Exploring the evolving landscape of radiomics in lung cancer: a comprehensive bibliometric analysis [2008–2024]

Introduction

Lung cancer is one of the most prevalent malignancies worldwide, with an estimated 2.4 million new cases and 2.5 million deaths in 2024, accounting for approximately 19% of all cancer-related fatalities annually (1). Despite advancements in early detection and therapeutic approaches, lung cancer remains challenging to manage due to its high incidence of late-stage diagnosis and complex disease heterogeneity (2). The transition from normal lung tissue to malignant tumors is a complex, multi-step process involving genetic, epigenetic, and micro-environmental changes. Among these, imaging biomarkers have emerged as a critical tool for capturing tumor heterogeneity and predicting clinical outcomes (3).

Radiomics, an emerging field in medical imaging, leverages advanced computational techniques to extract high-dimensional quantitative features from standard medical images such as computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) (4). These features, which are imperceptible to the human eye, provide detailed information about tumor shape, texture, and intensity (5). Radiomics has shown tremendous potential in improving the accuracy of lung cancer diagnosis, guiding treatment strategies, and predicting prognosis. By integrating artificial intelligence and machine learning algorithms, radiomics is evolving as a cornerstone of personalized medicine, offering a non-invasive approach to tumor characterization and decision-making (6). Recent studies underscore the value of radiomics in enhancing lung cancer management. Radiomics-based models have been applied to differentiate malignant from benign nodules, predict histopathological subtypes, and assess treatment responses (7).

These advancements are particularly relevant in lung cancer, where early diagnosis and timely interventions are critical for improving survival rates (8). Despite growing interest in the role of radiomics in lung cancer, no comprehensive study has systematically summarized the research trends and focal points in this area. In this study, we conducted a bibliometric analysis to investigate research trends and highlight key focus areas in the application of radiomics to lung cancer.

Methods

Bibliometric analysis approach

A comprehensive bibliometric analysis was conducted to systematically evaluate the research landscape of radiomics in lung cancer. Bibliometric analysis is a quantitative research method that uses mathematical and statistical techniques to analyze patterns in scientific publications, identify research trends, map collaboration networks, and assess the impact of research outputs in a specific field (9). This approach was chosen to provide an objective and comprehensive overview of the field’s development, key contributors, and emerging research directions.

Search strategies and data collection

A comprehensive bibliometric search on radiomics in lung cancer was conducted using the Web of Science Core Collection (WoSCC). WoSCC was selected as the primary database for this analysis due to several reasons, including that it provides comprehensive citation data essential for bibliometric analysis, maintains consistent indexing standards across disciplines, offers complete bibliographic information including author affiliations, keywords, and references, and is widely recognized as the gold standard database for bibliometric studies (10). Although other databases such as Scopus and PubMed could provide additional coverage, WoSCC’s robust analytical capabilities and standardized data structure made it the most suitable choice for this bibliometric analysis, encompassing publications between 2008 and 2024. The timeframe of 2008–2024 was selected based on preliminary searches showing that the term “radiomics” was first introduced in the literature around 2008, marking the emergence of this field. Although publication growth was minimal before 2016 (as confirmed by our results), including this early period allowed us to capture the complete evolution of radiomics research in lung cancer from its inception to current developments. The search strategy was developed through an iterative process combining expert consultation and preliminary literature review. Search terms were refined based on Medical Subject Headings (MeSH) (11) terms and keywords frequently used in seminal radiomics publications. The search strategy utilized the following terms: TS=(radiomics OR radiogenomics OR “imaging omics”) AND TS=(“lung neoplasms” OR “bronchogenic carcinoma” OR “carcinoma, bronchogenic” OR “carcinomas, bronchogenic” OR “small cell lung carcinoma” OR “primary bronchogenic carcinoma” OR “carcinoma, non-small cell lung” OR “lung carcinoma, non-small-cell” OR “non-small cell lung carcinoma” OR “non-small-cell lung carcinoma” OR “carcinoma, small cell lung” OR “non-small cell lung cancer” OR “cancer of lung” OR “cancer of the lung” OR “lung cancer” OR “oat cell lung cancer” OR “small cell cancer of the lung” OR “small cell lung cancer” OR “carcinoma, Lewis lung” OR “Lewis lung carcinoma” OR “lung carcinoma, Lewis” OR “carcinoma, small cell lung” OR “oat cell carcinoma of lung”) (12). The inclusion criteria were as follows: original research articles published in English, studies focusing on radiomics applications in lung cancer, and articles with complete bibliographic information. The exclusion criteria were as follows: review articles, conference proceedings, meeting abstracts, book chapters, early access publications, corrections, retracted papers, and non-English publications. The language restriction to English was applied to ensure consistency in analysis and because English represents the primary language of international scientific communication. Data were extracted on 30 November 2024, in text format, including titles, author details, institutions, countries/regions, keywords, and journal names, for subsequent bibliometric analysis.

Statistical analysis

VOSviewer (1.6.20; https://www.vosviewer.com/), CiteSpace (6.3.R1; https://citespace.podia.com/) and R package “bibliometrix” (4.3.3; https://cran.r-project.org/web/packages/bibliometrix/index.html) were employed for data analysis and visualization. VOSviewer, a widely used software for bibliometric analysis and network visualization, was utilized to map collaborations among countries, institutions, authors, and keywords, as well as to analyze co-occurrence and coupling networks of journals (13). CiteSpace was used to identify and visualize citation bursts for keywords. The parameters set as follows: time slicing between January 2008 and November 2024. The R package “Bibliometrix” was used for conducting comprehensive bibliometric analysis, including data extraction, analysis, and visualization of scientific literature (14).

Several bibliometric indicators parameters from the WoSCC, including the h-index, g-index, and m-index, were employed to quantify the academic impact of individuals and journals (15-17). The h-index is a vital indicator for evaluating researchers’ academic contributions and predicting their future scientific achievements (18). The g-index enhances this evaluation by giving more weight to highly cited articles, providing a better assessment of a researcher’s impact. The m-index, which is calculated by dividing the h-index by the number of years since the researcher’s first publication, allows for a comparison of researchers at different career stages. Journals were assessed using the latest impact factor (IF) and journal citation reports (JCR) metrics.

Results

An overview of publications

A total of 1,324 documents were included in this research, after excluding documents that were neither in English nor classified as the correct article type (Figure 1A). These studies encompassed 266 journals and involved 7,995 authors, with a total of 1,946 keywords and 26,776 references. The annual article count demonstrated an impressive average growth rate of 39.89%, with an international collaboration rate of 26.21%. On average, each paper was contributed by 8.99 co-authors, each article had an average age of 2.84 years, and the average number of citations per article was 36.92 (Figure 1B).

Figure 1 Overview of research. (A) Flowchart of the literature screening process. (B) Summary information of the included studies. (C) Annual number of publications.

The steady annual growth rate indicated that research on radiomics in lung cancer has been consistently expanding over time. Between January 2008 and November 2024, the number of published papers followed a continual upward trend. This growth can be divided into two distinct phases. In the first phase, before 2016, the annual increase was relatively slow, with a maximum of 25 papers published per year. In the second phase, from 2017 onward, the growth accelerated significantly, with annual publications exceeding 50 papers, peaking at 246 papers in 2023 (Figure 1C).

Analysis of countries

The top 20 countries by publication volume were primarily in Asia, North America, and Europe. China led the field with 622 publications (47%) and 9,131 citations, followed by the USA with 240 publications (18.1%) and 17,850 citations, and Italy with 86 publications (6.5%) and 2,048 citations. Publications were further categorized into single country publications (SCP) and multiple country publications (MCP). Among the two leading contributors, China had 525 SCPs and 97 MCPs, resulting in an MCP ratio of 15.6%. In contrast, the USA had 157 SCPs and 83 MCPs, achieving a much higher MCP ratio of 34.6% (Figure 2A and Table 1).

Figure 2 Analysis of countries and institutions. (A) Distribution of corresponding author’s publications by country. (B) Visualization map depicting the collaboration among different countries. (C) Top 10 institutions by article count and rank. (D) Visualization map depicting the collaboration among different institutions. MCP, multiple country publications; SCP, single country publications.

Among the 41 countries contributing to international collaborations with a minimum of two publications, the USA emerged as the most interconnected, achieving the highest collaboration network strength of 283, followed closely by the Netherlands (total link strength =187) and China (total link strength =156) (Figure 2B).

Analysis of institutions

The top 10 institutions (Figure 2C) were geographically diverse, spanning Asia, Europe, and the Americas. The top three institutions, namely, University of Texas System [163], UT MD Anderson Cancer Center [131], and Harvard University [130], were all from the USA. Other institutions included several from China (e.g., Shandong First Medical University, Fudan University, and Shanghai Jiao Tong University), one from South Korea (Sungkyunkwan University), and one from the Netherlands (Maastricht University). Among the 77 institutions engaged in international collaborations with at least 10 articles, the Chinese Academy of Sciences exhibited the highest collaboration strength (total link strength =56), followed by the University of Southern Denmark (total link strength =40) and the University of Groningen (total link strength =39) (Figure 2D).

Analysis of journals

The top three journals in terms of h-index were Scientific Reports [h-index: 26, total publications (TP): 58, IF: 3.8], Frontiers in Oncology (h-index: 24, TP: 122, IF: 3.5), and Medical Physics (h-index: 25, TP: 56, IF: 3.2). Among the top journals by h-index, Radiology had the highest IF (12.1), followed by the European Journal of Nuclear Medicine and Molecular Imaging (IF: 8.6) and Radiologia Medica (IF: 9.7). Radiology had the highest total citation count (TC =2,696), with International Journal of Radiation Oncology Biology Physics (TC =1,350) and European Journal of Nuclear Medicine and Molecular Imaging (TC =1,155) also ranking highly in citations (Table 2).

A total of 81 journals with at least four related publications were cited in tandem. The three key journals with the highest total link strength in the co-occurrence networks were Frontiers in Oncology (total link strength =987), Scientific Reports (total link strength =769), and Medical Physics (total link strength =615) (Figure 3A). Coupling networks evaluated shared references among journals, where strong link strength signified significant reference overlap, indicating a common research foundation. The three key journals with the highest total link strength in the coupling networks were Frontiers in Oncology (total link strength =96,829), Scientific Reports (total link strength =51,788), and Medical Physics (total link strength =51,788) (Figure 3B).

Figure 3 Visualization map depicting the co-occurrence networks of journals and coupling networks. (A) The co-occurrence networks of journals. (B) The coupling networks of journals.

Analysis of authors

Aerts Hugo J. W. L. led the field with an h-index of 28, a total of 32 publications, and 16,773 total citations, making him the most influential author in radiomics for lung cancer. Lambin Philippe followed closely with an h-index of 26, TP of 29, and TC of 14,167. Gillies Robert J. ranked third with an h-index of 25, TP of 31, and TC of 10,499. Leijenaar Ralph T. H. and Parmar, Chintan, despite having relatively modest TP of 16 and 14, respectively, achieved exceptionally high TC of 6,886 and 6,940, demonstrating the significant impact of their work within the radiomics and lung cancer research domain (Table 3).

Among the 95 authors involved in international collaborations with a minimum of 7 articles, Gillies Robert J. had the highest collaboration strength (total link strength =114), followed by Aerts Hugo J. W. L. (total link strength =102) and Lambin, Philippe (total link strength =96). Notably, these three authors not only ranked highest in total link strength but also held the top three positions in h-index (Figure 4).

Figure 4 Visualization map depicting the collaboration among different authors.

Analysis of keyword co-occurrence and burst keyword

A total of 79 keywords with at least 20 occurrences were identified, allowing for the rapid identification of research hotspots within the field. The keywords could be categorized into four major clusters, each representing distinct research focuses in radiomics and lung cancer. Cluster 1 (red) emphasizes diagnostic methods and imaging techniques, with important keywords such as “computed tomography”, “positron-emission tomography”, “texture analysis”, and “imaging phenotypes”. Cluster 2 (blue) focuses on clinical outcomes and treatment strategies, incorporating terms such as “chemotherapy”, “radiotherapy”, “immunotherapy”, and “survival”. Cluster 3 (green) explores tumor biology and molecular mechanisms, featuring keywords such as “mutations”, “biomarkers”, “egfr”, and “prognostic value”. Cluster 4 (yellow) addresses tumor heterogeneity and prediction models, including “tumor heterogeneity”, “variability”, “prediction”, and “signature”. These clusters provide a comprehensive overview of the diverse research areas within radiomics in lung cancer (Figure 5A).

Figure 5 Analysis of keywords. (A) Visual analysis of keyword co-occurrence network analysis. (B) Top 30 keywords with the strongest citation bursts. CT, computed tomography; PET, positron emission tomography.

Keyword burst analysis showed a sharp increase in citations within a specific period. Based on the figure, the earliest keyword burst emerged in 2010 with “cell lung cancer”. Other notable early keywords include “radiotherapy” [2013], and “heterogeneity” [2014]. Between 2015 and 2017, keywords such as “tumor heterogeneity”, “textural features”, and “18F-FDG PET” gained prominence. More recent bursts include “radiogenomics” [2019] and “repeatability” [2019], highlighting the integration of genomic data with imaging and the emphasis on reproducibility in radiomics studies. The most recent keywords, including “biomarkers” and “selection”, emerged in 2020 and continued until 2021, indicating ongoing research trends (Figure 5B).

Discussion

This study, based on 1,324 articles, highlights the current state of radiomics research in lung cancer, addressing publication trends, collaboration networks, key institutions, influential journals, and prominent authors. China led in publication volume, followed by the USA and Italy, with the USA demonstrating the highest total citations, indicating greater academic impact. Smaller research communities, such as Denmark and Australia, rely heavily on international collaboration, whereas larger contributors such as China prioritize domestic research. Among institutions, the University of Texas System and Harvard University in the USA dominated, with significant contributions from Chinese institutions such as Shandong First Medical University. The Chinese Academy of Sciences stood out for its collaboration strength. Journals such as Scientific Reports, Frontiers in Oncology, and Medical Physics ranked among the top in productivity and academic impact, underscoring their importance in this field. Key authors, including Aerts Hugo J. W. L., Lambin Philippe, and Gillies Robert J., led the field with high h-index scores and extensive collaborations, demonstrating their influential roles in advancing lung cancer radiomics research. Cluster analysis based on keywords resulted in the formation of four distinct clusters, each represented by a specific color.

Cluster 1 (red)

Diagnostic methods and imaging techniques. Diagnostic imaging techniques, such as CT-based and PET/CT-based radiomics, have been instrumental in non-invasively characterizing lung tumors, differentiating adenocarcinoma subtypes, and predicting lymph node metastasis with high accuracy (7,19). Recent advances have further enhanced diagnostic capabilities through ensemble learning approaches, as demonstrated by Tang et al., who developed a multi-type classification system for lung nodules using CT radiomics combined with diversity weighting, achieving improved accuracy in distinguishing between different nodule types (20). These approaches reduce the need for invasive diagnostic procedures and enhance early detection capabilities.

Cluster 2 (blue)

The role of radiomics in advancing precision medicine. In treatment prediction, radiomics has demonstrated significant potential by integrating imaging features with molecular biomarkers, such as programmed cell death ligand 1 (PD-L1) expression, to personalize immunotherapy outcomes in non-small cell lung cancer (NSCLC) (21,22). Furthermore, delta-radiomics, which evaluates temporal imaging changes, has been applied to predict responses to neoadjuvant chemoimmunotherapy, advancing precision medicine strategies and improving treatment outcomes (23,24).

Cluster 3 (green)

Tumor biology and molecular mechanisms. The integration of radiomics with deep learning and other omics data, such as genomic and immunome profiles, is expected to further improve predictive accuracy and treatment customization (25). The integration of semantic features with radiomic analysis has shown particular promise, as demonstrated by Wu et al., who developed an integrated nomogram combining semantic–radiomic features to predict invasive pulmonary adenocarcinomas in patients with persistent subsolid nodules, achieving superior predictive performance compared to traditional approaches (26). These advancements emphasize the role of robust computational models and standardized protocols across institutions to ensure global scalability and reproducibility. By linking imaging data with personalized medicine, radiomics continues to advance lung cancer care, addressing patient-specific challenges and improving both diagnosis and treatment outcomes (5,27).

Cluster 4 (yellow)

Tumor heterogeneity and prediction models. Radiomic analysis of tumor heterogeneity has significantly enhanced prognostic models by linking intertumoral features to survival outcomes, particularly in early-stage lung cancer treated with stereotactic radiotherapy (28). The quality and reliability of these prediction models have become increasingly important, with recent systematic reviews highlighting the need for standardized quality assessments. Jia et al. conducted a comprehensive evaluation of CT-based radiomics models for NSCLC prognosis using the radiomics quality score 2.0, emphasizing the importance of methodological rigor in model development (29). These heterogeneity metrics offer critical insights into patient prognosis, advancing precision-driven therapeutic strategies. Additionally, multiscale radiomic approaches have deepened the understanding of molecular heterogeneity, enabling more targeted therapeutic interventions (30). By analyzing variations across different scales, radiomics has strengthened the ability to capture intertumoral diversity, supporting the development of individualized and effective treatment plans.

Early foundational research (2020 and earlier), represented by key terms such as “positron-emission-tomography” and “texture analysis”, laid the groundwork for the field (31). This phase emphasized imaging modalities such as CT and PET, which were instrumental in tumor characterization. Studies during this period focused on the quantitative extraction of imaging features through texture analysis, enabling a deeper understanding of tumor heterogeneity. These findings highlighted the importance of tumor morphology and metabolic activity in influencing treatment resistance and overall prognosis (32). Imaging phenotypes derived from these modalities provided critical insights into tumor biology, creating a foundation for predictive and diagnostic models (33).

In 2021, a marked shift toward clinical applications and patient-centered outcomes emerged, as reflected by keywords such as “survival”, “classification”, and “features”. This period saw the integration of radiomics features with clinical and genomic data, particularly in the management of NSCLC. Radiomics demonstrated its utility in predicting survival rates and treatment responses, offering a more refined approach to patient stratification (34). For example, combining imaging phenotypes with clinical data allowed for superior accuracy in forecasting overall survival in NSCLC patients compared to traditional staging methods (35,36). During this phase, radiogenomics emerged as a transformative approach, integrating radiomics features with genomic and molecular profiles to identify tumor-specific biomarkers (37). This integration advanced precision oncology by enabling the development of personalized treatment strategies that addressed both radiological and molecular tumor characteristics (38). Keywords such as “classification” and “selection” underscored efforts to refine diagnostic precision and stratify patients for tailored therapies. Studies showed that radiomics models were increasingly utilized to differentiate between benign and malignant nodules, achieving high sensitivity and specificity, thereby enhancing early detection rates and reducing the need for invasive biopsies (19).

Since 2022, emerging trends have focused on risk assessment and therapeutic strategies, as highlighted by keywords such as “immunotherapy”, “risk-factors”, “open-label”, and “epidemiology”. These advancements underscore the integration of radiomics features into precision medicine for lung cancer (39). For instance, recent studies have demonstrated the utility of radiomics in predicting patient responses to immunotherapy. One multicenter study highlighted the use of radiomics-based models to predict treatment efficacy for stage IB–IV NSCLC patients, with imaging biomarkers successfully identifying responders to immune checkpoint inhibitors. Another retrospective cohort study revealed that baseline CT radiomics features could reliably predict PD-L1 expression, a critical biomarker for selecting immunotherapy candidates (40,41). Meanwhile, more research has enhanced the design of predictive models in “open label” clinical trials. For example, one study employed advanced radiomics features combined with clinical data to improve survival prediction for NSCLC patients receiving chemoimmunotherapy, demonstrating how imaging-derived biomarkers can guide treatment decisions (33). Another study investigated delta-radiomics signatures, showing their ability to dynamically monitor treatment response, providing a non-invasive method for evaluating therapeutic efficacy during immune-based treatments (42).

Around 2022, developments also focused on “epidemiology”, as studies had linked radiomics features with epidemiological risk factors. For example, radiomics-driven models have been integrated into clinical workflows to assess disease progression in diverse cohorts, enhancing the robustness of predictive tools across populations (43). Furthermore, innovative approaches integrating imaging data with genomic signatures have successfully identified tumor-specific markers, offered tailored therapeutic strategies, and bridged the gap between radiomics research and its clinical applications (44). Such advancements reflect radiomics’ growing potential in optimizing lung cancer management, from personalized immunotherapy to broader applications in clinical trials and public health.

Future radiomics research will benefit from the integration of multimodal data, such as “genomics”, “proteomics”, and “metabolomics”, aligning with the growing emphasis on understanding tumor biology and advancing precision medicine strategies. Incorporating these diverse datasets into predictive models can enhance diagnostic accuracy, optimize treatment planning, and enable more personalized care approaches. Furthermore, longitudinal studies focusing on “tumor progression” and “therapy adaptation” will play a critical role in refining the predictive accuracy and practical applicability of radiomics models. These advancements will complement ongoing efforts to standardize methodologies and driving transformative improvements in lung cancer diagnosis, prognosis, and management.

Strengths and limitations

Our study exhibits several strengths. It comprehensively encompasses literature from almost two decades, employs multiple bibliometric tools for a rigorous analysis, and integrates both quantitative and qualitative evaluations of research trends. There are limitations, including potential publication bias, as only English-language articles were considered, which may have led to the exclusion of relevant studies in other languages. Additionally, this analysis relied solely on the WoSCC database. Although WoSCC provides comprehensive coverage and standardized bibliometric data, using a single database may not capture all relevant publications indexed in other databases such as Scopus, PubMed, or regional databases, potentially limiting the completeness of our analysis. Furthermore, the analysis is based on available publications, and the conclusions may not fully reflect ongoing research efforts or emerging trends beyond the publication period.

Conclusions

This bibliometric study highlights key research themes in radiomics for lung cancer. Research hotspots feature diagnostic methods, clinical outcomes and treatment strategies, molecular mechanisms, and prediction models, along with emerging trends in 2024 such as “prediction model” and “lung neoplasms”. Burst keywords such as “selection” and “biomarkers” reveal trends in therapeutic strategies and risk assessment. Future directions should focus on standardizing methodologies, prediction models, and integrating multi-modal data to improve diagnostics, treatment planning, and personalized care.

Acknowledgments

None.

Footnote

Funding: This research was supported by the National Natural Science Foundation of China (Nos. 82071911 and 81671646).

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://qims.amegroups.com/article/view/10.21037/qims-2025-1155/coif). All authors report that this research was supported by the National Natural Science Foundation of China (Nos. 82071911 and 81671646). The authors have no other conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Van Schil PE, Asamura H, Nishimura KK, Rami-Porta R, Kim YT, Bertoglio P, Cangir AK, Donington J, Fang W, Giroux DJ, Lievens Y, Liu H, Lyons G, Sakai S, Travis WD, Ugalde P, Jeffrey Yang CF, Yotsukura M, Detterbeck F; Members of the IASLC Staging and Prognostic Factors Committee and of the Advisory Boards, and Participating Institutions. The International Association for the Study of Lung Cancer Lung Cancer Staging Project: Proposals for the Revisions of the T-Descriptors in the Forthcoming Ninth Edition of the TNM Classification for Lung Cancer. J Thorac Oncol 2024;19:749-65.
2. Nasim F, Sabath BF, Eapen GA. Lung Cancer. Med Clin North Am 2019;103:463-73. [Crossref] [PubMed]
3. Jones GS, Baldwin DR. Recent advances in the management of lung cancer. Clin Med (Lond) 2018;18:s41-6. [Crossref] [PubMed]
4. Li Y, Wu X, Yang P, Jiang G, Luo Y. Machine Learning for Lung Cancer Diagnosis, Treatment, and Prognosis. Genomics Proteomics Bioinformatics 2022;20:850-66. [Crossref] [PubMed]
5. Chen M, Copley SJ, Viola P, Lu H, Aboagye EO. Radiomics and artificial intelligence for precision medicine in lung cancer treatment. Semin Cancer Biol 2023;93:97-113. [Crossref] [PubMed]
6. Tunali I, Gillies RJ, Schabath MB. Application of Radiomics and Artificial Intelligence for Lung Cancer Precision Medicine. Cold Spring Harb Perspect Med 2021;11:a039537. [Crossref] [PubMed]
7. Tong H, Sun J, Fang J, Zhang M, Liu H, Xia R, Zhou W, Liu K, Chen X. A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts Tumor Immune Profiles in Non-Small Cell Lung Cancer: A Retrospective Multicohort Study. Front Immunol 2022;13:859323. [Crossref] [PubMed]
8. Lee G, Park H, Bak SH, Lee HY. Radiomics in Lung Cancer from Basic to Advanced: Current Status and Future Directions. Korean J Radiol 2020;21:159-71. [Crossref] [PubMed]
9. Wei N, Xu Y, Li Y, Shi J, Zhang X, You Y, Sun Q, Zhai H, Hu Y. A bibliometric analysis of T cell and atherosclerosis. Front Immunol 2022;13:948314. [Crossref] [PubMed]
10. Liu W. Caveats for the use of Web of Science Core Collection in old literature retrieval and historical bibliometric analysis. Technological Forecasting and Social Change 2021;172:121023.
11. Meshkani Z, Moradi N, Aboutorabi A, Noman S, Motlagh AG, Langarizadeh M. Systematic review of women's knowledge, attitude, and practice towards breast cancer. J Educ Health Promot 2022;11:171. [Crossref] [PubMed]
12. Volpe S, Mastroleo F, Krengli M, Jereczek-Fossa BA. Quo vadis Radiomics? Bibliometric analysis of 10-year Radiomics journey. Eur Radiol 2023;33:6736-45. [Crossref] [PubMed]
13. van Eck NJ, Waltman L. Software survey: VOSviewer, a computer program for bibliometric mapping. Scientometrics 2010;84:523-38. [Crossref] [PubMed]
14. Zhang L, Zheng H, Jiang ST, Liu YG, Zhang T, Zhang JW, Lu X, Zhao HT, Sang XT, Xu YY. Worldwide research trends on tumor burden and immunotherapy: a bibliometric analysis. Int J Surg 2024;110:1699-710. [Crossref] [PubMed]
15. Ali MJ. Understanding the 'g-index' and the 'e-index'. Semin Ophthalmol 2021;36:139. [Crossref] [PubMed]
16. Luc JGY, Norton EL, Castro-Varela A, Russell JL, Miter SL. Role of the m-Index in Leveling the Playing Field. Ann Thorac Surg 2024;117:1068-9. [Crossref] [PubMed]
17. Radford DM, Parangi S, Tu C, Silver JK. h-Index and Academic Rank by Gender Among Breast Surgery Fellowship Faculty. J Womens Health (Larchmt) 2022;31:110-6. [Crossref] [PubMed]
18. Bertoli-Barsotti L, Lando T. A theoretical model of the relationship between the h-index and other simple citation indicators. Scientometrics 2017;111:1415-48. [Crossref] [PubMed]
19. Manafi-Farid R, Karamzade-Ziarati N, Vali R, Mottaghy FM, Beheshti M. 2-[18F]FDG PET/CT radiomics in lung cancer: An overview of the technical aspect and its emerging role in management of the disease. Methods 2021;188:84-97.
20. Tang G, Du L, Ling S, Che Y, Chen X. Multi-type classification of lung nodules based on CT radiomics and ensemble learning for diversity weighting. Quant Imaging Med Surg 2024;14:8942-65. [Crossref] [PubMed]
21. Zwanenburg A, Vallières M, Abdalah MA, Aerts HJWL, Andrearczyk V, Apte A, et al. The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. Radiology 2020;295:328-38. [Crossref] [PubMed]
22. Nardone V, Tini P, Pastina P, Botta C, Reginelli A, Carbone SF, et al. Radiomics predicts survival of patients with advanced non-small cell lung cancer undergoing PD-1 blockade using Nivolumab. Oncol Lett 2020;19:1559-66. [Crossref] [PubMed]
23. Alahmari SS, Cherezov D, Goldgof D, Hall L, Gillies RJ, Schabath MB. Delta Radiomics Improves Pulmonary Nodule Malignancy Prediction in Lung Cancer Screening. IEEE Access 2018;6:77796-806.
24. Han X, Wang M, Zheng Y, Wang N, Wu Y, Ding C, Jia X, Yang R, Geng M, Chen Z, Zhang S, Zhang K, Li Y, Liu J, Gu J, Liao Y, Fan J, Shi H. Delta-radiomics features for predicting the major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer. Eur Radiol 2024;34:2716-26. [Crossref] [PubMed]
25. Huang D, Li Z, Jiang T, Yang C, Li N. Artificial intelligence in lung cancer: current applications, future perspectives, and challenges. Front Oncol 2024;14:1486310. [Crossref] [PubMed]
26. Wu FZ, Wu YJ, Tang EK. An integrated nomogram combined semantic-radiomic features to predict invasive pulmonary adenocarcinomas in subjects with persistent subsolid nodules. Quant Imaging Med Surg 2023;13:654-68. [Crossref] [PubMed]
27. Fornacon-Wood I, Faivre-Finn C, O'Connor JPB, Price GJ. Radiomics as a personalized medicine tool in lung cancer: Separating the hope from the hype. Lung Cancer 2020;146:197-208. [Crossref] [PubMed]
28. Kothari G, Korte J, Lehrer EJ, Zaorsky NG, Lazarakis S, Kron T, Hardcastle N, Siva S. A systematic review and meta-analysis of the prognostic value of radiomics based models in non-small cell lung cancer treated with curative radiotherapy. Radiother Oncol 2021;155:188-203. [Crossref] [PubMed]
29. Jia X, Wang Y, Zhang H, Sun D. Current status and quality of prognosis prediction models of non-small cell lung cancer constructed using computed tomography (CT)-based radiomics: a systematic review and radiomics quality score 2.0 assessment. Quant Imaging Med Surg 2024;14:6978-89. [Crossref] [PubMed]
30. Ninomiya K, Arimura H. Homological radiomics analysis for prognostic prediction in lung cancer patients. Phys Med 2020;69:90-100. [Crossref] [PubMed]
31. Liu C, Ma C, Duan J, Qiu Q, Guo Y, Zhang Z, Yin Y. Using CT texture analysis to differentiate between peripheral lung cancer and pulmonary inflammatory pseudotumor. BMC Med Imaging 2020;20:75. [Crossref] [PubMed]
32. Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, Bussink J, Monshouwer R, Haibe-Kains B, Rietveld D, Hoebers F, Rietbergen MM, Leemans CR, Dekker A, Quackenbush J, Gillies RJ, Lambin P. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 2014;5:4006. [Crossref] [PubMed]
33. Besse B, Felip E, Garcia Campelo R, Cobo M, Mascaux C, Madroszyk A, et al. Randomized open-label controlled study of cancer vaccine OSE2101 versus chemotherapy in HLA-A2-positive patients with advanced non-small-cell lung cancer with resistance to immunotherapy: ATALANTE-1. Ann Oncol 2023;34:920-33. [Crossref] [PubMed]
34. Walls GM, Osman SOS, Brown KH, Butterworth KT, Hanna GG, Hounsell AR, McGarry CK, Leijenaar RTH, Lambin P, Cole AJ, Jain S. Radiomics for Predicting Lung Cancer Outcomes Following Radiotherapy: A Systematic Review. Clin Oncol (R Coll Radiol) 2022;34:e107-22. [Crossref] [PubMed]
35. van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, Beets-Tan RGH, Fillion-Robin JC, Pieper S, Aerts HJWL. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res 2017;77:e104-7. [Crossref] [PubMed]
36. Saad MB, Hong L, Aminu M, Vokes NI, Chen P, Salehjahromi M, et al. Predicting benefit from immune checkpoint inhibitors in patients with non-small-cell lung cancer by CT-based ensemble deep learning: a retrospective study. Lancet Digit Health 2023;5:e404-20. [Crossref] [PubMed]
37. Wang T, She Y, Yang Y, Liu X, Chen S, Zhong Y, Deng J, Zhao M, Sun X, Xie D, Chen C. Radiomics for Survival Risk Stratification of Clinical and Pathologic Stage IA Pure-Solid Non-Small Cell Lung Cancer. Radiology 2022;302:425-34. [Crossref] [PubMed]
38. Liu A, Wang Z, Yang Y, Wang J, Dai X, Wang L, Lu Y, Xue F. Preoperative diagnosis of malignant pulmonary nodules in lung cancer screening with a radiomics nomogram. Cancer Commun (Lond) 2020;40:16-24. [Crossref] [PubMed]
39. Wang R, Dai W, Gong J, Huang M, Hu T, Li H, Lin K, Tan C, Hu H, Tong T, Cai G. Development of a novel combined nomogram model integrating deep learning-pathomics, radiomics and immunoscore to predict postoperative outcome of colorectal cancer lung metastasis patients. J Hematol Oncol 2022;15:11. [Crossref] [PubMed]
40. Zhang C. de A F Fonseca L, Shi Z, Zhu C, Dekker A, Bermejo I, Wee L. Systematic review of radiomic biomarkers for predicting immune checkpoint inhibitor treatment outcomes. Methods 2021;188:61-72. [Crossref] [PubMed]
41. Sako C, Schmidt TG, Patel AA, Owen DH, Amini A, Curti BD, et al. 1237 Deep learning serial CT response score predicts overall survival in advanced NSCLC treated with PD-(L)1 immune checkpoint inhibitors. Journal for ImmunoTherapy of Cancer 2024; [Crossref]
42. Liu Y, Wu M, Zhang Y, Luo Y, He S, Wang Y, Chen F, Liu Y, Yang Q, Li Y, Wei H, Zhang H, Jin C, Lu N, Li W, Wang S, Guo Y, Ye Z. Imaging Biomarkers to Predict and Evaluate the Effectiveness of Immunotherapy in Advanced Non-Small-Cell Lung Cancer. Front Oncol 2021;11:657615. [Crossref] [PubMed]
43. Wu G, Woodruff HC, Shen J, Refaee T, Sanduleanu S, Ibrahim A, Leijenaar RTH, Wang R, Xiong J, Bian J, Wu J, Lambin P. Diagnosis of Invasive Lung Adenocarcinoma Based on Chest CT Radiomic Features of Part-Solid Pulmonary Nodules: A Multicenter Study. Radiology 2020;297:451-8. [Crossref] [PubMed]
44. Grossmann P, Stringfield O, El-Hachem N, Bui MM, Rios Velazquez E, Parmar C, Leijenaar RT, Haibe-Kains B, Lambin P, Gillies RJ, Aerts HJ. Defining the biological basis of radiomic phenotypes in lung cancer. Elife 2017;6:e23421. [Crossref] [PubMed]