You're using an outdated browser. Please upgrade to a modern browser for the best experience.
Submitted Successfully!
Thank you for your contribution! You can also upload a video entry or images related to this topic. For video creation, please contact our Academic Video Service.
Version Summary Created by Modification Content Size Created at Operation
1
Francisco Silva
 -- 1415 2022-04-21 11:50:29 |
2 format correct
Conner Chen
 -8 word(s) 1407 2022-04-22 03:16:53 | |
3 format correct
Conner Chen
 Meta information modification 1407 2022-04-22 03:19:42 | |
4 format correct
Conner Chen
 Meta information modification 1407 2022-04-25 10:38:34 |

Video Upload Options

We provide professional Academic Video Service to translate complex research into visually appealing presentations. Would you like to try it?
No, upload directly Yes

Confirm

Are you sure to Delete?
Yes No
Cite
If you have any further questions, please contact Encyclopedia Editorial Office.
Silva, F.; Pereira, T.; Neves, I.; Morgado, J.; Freitas, C.; Malafaia, M.; Sousa, J.; , .; Costa, J.L.; Hespanhol, V.; et al. Lung Cancer: Computer-Aided Decision Systems. Encyclopedia. Available online: https://encyclopedia.pub/entry/22100 (accessed on 12 July 2025).
Silva F, Pereira T, Neves I, Morgado J, Freitas C, Malafaia M, et al. Lung Cancer: Computer-Aided Decision Systems. Encyclopedia. Available at: https://encyclopedia.pub/entry/22100. Accessed July 12, 2025.
Silva, Francisco, Tania Pereira, Inês Neves, Joana Morgado, Cláudia Freitas, Mafalda Malafaia, Joana Sousa,  , José Luis Costa, Venceslau Hespanhol, et al. "Lung Cancer: Computer-Aided Decision Systems" Encyclopedia, https://encyclopedia.pub/entry/22100 (accessed July 12, 2025).
Silva, F., Pereira, T., Neves, I., Morgado, J., Freitas, C., Malafaia, M., Sousa, J., , ., Costa, J.L., Hespanhol, V., Cunha, A., & Oliveira, H. (2022, April 21). Lung Cancer: Computer-Aided Decision Systems. In Encyclopedia. https://encyclopedia.pub/entry/22100
Silva, Francisco, et al. "Lung Cancer: Computer-Aided Decision Systems." Encyclopedia. Web. 21 April, 2022.
Lung Cancer: Computer-Aided Decision Systems
Edit
This entry is adapted from the peer-reviewed paper 10.3390/jpm12030480

Computer-aided decision systems could be defined as tools that automatically extract valuable information from medical data and help make more accurate and fast decisions. In lung cancer, CADs focus on using imaging results from CT scans and producing predictions that help the clinicians to decide on the follow-up of the patients or the best treatment plans. An effective CAD should comprise various components: pre-processing, segmentation, feature extraction, classification, grading and characterization of cancer. An ideal CAD would present specific features (e.g. accurate, non-invasive, low-cost, repeatable, generalizable and interpretable) to be integrated into the clinical routine of the cancer assessment.

computer-aided decision lung cancer assessment

1. Introduction

Lung cancer is a disease that involves the accumulation of multiple genetic mutations and epigenetic changes, which results in an out-of-control cell proliferation that disrupts regular cells. Lung cancer is the leading cause of cancer-related fatalities worldwide, accounting for about 1.6 million deaths per year [1][2]; it is the second most common cancer diagnosis, comprising a total of 13% of new cancer cases each year [3]. Age is a risk factor for lung cancer [4], due to biologic factors, including DNA damage (over time) and telomere shortening. Smoking is the primary “agent” in the development of lung cancer, responsible for about 80% of lung cancer-related deaths [5]. Men and women who smoke are 23% and 13%, respectively, more likely to develop lung cancer compared to never-smokers [6]. The risk of being diagnosed with lung cancer, due to tobacco consumption, varies in ethnic groups, e.g., compared to white people, African Americans and native Hawaiian smokers are shown to be at a greater risk of developing lung cancer, with the highest incidences and death rates. Latino and Japanese American smokers are less likely to develop the disease and present the lowest cancer-specific mortality [1][6]. Accumulating evidence supports that genetic factors are also risk factors for lung cancer [7]. Recently, several novel lung cancer susceptibility genes, including those on chromosomes 6q23-25 and 13q31.3, were identified by large-scale genome-wide association studies as being associated with lung cancer risk, particularly in never-smokers, who account for 25% of lung cancer patients worldwide [8][9]. Furthermore, an individual who has a positive family history of lung cancer has a 1.7-fold increased risk of developing lung cancer [9][10][11]. Lung cancer in never-smokers has been associated with genetic factors, as well as occupational exposures to lung carcinogens, exposure to ionizing radiation, and a poor diet [1][5][9][12].
Lung cancer can be classified into two major histological subtypes: non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC). NSCLC accounts for about 85% of all lung cancer cases and presents a 25% chance of a 5-year-survival [13]. Adenocarcinoma and squamous cell carcinoma are its two major histologic types, accounting for about 40% and 25% of lung cancers, respectively [14]. SCLC is the lung cancer type that tends to spread the fastest, accounting for 10% to 15% of all lung cancers [15]. Individuals who have this type of lung cancer present a 7% chance of a 5-year-survival [13]. Figure 1 represents the distribution of the main histological subtypes.
Figure 1. Prevalence of the major histological subtypes of lung cancer: non-small cell lung cancer and small cell lung cancer.
Computed tomography (CT) is the most useful imaging modality used for lung cancer management, including diagnosis, staging, treatment planning, and treatment response evaluation [16][17][18][19]. CT is the recommended screening test for lung cancer; but confirmation of the malignancy and characterization of the nodule are traditionally conducted via a biopsy, which is an invasive and risky procedure for the patient that can lead to some clinical complications. Recently, non-invasive, fast, and easy-to-use techniques, such as computer-aided diagnosis (CAD) based on CT scans, have been developed for lung cancer characterization, to improve the accuracy of diagnosis, determine the most appropriate treatment for each subject and, consequently, decrease the mortality rate of patients battling lung cancer [20][21][22]. Since imaging is already regularly repeated during treatment, it has the potential to continuously supervise therapy and monitor the rise and growth of the disease or its response to therapy.

2. Computer-Aided Decision Systems

Computer-aided decision systems could be defined as tools that automatically extract valuable information from medical data and help make more accurate and fast decisions. In lung cancer, CADs focus on using imaging results from CT scans and producing predictions that help the clinicians to decide the follow-up of the patients or the best treatment plans. An effective CAD should comprise various components: pre-processing, segmentation, feature extraction, classification, grading, and characterization of cancer. An ideal CAD would present specific features (e.g., accurate, non-invasive, low-cost, repeatable, generalizable, and interpretable) to be integrated into the clinical routine of the cancer assessment. Key features of CADs for lung cancer diagnosis:
  • Accurate: to be used to help clinicians produce better decisions;
  • Non-invasive: to avoid the problems associated with an invasive procedure;
  • Low-cost: to be implemented on a large scale;
  • Repeatable: allowing it to be performed several times to follow the progress and treatment results;
  • Generalizable: to be able to deal with the heterogeneities of the population and make correct predictions for unseen data;
  • Interpretable: to give additional information to clinicians to trust in the decision.
The developed approaches were first based on statistical methods (and more recently on machine learning models). The initial automatic methods attempted to correlate imaging features with the malignancy, which is defined as radiomics. The use of the most powerful methods opened up the possibility of exploring a characterization of cancer, such as the genotype (see Figure 2). Radiogenomics is an approach to predict the genotype (genes mutation status) based on imaging information (phenotype), which could reduce the need for biopsies.
Jpm 12 00480 g003 550
Figure 2. Radiomic vs. radiogenomic perspectives for lung cancer assessment. The assessment of lung cancer was first based on the nodule; however, recently, in radiogenomics approaches, other lung structures were shown to have relevant information for cancer characterization. Those approaches brought new challenges, such as the segmentation of lungs, to use this region of interest (ROI) in the AI-based models.
For the particular case of lung cancer, there are specific elements that are crucial to consider in the phenotype characterization. The first element is the nodule, which is a cluster of tumor cells. This structure must be detected, segmented, and assessed to make the initial diagnosis of malignancy. For the malignant cases, CADs could help in cancer characterization, based on more information from the lung structures surrounding the nodules since other lung pathologies are correlated with cancer development [23].
Exploratory studies that have taken into account features from multiple lung structures, and did not just focus on the nodule, showed the importance of including extra-tumor features to obtain a successful genomic prediction (see Figure 2, where it is illustrated that radiogenomics approaches use information from more than just the nodule region) [24][23][25][26][27][28]. This seems to indicate that cancer development is related to multiple physiological changes not restricted to the nodule region and that the next generation of CADs should consider large lung regions to allow for a more complete lung cancer characterization [16][29]. This comprehensive approach, in the treatment planning field, would allow for the selection of a personalized treatment that would improve effectiveness and efficiency while diminishing avoidable therapy-related adverse events. This strategy may be particularly helpful in elderly or unfit patients who are at higher risk of procedure-related complications.
A deep characterization of lung cancer shows the need for more comprehensive analyses, capturing more information of other lung structures related to cancer development, which potentially present relevant information for more accurate predictions of the main biomarkers. Figure 3 illustrates the two main perspectives for AI-based CAD development for lung cancer, focusing on the nodule region or approaching a more holistic perspective of the lung condition. The following sections are dedicated toward analyzing the methodologies developed for nodule detection, segmentation, and classification; lung segmentation, genotype prediction, and other biomarkers prediction reflecting the movement from approaches centered on the nodule to more inclusive approaches. The selected works were presented in chronological order, with a deep discussion of the current limitations and possible opportunities and solutions. There are several up-to-date and significant reviews on each specific part of the CAD development solutions. The correspondent review papers are presented at the beginning of each section dedicated to CADs. The present research is dedicated toward capturing a global perspective of the general pipeline of CADs based on CT images dedicated to lung cancer evaluation; here present the specific challenges of each part of the clinical pathway.
Jpm 12 00480 g004 550
Figure 3. Two main perspectives for CADs in lung cancer, focused on the nodule and a more holistic approach that takes into consideration information about the surrounding structures of the nodule.

References

  1. Barta, J.A.; Powell, C.A.; Wisnivesky, J.P. Global epidemiology of lung cancer. Ann. Glob. Health 2019, 85, 8.
  2. World Health Organization. Latest global cancer data: Cancer burden rises to 18.1 million new cases and 9.6 million cancer deaths in 2018. In International Agency for Research on Cancer; World Health Organization: Geneva: Switzerland, 2018.
  3. Torre, L.A.; Siegel, R.L.; Jemal, A. Lung cancer statistics. Lung Cancer Pers. Med. 2016, 893, 1–19.
  4. Galvez-Nino, M.; Ruiz, R.; Pinto, J.A.; Roque, K.; Mantilla, R.; Raez, L.E.; Mas, L. Lung cancer in the young. Lung 2020, 198, 195–200.
  5. Zappa, C.; Mousa, S.A. Non-small cell lung cancer: Current treatment and future advances. Transl. Lung Cancer Res. 2016, 5, 288.
  6. Kanwal, M.; Ding, X.J.; Cao, Y. Familial risk for lung cancer. Oncol. Lett. 2017, 13, 535–542.
  7. Ji, X.; Bossé, Y.; Landi, M.T.; Gui, J.; Xiao, X.; Qian, D.; Joubert, P.; Lamontagne, M.; Li, Y.; Gorlov, I.; et al. Identification of susceptibility pathways for the role of chromosome 15q25. 1 in modifying lung cancer risk. Nat. Commun. 2018, 9, 3221.
  8. Yokota, J.; Shiraishi, K.; Kohno, T. Genetic basis for susceptibility to lung cancer: Recent progress and future directions. Adv. Cancer Res. 2010, 109, 51–72.
  9. Okazaki, I.; Ishikawa, S.; Ando, W.; Sohara, Y. Lung adenocarcinoma in never smokers: Problems of primary prevention from aspects of susceptible genes and carcinogens. Anticancer. Res. 2016, 36, 6207–6224.
  10. de Groot, P.M.; Wu, C.C.; Carter, B.W.; Munden, R.F. The epidemiology of lung cancer. Transl. Lung Cancer Res. 2018, 7, 220.
  11. Rivera, G.A.; Wakelee, H. Lung cancer in never smokers. Lung Cancer Pers. Med. 2016, 893, 43–57.
  12. Malhotra, J.; Malvezzi, M.; Negri, E.; La Vecchia, C.; Boffetta, P. Risk factors for lung cancer worldwide. Eur. Respir. J. 2016, 48, 889–902.
  13. Society, A.C. Cancer Facts & Figures. 2021. Available online: https://www.cancer.org/research/cancer-facts-statistics/all-cancer-facts-figures/cancer-facts-figures-2021 (accessed on 15 April 2021).
  14. Herbst, R.S.; Morgensztern, D.; Boshoff, C. The biology and management of non-small cell lung cancer. Nature 2018, 553, 446–454.
  15. Society, A.C. Lung Cancer. 2019. Available online: https://www.cancer.org/cancer/lung-cancer.html (accessed on 15 April 2021).
  16. Zhang, H.; Cai, W.; Wang, Y.; Liao, M.; Tian, S. CT and clinical characteristics that predict risk of EGFR mutation in non-small cell lung cancer: A systematic review and meta-analysis. Int. J. Clin. Oncol. 2019, 24, 649–659.
  17. Chaudhry, A.; Gul, M.; Chaudhry, A. Utility of computed tomography lung cancer screening and the management of computed tomography screen-detected findings. J. Thorac. Dis. 2018, 10, 1352.
  18. Al Mohammad, B.; Brennan, P.C.; Mello-Thoms, C. A review of lung cancer screening and the role of computer-aided detection. Clin. Radiol. 2017, 72, 433–442.
  19. de Koning, H.J.; van der Aalst, C.M.; de Jong, P.A.; Scholten, E.T.; Nackaerts, K.; Heuvelmans, M.A.; Lammers, J.W.J.; Weenink, C.; Yousaf-Khan, U.; Horeweg, N.; et al. Reduced lung-cancer mortality with volume CT screening in a randomized trial. N. Engl. J. Med. 2020, 382, 503–513.
  20. Junior, J.R.F.; Koenigkam-Santos, M.; Cipriano, F.E.G.; Fabro, A.T.; de Azevedo-Marques, P.M. Radiomics-based features for pattern recognition of lung cancer histopathology and metastases. Comput. Methods Programs Biomed. 2018, 159, 23–30.
  21. Ostridge, K.; Wilkinson, T.M. Present and future utility of computed tomography scanning in the assessment and management of COPD. Eur. Respir. J. 2016, 48, 216–228.
  22. Bakr, S.; Gevaert, O.; Echegaray, S.; Ayers, K.; Zhou, M.; Shafiq, M.; Zheng, H.; Benson, J.A.; Zhang, W.; Leung, A.N.; et al. A radiogenomic dataset of non-small cell lung cancer. Sci. Data 2018, 5, 180202.
  23. Pereira, T.; Freitas, C.; Costa, J.L.; Morgado, J.; Silva, F.; Negrão, E.; de Lima, B.F.; da Silva, M.C.; Madureira, A.J.; Ramos, I.; et al. Comprehensive Perspective for Lung Cancer Characterisation Based on AI Solutions Using CT Images. J. Clin. Med. 2021, 10, 118.
  24. Pinheiro, G.; Pereira, T.; Dias, C.; Freitas, C.; Hespanhol, V.; Costa, J.L.; Cunha, A.; Oliveira, H.P. Identifying relationships between imaging phenotypes and lung cancer-related mutation status: EGFR and KRAS. Sci. Rep. 2020, 10, 3625.
  25. Liu, Y.; Kim, J.; Balagurunathan, Y.; Li, Q.; Garcia, A.L.; Stringfield, O.; Ye, Z.; Gillies, R.J. Radiomic features are associated with EGFR mutation status in lung adenocarcinomas. Clin. Lung Cancer 2016, 17, 441–448.
  26. Gevaert, O.; Echegaray, S.; Khuong, A.; Hoang, C.D.; Shrager, J.B.; Jensen, K.C.; Berry, G.J.; Guo, H.H.; Lau, C.; Plevritis, S.K.; et al. Predictive radiogenomics modeling of EGFR mutation status in lung cancer. Sci. Rep. 2017, 7, 41674.
  27. Wilson, R.; Devaraj, A. Radiomics of pulmonary nodules and lung cancer. Transl. Lung Cancer Res. 2017, 6, 86.
  28. Yamashita, R.; Nishio, M.; Do, R.K.G.; Togashi, K. Convolutional neural networks: An overview and application in radiology. Insights Imaging 2018, 9, 611–629.
  29. Dias, C.; Pinheiro, G.; Cunha, A.; Oliveira, H.P. Radiogenomics: Lung Cancer-Related Genes Mutation Status Prediction. In Proceedings of the Iberian Conference on Pattern Recognition and Image Analysis, Madrid, Spain, 1–4 July 2019; pp. 335–345.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
Upload a video for this entry
Information
Subjects: Engineering, Biomedical
Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to https://encyclopedia.pub/register :
Francisco Silva
,
Tania Pereira
,
Inês Neves
,
Joana Morgado
,
Cláudia Freitas
,
Mafalda Malafaia
,
Joana Sousa
,
,
José Luis Costa
,
Venceslau Hespanhol
,
António Cunha
,
Hélder Oliveira
View Times: 675
Revisions: 4 times (View History)
Update Date: 25 Apr 2022
Table of Contents
    1000/1000
    Hot Most Recent
    Academic Video Service
    Feedback