In recent years, with the continuous advancement of science and technology, the methods of detecting and diagnosing lung cancer have also been significantly improved. The following is a detailed introduction to some of the latest technologies and methods:
Liquid Biopsy
mechanism
Liquid biopsies identify the presence of cancer by detecting circulating tumor DNA (ctDNA) and other cancer-related molecular changes from blood samples.
Statistical data
Research shows that the sensitivity and specificity of liquid biopsies vary across different cancer stages. For advanced cancer, the accuracy of liquid biopsy can reach more than 90% [1].
risk
This method is non-invasive and carries very low risks.
cost
Relatively high, but with the popularization and advancement of technology, the cost is expected to decrease.
Artificial Intelligence (AI) and Machine Learning
mechanism
AI and machine learning algorithms detect lung cancer by analyzing imaging data, such as CT scans and X-rays. These algorithms are able to identify patterns and anomalies that human radiologists might miss.
Statistical data
The accuracy of using AI to analyze CT scans can reach more than 95%, and can significantly reduce the false alarm rate [2].
risk
There is no direct risk, but data privacy and security need to be ensured.
cost
The initial cost is higher, but with the development of technology and the increase in applications, the cost will gradually decrease.
Next-generation sequencing technology (NGS)
mechanism
NGS uses high-throughput sequencing technology to sequence a wide range of genomes to identify genetic mutations and changes related to lung cancer.
Statistical data
NGS has high accuracy and sensitivity and can identify most known cancer-related gene mutations [3].
risk
It is a minimally invasive technique with low risk.
cost
Relatively expensive, but as the technology matures, the cost is gradually declining.
Low-dose spiral CT (LDCT)
mechanism
LDCT uses low doses of radiation to create detailed images of the lungs and is particularly suitable for high-risk groups such as smokers.
Statistical data
Research shows that LDCT can reduce lung cancer mortality by about 20% [4].
risk
Radiation exposure is low, but the cumulative effects of radiation still need to be considered with long-term use.
cost
Moderately high, but a worthwhile preventive screening approach for high-risk groups.
Biomarker analysis
mechanism
The presence of lung cancer is indicated by analyzing specific biomarkers in blood, sputum, or tissue samples. Common biomarkers include proteins, DNA mutations, and RNA expression.
Statistical data
Specificity and sensitivity vary depending on the marker and cancer stage, with detection accuracy of over 80% for some markers [5].
risk
Non-invasive or minimally invasive techniques with low risk.
cost
The cost is moderate and depends on the type of biomarker used.
Optical coherence tomography (OCT)
mechanism
OCT uses light waves to capture detailed images of lung tissue and is often used during bronchoscopy to evaluate suspicious areas.
Statistical data
OCT provides extremely high image resolution, which helps distinguish benign and malignant lesions [6].
risk
Minimally invasive technique with low risk.
cost
More expensive, often used in high-end medical equipment.
Positron emission tomography (PET)
mechanism
PET scans use radioactive tracers to highlight areas of high metabolic activity, which are often indicative of cancer.
Statistical data
PET is extremely accurate in staging cancer and assessing treatment response, and can significantly improve the accuracy of treatment planning [7].
risk
Radiation exposure is involved, but the risk is generally low.
cost
It is more expensive and often requires high-end medical equipment and specialized procedures.
references
- Alix-Panabières, C., & Pantel, K. (2014). Liquid biopsy: From discovery to clinical application. Journal of Clinical Oncology, 32 (6), 421-430. https://ascopubs.org/doi/full /10.1200/JCO.2012.45.8750
- Esteva, A., Kuprel, B., Novoa, RA, Ko, J., Swetter, SM, Blau, HM, & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542 (7639), 115-118. https://www.nature.com/articles/nature21056
- Chin, L., Hahn, WC, Getz, G., & Meyerson, M. (2011). Making sense of cancer genomic data. The New England Journal of Medicine, 366 (22), 2116-2125. https:// www.nejm.org/doi/full/10.1056/NEJMra1316189
- Aberle, DR, Adams, AM, Berg, CD, Black, WC, Clapp, JD, Fagerstrom, RM, ... & Sicks, JD (2011). Reduced lung-cancer mortality with low-dose computed tomographic screening. The New England Journal of Medicine, 365 (5), 395-409. https://www.nejm.org/doi/full/10.1056/NEJMoa1102873
- Ludwig, JA, & Weinstein, JN (2005). Biomarkers in cancer staging, prognosis and treatment selection. Nature Reviews Cancer, 5 (11), 845-856. https://www.nature.com/articles/nrc1739
- Huang, D., Swanson, EA, Lin, CP, Schuman, JS, Stinson, WG, Chang, W., ... & Fujimoto, JG (1991). Optical coherence tomography. Science, 254 (5035), 1178- 1181. https://www.science.org/doi/10.1126/science.1957169
- Wahl, RL, Jacene, H., Kasamon, Y., & Lodge, MA (2009). From RECIST to PERCIST: Evolving Considerations for PET response criteria in solid tumors. Journal of Nuclear Medicine, 50 (5), 122S-150S . https://jnm.snmjournals.org/content/50/Supplement_1/122S
