To explore the role of image processing techniques in detecting lung cancer from medical imaging such as CT or X-ray scans.
To analyze the integration of liquid biopsy data (e.g., ctDNA, CTCs) with imaging results for enhanced diagnostic accuracy.
To develop an AI-assisted system that supports early detection and classification of lung cancer.
To evaluate the accuracy, sensitivity, and specificity of combined diagnostic methods.
To propose a computational model or framework that fuses image and molecular data for robust lung cancer detection.
Conduct a literature review on lung cancer detection using medical imaging (CT, X-ray) and liquid biopsy techniques.
Collect or access publicly available medical image datasets (e.g., LIDC-IDRI) and sample genomic/biomarker datasets if available.
Preprocess images using techniques like noise removal, normalization, and segmentation to extract regions of interest (ROIs).
Implement image processing and machine learning models (e.g., CNNs, SVM) to classify cancerous and non-cancerous regions.
Integrate molecular biomarkers (from liquid biopsy literature or synthetic data) to enhance detection accuracy.
Evaluate the system using metrics like accuracy, precision, recall, F1-score, and ROC curves.
Prepare a detailed report outlining the technical approach, dataset used, testing results, benefits of multimodal diagnostics, and future scope for clinical application.
