i+1].to(device), \n threshold=threshold\n )\n axes[i, 3].set_title(f'Binary Prediction\\nDice: {dice:.3f}')\n axes[i, 3].axis('off')\n \n plt.tight_layout()\n plt.show()\n\n# Visualize predictions\nprint(\"\\nVisualizing predictions on validation set...\")\nvisualize_predictions(\n model=model,\n dataloader=val_loader,\n device=device,\n n_samples=6,\n threshold=0.5\n)\n\nprint(\"✓ Validation predictions visualized\")\nprint(\"\\n\")\n\n\nprint(\"=\"*80)\nprint(\"STEP 7.1: OPTIMIZING PREDICTION THRESHOLD\")\nprint(\"=\"*80)\n\ndef evaluate_threshold(model, dataloader, device, threshold):\n model.eval()\n dice_scores = []\n iou_scores = []\n \n with torch.no_grad():\n for batch in dataloader:\n images = batch['image'].to(device)\n masks = batch['mask'].to(device)\n \n outputs = model(images)\n \n dice = dice_coefficient(outputs, masks, threshold=threshold)\n iou = iou_score(outputs, masks, threshold=threshold)\n \n dice_scores.append(dice)\n iou_scores.append(iou)\n \n return np.mean(dice_scores), np.mean(iou_scores)\n\nprint(\"Testing different thresholds...\")\nthresholds = [0.3, 0.7]\nthreshold_results = []\n\nfor thresh in tqdm(thresholds, desc=\"Testing thresholds\"):\n dice, iou = evaluate_threshold(model, val_loader, device, thresh)\n threshold_results.append({\n 'threshold': thresh,\n 'dice': dice,\n 'iou': iou\n })\n print(f\" Threshold {thresh:.2f}: Dice={dice:.4f}, IoU={iou:.4f}\")\n\nthreshold_df = pd.DataFrame(threshold_results)\nbest_threshold_idx = threshold_df['dice'].idxmax()\nbest_threshold = threshold_df.iloc[best_threshold_idx]['threshold']\nbest_dice = threshold_df.iloc[best_threshold_idx]['dice']\n\nprint(f\"\\n✓ Best threshold: {best_threshold}\")\nprint(f\" Dice score: {best_dice:.4f}\")\n\nfig, axes = plt.subplots(1, 2, figsize=(15, 5))\nfig.suptitle('Threshold Optimization', fontsize=16, fontweight='bold')\n\naxes[0].plot(threshold_df['threshold'], threshold_df['dice'], \n marker='o', linewidth=2, markersize=8, color='green')\naxes[0].axvline(best_threshold, color='red', linestyle='--', \n label=f'Best: {best_threshold}')\naxes[0].set_xlabel('Threshold')\naxes[0].set_ylabel('Dice Score')\naxes[0].set_title('Dice Score vs Threshold')\naxes[0].legend()\naxes[0].grid(True, alpha=0.3)\n\naxes[1].plot(threshold_df['threshold'], threshold_df['iou'], \n marker='s', linewidth=2, markersize=8, color='purple')\naxes[1].axvline(best_threshold, color='red', linestyle='--', \n label=f'Best: {best_threshold}')\naxes[1].set_xlabel('Threshold')\naxes[1].set_ylabel('IoU Score')\naxes[1].set_title('IoU Score vs Threshold')\naxes[1].legend()\naxes[1].grid(True, alpha=0.3)\n\nplt.tight_layout()\nplt.show()\n\nprint(\"\\n\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T13:04:15.944040Z","iopub.execute_input":"2025-10-26T13:04:15.944369Z","iopub.status.idle":"2025-10-26T13:05:33.978544Z","shell.execute_reply.started":"2025-10-26T13:04:15.944345Z","shell.execute_reply":"2025-10-26T13:05:33.977437Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# POST-PROCESSING","metadata":{}},{"cell_type":"code","source":"def remove_small_regions(mask, min_size=100):\n\n from scipy import ndimage\n \n labeled_mask, num_features = ndimage.label(mask)\n \n for region_label in range(1, num_features + 1):\n region = (labeled_mask == region_label)\n if region.sum() < min_size:\n mask[region] = 0\n \n return mask\n\ndef apply_morphology(mask, kernel_size=3):\n \n kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (kernel_size, kernel_size))\n \n # Opening: remove small noise\n mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)\n \n # Closing: fill small holes\n mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel)\n \n return mask\n\ndef post_process_mask(mask, threshold=0.5, min_size=100, morphology_kernel=3):\n\n # Binarize\n binary_mask = (mask > threshold).astype(np.uint8)\n \n # Apply morphology\n if morphology_kernel > 0:\n binary_mask = apply_morphology(binary_mask, morphology_kernel)\n \n # Remove small regions\n if min_size > 0:\n binary_mask = remove_small_regions(binary_mask, min_size)\n \n return binary_mask\n\nprint(\"✓ Post-processing functions created:\")\nprint(\" - remove_small_regions(): Remove small isolated regions\")\nprint(\" - apply_morphology(): Morphological opening/closing\")\nprint(\" - post_process_mask(): Complete pipeline\")\nprint(\"\\n\")\n\n\nprint(\"=\"*80)\nprint(\"STEP 8.1: RUN LENGTH ENCODING (RLE) FUNCTIONS\")\nprint(\"=\"*80)\n\ndef rle_encode(mask):\n \n pixels = mask.T.flatten()\n \n pixels = np.concatenate([[0], pixels, [0]])\n \n runs = np.where(pixels[1:] != pixels[:-1])[0] + 1\n runs[1::2] -= runs[::2]\n \n return ' '.join(str(x) for x in runs)\n\ndef rle_decode(rle_string, shape):\n if rle_string == \"authentic\":\n return np.zeros(shape, dtype=np.uint8)\n \n runs = np.array([int(x) for x in rle_string.split()])\n starts = runs[::2]\n lengths = runs[1::2]\n \n mask = np.zeros(shape[0] * shape[1], dtype=np.uint8)\n for start, length in zip(starts, lengths):\n mask[start:start+length] = 1\n\n mask = mask.reshape(shape[::-1]).T\n \n return mask\n\nprint(\"✓ RLE encoding functions created:\")\nprint(\" - rle_encode(): Convert mask to RLE string\")\nprint(\" - rle_decode(): Convert RLE string back to mask\")\n\nprint(\"\\nTesting RLE encoding...\")\ntest_mask = np.zeros((10, 10), dtype=np.uint8)\ntest_mask[2:5, 3:7] = 1\ntest_rle = rle_encode(test_mask)\ntest_decoded = rle_decode(test_rle, test_mask.shape)\nprint(f\" Original mask sum: {test_mask.sum()}\")\nprint(f\" RLE string: {test_rle}\")\nprint(f\" Decoded mask sum: {test_decoded.sum()}\")\nprint(f\" Encoding correct: {np.array_equal(test_mask, test_decoded)}\")\nprint(\"\\n\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T13:05:33.980147Z","iopub.execute_input":"2025-10-26T13:05:33.980452Z","iopub.status.idle":"2025-10-26T13:05:33.995902Z","shell.execute_reply.started":"2025-10-26T13:05:33.980424Z","shell.execute_reply":"2025-10-26T13:05:33.995038Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# GENERATE TEST PREDICTIONS","metadata":{}},{"cell_type":"code","source":"import os\nimport numpy as np\nimport pandas as pd\nfrom PIL import Image\nfrom tqdm import tqdm\nimport torch\nimport cv2\n\n# -----------------------\n# CONFIGURATION\n# -----------------------\nBASE_PATH = \"/kaggle/input/recodai-luc-scientific-image-forgery-detection\"\nTEST_IMAGES_PATH = os.path.join(BASE_PATH, \"test_images\")\nSAMPLE_SUBMISSION_PATH = os.path.join(BASE_PATH, \"sample_submission.csv\")\n\nPREDICTION_CONFIG = {\n 'threshold': best_threshold, # à définir selon ton entraînement\n 'min_region_size': 50,\n 'morphology_kernel': 3,\n 'min_forgery_pixels': 100,\n}\n\n# -----------------------\n# FONCTION DE PREDICTION\n# -----------------------\ndef predict_test_image(model, image_path, device, config, target_size=(512, 512)):\n model.eval()\n \n image = Image.open(image_path).convert('RGB')\n original_size = image.size\n image = image.resize(target_size, Image.BILINEAR)\n image_array = np.array(image, dtype=np.float32) / 255.0\n\n transformed = val_transform(image=image_array, mask=np.zeros(target_size))\n image_tensor = transformed['image'].unsqueeze(0).to(device)\n \n with torch.no_grad():\n output = model(image_tensor)\n prediction = torch.sigmoid(output)[0, 0].cpu().numpy()\n \n binary_mask = post_process_mask(\n prediction,\n threshold=config['threshold'],\n min_size=config['min_region_size'],\n morphology_kernel=config['morphology_kernel']\n )\n \n binary_mask = cv2.resize(\n binary_mask.astype(np.float32),\n original_size,\n interpolation=cv2.INTER_NEAREST\n ).astype(np.uint8)\n\n total_forged_pixels = binary_mask.sum()\n \n if total_forged_pixels < config['min_forgery_pixels']:\n return \"authentic\"\n else:\n rle = rle_encode(binary_mask)\n if isinstance(rle, (list, np.ndarray)):\n rle = \"[\" + \" \".join(map(str, rle)) + \"]\"\n elif not (rle.startswith(\"[\") and rle.endswith(\"]\")):\n rle = \"[\" + rle.strip() + \"]\"\n return rle\n\n# -----------------------\n# GENERER LES PREDICTIONS POUR LES IMAGES VISIBLES\n# -----------------------\ntest_images = sorted([f for f in os.listdir(TEST_IMAGES_PATH) if f.endswith('.png')])\npredictions = {}\n\nfor img_name in tqdm(test_images, desc=\"Processing test images\"):\n case_id = img_name.replace('.png', '')\n img_path = os.path.join(TEST_IMAGES_PATH, img_name)\n \n rle_or_authentic = predict_test_image(model, img_path, device, PREDICTION_CONFIG)\n predictions[case_id] = rle_or_authentic\n\n# -----------------------\n# UTILISER LE SAMPLE SUBMISSION POUR TOUTES LES LIGNES\n# -----------------------\nsample_submission = pd.read_csv(SAMPLE_SUBMISSION_PATH)\nsubmission_data = []\n\nfor case_id in sample_submission['case_id']:\n case_id_str = str(case_id)\n if case_id_str in predictions:\n annotation = predictions[case_id_str]\n else:\n # Pour les images invisibles du test privé, mettre \"authentic\" par défaut\n annotation = \"authentic\"\n submission_data.append({'case_id': case_id, 'annotation': annotation})\n\nsubmission_df = pd.DataFrame(submission_data)\n\n# -----------------------\n# CHECK FINAL\n# -----------------------\nassert submission_df.shape[1] == 2\nassert submission_df.columns.tolist() == ['case_id', 'annotation']\nassert submission_df['case_id'].apply(lambda x: isinstance(x, (int, np.integer))).all()\nassert submission_df['annotation'].apply(lambda x: x==\"authentic\" or (x.startswith(\"[\") and x.endswith(\"]\"))).all()\n\n# -----------------------\n# SAVE CSV\n# -----------------------\nsubmission_df.to_csv('submission.csv', index=False)\nprint(\"✅ Submission file created successfully!\")\nprint(submission_df.head())\nprint(\"Number of rows:\", len(submission_df))\n\n# Optionnel : statistiques\nauthentic_count = (submission_df['annotation'] == 'authentic').sum()\nforged_count = len(submission_df) - authentic_count\nprint(f\"Authentic: {authentic_count}, Forged: {forged_count}\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-10-26T13:41:00.159705Z","iopub.execute_input":"2025-10-26T13:41:00.159989Z","iopub.status.idle":"2025-10-26T13:41:00.265651Z","shell.execute_reply.started":"2025-10-26T13:41:00.159969Z","shell.execute_reply":"2025-10-26T13:41:00.264808Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Conclusion","metadata":{}},{"cell_type":"markdown","source":"\n Scientific image forgery (copy-move) threatens research integrity by misleading scientists and wasting resources.\n The goal: build an automated model to detect and segment forged regions in biomedical images.\n
\n\n\n A U-Net model with a ResNet34 backbone trained on 5,128 images\n (2,751 forged / 2,377 authentic). Used Dice + BCE loss to handle imbalance and achieved strong Dice performance on validation.\n
\n\n\n Helps journals and researchers detect fraud early and restore trust in scientific imagery.\n
\n