Advanced U-Net Architectures with CNN Backbones for Automated Lung Cancer Detection and Segmentation in Chest CT Images

2025-07-14

AI Summary

To address the clinical need for improved accuracy in automatic lung cancer detection and segmentation from chest CT images, this study proposes a multi-model comparative framework integrating U-Net with advanced CNN backbones—ResNet50, VGG16, and Xception. The method innovatively combines CLAHE-based preprocessing, U-Net-based segmentation, and hybrid classification leveraging traditional machine learning (SVM, Random Forest, Gradient Boosting) alongside CNN features. A rigorous five-fold cross-validation protocol ensures robust performance evaluation. Experimental results demonstrate that U-Net-ResNet50 achieves a Dice coefficient of 0.9495 for malignant region segmentation, while U-Net-VGG16 attains 0.9532 for benign regions. The Xception-based CNN classifier yields 99.1% accuracy and a 99.42% F1-score. Collectively, the framework significantly outperforms existing approaches, offering an efficient and robust technical foundation for early, precise lung cancer diagnosis.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Natural Language Processing: Text Classification & Sentiment Analysis

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This study investigates the effectiveness of U-Net architectures integrated with various convolutional neural network (CNN) backbones for automated lung cancer detection and segmentation in chest CT images, addressing the critical need for accurate diagnostic tools in clinical settings. A balanced dataset of 832 chest CT images (416 cancerous and 416 non-cancerous) was preprocessed using Contrast Limited Adaptive Histogram Equalization (CLAHE) and resized to 128x128 pixels. U-Net models were developed with three CNN backbones: ResNet50, VGG16, and Xception, to segment lung regions. After segmentation, CNN-based classifiers and hybrid models combining CNN feature extraction with traditional machine learning classifiers (Support Vector Machine, Random Forest, and Gradient Boosting) were evaluated using 5-fold cross-validation. Metrics included accuracy, precision, recall, F1-score, Dice coefficient, and ROC-AUC. U-Net with ResNet50 achieved the best performance for cancerous lungs (Dice: 0.9495, Accuracy: 0.9735), while U-Net with VGG16 performed best for non-cancerous segmentation (Dice: 0.9532, Accuracy: 0.9513). For classification, the CNN model using U-Net with Xception achieved 99.1 percent accuracy, 99.74 percent recall, and 99.42 percent F1-score. The hybrid CNN-SVM-Xception model achieved 96.7 percent accuracy and 97.88 percent F1-score. Compared to prior methods, our framework consistently outperformed existing models. In conclusion, combining U-Net with advanced CNN backbones provides a powerful method for both segmentation and classification of lung cancer in CT scans, supporting early diagnosis and clinical decision-making.

Problem

• Automated lung cancer detection in chest CT images
• Segmentation of lung regions using U-Net and CNN backbones
• Improving diagnostic accuracy with hybrid CNN models

Innovation

• U-Net with CNN backbones for segmentation
• Hybrid CNN-SVM models for classification
• CLAHE preprocessing for image enhancement