Advances in Early Lung Cancer Detection: A Systematic Review

Abstract

Thediagnosisofmostlungcancerpatientshappen onlywhenitisadvanced,wherethecurativetherapyisnotany moreachoice.Lungcancerhasmoredeathratesthanother prevalentcancerslikeprostate,breastandskinaroundtheglobe.Itsmortalityrate can be reduced to a certain extend by the earlier detection.It is also very important to know the different types of detection methods and its effectiveness. This review centers upon the likelihood of diagnosing lung cancer at itsearlier stage by utilizing different biomarkers like protein biomarkers and exhaled breath analysis and imaging procedures like CT scan imaging.

Introduction

Cancer is characterized by uncontrolled cell growth, with lung cancer being the leading cause of cancer deaths worldwide. Most lung cancer cases (80-90%) are linked to cigarette smoking, though other factors like passive smoking, occupational exposures, and radon gas also contribute. Despite advances, lung cancer survival rates remain low (about 18% five-year survival), partly due to late diagnosis.

Early detection significantly improves outcomes. Current diagnostic methods include chest X-rays, CT scans, MRI, PET, sputum cytology, and breath analysis, each with limitations such as radiation exposure, high cost, false negatives, or invasiveness.

Recent advances focus on non-invasive, sensitive, and cost-effective techniques. Protein biomarkers (e.g., CEA, CYFRA 21-1, NSE) in blood or urine aid diagnosis but often require combinations for accuracy. Exhaled breath analysis of volatile organic compounds (VOCs) offers a promising non-invasive approach using sensor arrays and pattern recognition (e-Nose systems) to differentiate cancer patients from healthy individuals.

CT scan imaging remains a reliable tool but is enhanced by computer-aided diagnosis techniques like image processing (filtering, segmentation) and machine learning classifiers (e.g., Support Vector Machines) to improve tumor detection and classification accuracy.

Overall, integrating biomarker analysis, breath testing, and advanced imaging with AI offers promising pathways for earlier, more accurate lung cancer diagnosis.

Conclusion

The quick invasion and short survival time of the malignant tumours causes the lung cancer to be the mostly deadly of all types of cancers. A significant reduction in lung cancer disease and death rate is possible by the early detection. Standard diagnostic procedures are not always acceptable for the early prediction of lung cancer as they detect abnormalities at the later stages. Biomarkers, the application of biosensor technology can provide a reliable detection technique for the early prediction of lung cancer. With the recent advancements in biosensing systems, detecting the normal range of protein biomarkers of ng mL?1 by using nanomaterials amplification, surface chemistries and bioassay format is possible. Biosensorsystems with microfluidics and nanomaterials can greatly improve the efficiency and reliability. Breath analysis is a multidisciplinary field comprising of analytical chemistry, clinical, data processing and metabolomics expertise. Breath VOC analysis is a practicable and reliable technique for the early prediction of lung cancer. Nowadays, E-nose based VOC analysis is showing optimistic prospects in clinical practices. In several medical situations image processing is broadly used for image magnification in the diagnosis stage to assist the prior medical therapy. The early lung cancer detection basedonwatershedimagesegmentation,featureextractionand Support Vector Machinealgorithm (supervisedlearning) has high accuracy and robustness. The methods of early detection of lung cancers explainedin our literatureprovides economical, non-invasive, sensitive, and user-friendly diagnosis tool with highly reliable, specific and sensitive for cancer markers.

References

[1] American Cancer Society. “Cancer Facts & Figures 2018”. Atlanta:American Cancer Society; 2018. [2] J. Ferlay, H. Shin, F. Bray, D. Forman, C. Mathers, D. Parkin,GLOBOCAN 2008,Cancer Incidence and Mortality Worldwide: IARCCancerBase No. 10, 2010. [3] A. Jemal, F. Bray, M.M. Center, J. Ferlay, E. Ward, D. Forman, Globalcancer statistics, CA: A Cancer Journal for Clinicians 61 (2011) 69–90. [4] JemalA, Ward EM,JohnsonCJ,etal.Annualreporttothenation on thestatus of cancer, 1975-2014, featuring survival. J Natl Cancer Inst2017;109. [5] Aberle DR, Berg CD, etal.National Lung Screening Trial ResearchTeam, The National Lung Screening Trial: overview and study design.Radiology2011;258:243–253. [6] Wang Li, Hong-Ying Liu1, Zi-Ru Jia1, Pan-Pan Qiao, Xi-Tian Pi1, JunChen1 and Lin-Hong Deng, Advances in the Early Detection of LungCancer using Analysis of Volatile Organic Compounds: From Imagingto Sensors, Asian Pacific Journal of Cancer Prevention, Vol 15, 2014 [7] A.B. de González, S. Darby, Risk of cancer from diagnostic X-rays:estimatesfortheUKand14 othercountries,Lancet 363 (2004)345–351. [8] R. Beets-Tan, G. Beets, R. Vliegen, A. Kessels, H.V. Boven, A.D.Bruine, M.VonMeyenfeldt, C. Baeten, J. Van Engelshoven, Accuracyof magnetic reso-nance imaging in prediction of tumour-free resectionmargin in rectal cancersurgery, Lancet 357 (2001) 497–504. [9] Zeynep Altintas and Ibtisam Tothill, Biomarkers and biosensors for theearly diagnosis of lung cancer, Sensors and Actuators B 188 (2013)988–998 [10] K. Matsuoka, S. Sumitomo, N. Nakashima, D. Nakajima, N. Misaki,Progno-stic value of carcinoembryonic antigen and CYFRA21-1 inpatients withpathological stage I non-small cell lung cancer, EuropeanJournal of Cardio-thoracic Surgery 32 (2007) 435–439. [11] Kim H, Oh I, Shin M. Park J, Choi H, Ban H, Kim K, Kim Y, Shin J.RyangD,PlasmaproGRPconcentrationissensitiveandspecificfodiscriminating small cell lung cancer from nonmalignant conditions ornon-small cell lung cancer. J. Korean Med. Sci. 2011, 26, 625–630 [12] Z. Altintas, Y. Uludag, Y. Gurbuz, I.E. Tothill, Surface plasmonresonance basedimmunosensor for the detection of the cancer biomarkercarcinoembriyonicantigen, Talanta 86 (2011) 377–383. [13] F.Barlesi,C.Gimenez,J.P.Torre,C.Doddoli,J.Mancini,L.Greillier, F. Roux,J.P. Kleisbauer, Prognostic value of combination of Cyfra 21-1,CEA and NSEin patients with advanced non-small cell lung cancer,Respiratory Medicine98 (2004) 357–362. [14] V. Gregorc, A. Spreafico, I. Floriani, B. Colombo, V. Ludovini, L.Pistola, G.Bellezza, M.G. Viganò,E.Villa, A. Corti,Prognosticvalueofcirculating chromo-granin A and soluble tumor necrosis factor receptorsin advanced nonsmallcell lung cancer, Cancer 110 (2007) 845–853. [15] Phillips M, Breath Tests in Medicine. Scientific American (1992) 267,74–79. [16] Lourenco, C., & Turner, C, Breath analysis in disease diagnosis:methodological considerations and applications. Metabolites, 4 (2014)465–498. [17] P.J. Mazzone, “Analysis of volatile organic compounds in the exhaledbreath for the diagnosis of lung cancer”, J. Thorac. Oncol, 2008. vol. 3,no. 7, pp. 774-800 [18] Hakim M, Broza YY, Barash O, et al Volatile organic compounds oflung cancer and possible biochemical pathways. Chem Rev, (2012).112,5949-66. [19] D.ArulPonDaniel, K. Thangavel, K. T.Rajakeerthana,Empiricalstudyon Early Detection of Lung Cancer using Breath Analysis, IEEESponsored 2nd International Conference on Innovations in Information, EmbeddedandCommunicationsystems(ICIIECS)2015 [20] Inbar Nardi-Agmon, Manal Abud-Hawa, Ori Liran, Exhaled BreathAnalysis for Monitoring Response to Treatment in Advanced LungCancer, Journal of Thoracic Oncology Vol. 11 No. 6, 2016, 827-837 [21] Xiuhua,G., Tao, S., & Zhigang, L.(2011) “Prediction Models forMalignant Pulmonary Nodules Based-on Texture Features of CTImage.” In Theory and Applications of CT Imaging and Analysis. DOI:10.5772/14766. [22] BariqiAbdillah, AlhadiBustamam, and DevviSarwinda, Imageprocessingbaseddetection oflungcanceronCTscanimages, JournalofPhysics: Conference Series,2017, 893 012063 [23] Ann Mary, Binson V A, Room Reserved Reversible Data Hiding inEncrypted Images, International Journal of Advanced Research inElectrical, Electronics and Instrumentation Engineering. Vol. 4, SpecialIssue 1, March2015 [24] Rendon-Gonzalez, E., & Ponomaryov, V. (2016) “Automatic Lungnodule segmentation and classification in CT images based on SVM.”2016 9Th International Kharkiv Symposium On Physics AndEngineering Of Microwaves, Millimeter And Submillimeter Waves(MSMW). DOI: 10.1109/MSMW.2016.7537995.

Copyright

Copyright © 2025 Karthika M, Thenmozhi Sri Sakthi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.