Integrative Approaches in Lung Cancer Diagnosis: Bridging Molecular Biomarkers and AI Driven Imaging.
Authors
Affiliations (6)
Affiliations (6)
- Department of Pharmaceutical Chemistry, ISF College of Pharmacy, Moga, Punjab-142001, India.
- Faculty of Pharmaceutical Sciences, PCTE Group of Institutes, Baddowal, Ludhiana Punjab-142021, India.
- Department of Pharmaceutical Chemistry, School of Pharmaceutical Sciences, RIMT University, Mandi Gobindgarh, Punjab-147301, India.
- Department of Pharmaceutics, ISF College of Pharmacy and Research, Moga, Punjab-142001, India.
- Department of Pharmaceutical Sciences and Natural Products, School of Health Sciences, Central University of Punjab, VPO-Ghudda, Bathinda, Punjab-151401, India.
- Department of Pharmaceutical Chemistry & Analysis, ISF College of Pharmacy, Moga, Punjab-142001, India.
Abstract
Though critical, traditional diagnostic approaches such as X-ray, CT scans, bronchoscopy and tissue biopsy don't reliably detect lung cancer at early stages, paradigm shift has occurred recently with lung cancer diagnostics based on recent advances of molecular biology and computational technologies. Present review analyses incorporation of molecular biomarkers- EGFR, ALK, KRAS, BRAF, MET and PD-L1 expression into routine diagnostics facilitating precise subtyping and selection of appropriate therapy. Advanced technologies like liquid biopsy, circulating tumor DNA provide noninvasive alternatives to characterize tumor and monitor disease in real-time. Next generation sequencing and multiomic approaches like genomics, transcriptomics, proteomics supply detailed molecular profile of tumor microenvironment. Same tools help to transform ability to use medical imaging to detect early lesions on low dose CT scans allowing risk stratification through radiomics and pattern recognition with AI, specifically machine learning and deep learning. Recently, AI powered computer aided detection systems and predictive models are forming clinical decision support while creating ground for personalized diagnostics. Potential of AI and biomarker data integration is transformative, they possess many challenges on data standardization, interpretability, clinical validation, and ethical matters. Digital innovation and biological insights are still converging, though, offering faster, more precise, more patient specific lung cancer diagnosis.