Predictive value of multiple imaging predictive models for spread through air spaces of lung adenocarcinoma: A systematic review and network meta‑analysis
- Authors:
- Published online on: January 25, 2024 https://doi.org/10.3892/ol.2024.14255
- Article Number: 122
-
Copyright: © Liu et al. This is an open access article distributed under the terms of Creative Commons Attribution License.
Abstract
Introduction
Lung cancer, particularly lung adenocarcinoma (LUAD), is a major contributor to cancer-associated mortality worldwide, accounting for approximately 11.4% of all global cancer cases and 18.0% of cancer-related deaths. This prominence is potentially linked to its unique patterns of invasion. (1). Aside from infiltration of myofibroblast stroma, lymphovascular and pleural invasion, spread through air spaces (STAS) has emerged as an invasion pattern in LUAD (2). It was identified initially by Kadota et al (3) and recognized as a distinct form of tumor spread in the 2015 World Health Organization classification (3). STAS is characterized by presence of micropapillary clusters, solid nests or individual cells in lung parenchyma air spaces beyond the tumor margin (4). The current diagnostic methodology for STAS is analysis of pathological specimens obtained from lung tissues excised during surgical procedures in patients (5). It is found in 14.8–56.4% of LUAD cases and is associated with lower survival rates and a worse prognosis compared with STAS-negative tumors. Therefore, identification of STAS can provide key information for the clinical treatment of patients with LUAD (6,7). Reports indicate a significant risk of local and distant recurrence in STAS-positive cases treated with sublobar resection (3,8), whereas patients who undergo lobectomy have no increased recurrence risk. Thus, early detection of STAS is of clinical importance.
Radiomics, the conversion of radiographic images into quantifiable information, offers the potential to improve diagnosis, prognosis and the development of predictive models (9–11). Previous advancements in predicting STAS status in LUAD using radiomics methods reported promising results (12,13). However, bridging the gap between radiomics as a research tool and its clinical implementation presents challenges, including technical reproducibility, clinical validity, quantification and cost-effectiveness. There is also notable heterogeneity in previous studies, with lack of comprehensive evaluation of the performance of radiomics in predicting STAS in LUAD (14). Identifying factors affecting the predictive performance of radiomics is key for its clinical use. Several radiomics models employing computed tomography (CT), magnetic resonance imaging and positron emission tomography (PET)/CT have been developed for predicting STAS, showing diverse performance and indicating methodological variability (15,16). However, to date, there are no relevant network meta-analyses to evaluate the predictive value of these models, to the best of our knowledge. Therefore, the present study aimed to assess the risk of bias and methodological quality and to perform a network meta-analysis (NMA) to evaluate the effectiveness of radiomics models in predicting preoperative STAS in LUAD. This may be valuable for clinicians, radiologists and researchers in the field of LUAD diagnosis and treatment.
Materials and methods
Protocol and registration
The present review was performed in accordance with AMSTAR 2 (17). The methods and protocol for the present study were pre-registered, in accordance with standard procedures, in the International Platform of Registered Systematic Review and Meta-analysis Protocols (registration no. 202390105; DOI: 10.37766/inplasy2023.9.0105).
Retrieval strategy
A comprehensive literature search was performed using the following key terms: ‘Risk factor’, ‘predictive’, ‘spread through air spaces’, ‘lung adenocarcinoma’ and ‘nomograms’. This search used the PubMed (pubmed.ncbi.nlm.nih.gov/), Embase (embase.com/),Scopus(https://www.scopus.com/),Wiley(https://onlinelibrary.wiley.com/) and Web of Science(https://www.webofscience.com/wos/) databases, with a cut-off date of May 1, 2023. The references of included studies were also systematically reviewed to obtain potentially relevant publications (Table I).
Inclusion and exclusion criteria
The inclusion criteria included the following: i) Study focuses on patients who have been diagnosed with LUAD and who exhibit STAS; ii) objective of the study is to develop a predictive model to accurately identify the presence of STAS in patients with LUAD. Tumor STAS was defined as tumor cells (micropapillary structures, solid nests, or single cells-spreading within air spaces in the lung parenchyma beyond the edge of the main tumor (3). The present study selected studies that included patients who underwent segmental or lobar resection.
The exclusion criteria were as follows: i) Predictive models that were not constructed based on radiological features; ii) no clear inclusion and exclusion criteria; iii) reviews and lecture-type literature; iv) literature for which the full text could not be obtained and v) literature for which data could not be extracted.
Literature screening
The initial screening of titles and abstracts was independently conducted by two researchers (CL and PW) using Cochrane handbook's guidelines for systematic reviews of interventions (18), adhering to the predefined inclusion and exclusion criteria. Discrepancies or uncertainty about article inclusion were resolved through discussion or consultation with a third reviewer (XL).
Quality evaluation of literature
The quality of articles was assessed by two independent reviewers using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) (19), which is a tool for assessing quality of diagnostic studies, focusing on ‘risk-of-bias’ and ‘applicability concerns’. The risk-of-bias was assessed across four domains: Patient selection, index test, reference standard and flow and timing. The applicability was evaluated for the first three domains and rated as ‘yes’, ‘no’ or ‘unclear’, with ‘yes’ denoting low risk, ‘no’ indicating high risk and ‘unclear’ suggesting insufficient information. In cases of disagreement, a third reviewer was used for resolution. A Measurement Tool to Assess systematic Reviews was used for a stringent quality assessment (14).
Additionally, the methodological quality of studies was appraised using the Cochrane Handbook's risk-of-bias assessment tool (RevMan v.5.3.5, The Cochrane Collaboration) (20), covering six aspects (selection, performance bias, detection, attrition, reporting bias and other bias), which were categorized as ‘yes’, ‘no’ or ‘unclear’ to indicate the level of bias.
Data extraction
The data extracted primarily encompassed the following aspects: i) Characteristics of the included literature, such as author information, publication date, country of origin, predictive models and regression methods employed and predictive factors investigated; ii) details of the study subjects, such as sample size, sex distribution and tumor stage (according to the 8th edition of the AJCC staging standards) (21), with all participants having undergone surgery and iii) evaluation of effect indicators.
Statistical analysis
The effectiveness of various predictive models were evaluated based on their accuracy, sensitivity (SEN), and specificity (SPE). Predictive models were categorized according to their unique features for NMA to assess performance in predicting STAS. This NMA, conducted using Stata software (version 17.0; StataCorp LP) within a Bayesian framework, used the Markov Chain Monte Carlo Subset Simulation (22) in accordance with the PRISMA NMA guidelines (23). A nodal approach for quantifying and clarifying concordance between direct and indirect comparisons was adopted. The consistency criterion for the NMA was P>0.05. Network diagrams visually represented diagnostic methods, with nodes symbolizing each method and lines representing direct comparisons. The size of nodes and thickness of lines corresponded to the number of studies. To detect possible publication bias in selected studies, funnel plots were constructed for each measure of diagnostic efficiency, employing symmetry criteria as a key validation technique. Statistical heterogeneity was evaluated using I2 statistic, a measure in meta-analytical methods. This quantifies the proportion of the total variation in study estimates due to heterogeneity rather than chance. An I2 value of 0% indicates no observed heterogeneity, whilst higher values suggest increasing heterogeneity, with guidelines typically considering 25, 50 and 75% as low, moderate and high heterogeneity, respectively (18). Additionally, to ascertain the relative superiority of one method, the level of certainty for predictive models was quantified. This assessment was performed using surface under the cumulative ranking curve (SUCRA), forest plots and league tables.
Subgroup diagnostic meta-analyses were performed using Stata to assess relative predictive efficiency of composite models. The effectiveness of these models was evaluated using the area under the curve (AUC) derived from the summary receiver operating characteristics (sROC). Additionally, the Fagan plot was utilized to quantify the overall discriminatory power of a diagnostic test (24).
Results
Selection and characteristics of literature
Literature review was performed using 565 articles. Subsequent to this, a meticulous screening process was undertaken to ensure the relevance and quality of sources. This entailed the removal of 249 articles due to duplication. Further scrutiny, focusing on titles and abstracts, led to the exclusion of an additional 288 articles that were not pertinent. The remaining pool of 28 articles was subjected to a more rigorous evaluation, which included accessibility of full-text versions and the feasibility of data extraction. This process led to the disqualification of 14 articles, leaving a final count of 14 articles (Fig. 1).
These 14 articles, collectively encompassing data from 3,734 participants, were exclusively focused on patients diagnosed with STAS in LUAD. The predictive models were categorized into the following four distinct types based on their methodological approaches and radiological characteristics: i) Models developed using logistic regression analysis to screen CT features (Features_CT); ii) models using machine learning (ML) techniques to screen tumor radiological characteristics (ML_Tumour); iii) models applying ML for the screening of both tumor and peritumor radiological features (ML_Peri_tumour) and iv) models that used logistic regression analysis for screening of PET/CT features (pet_CT).
In the process of tumor and peritumor segmentation, the open-source software 3D Slicer v4.8.1 (slicer.org) was used. Moreover, all studies used pathological findings as a benchmark, forming a control group against which predictive models were evaluated. The data enabling direct comparative analysis in outcomes were also assessed (Table II) (5,15,16,25–35).
Quality assessment and publication bias
In the present study involving 14 articles and 17 predictive models, NMA was performed using Stata and the QUADAS-2 tool was used to assess quality, risk of bias and applicability of the articles. The inter-rater reliability (κ-agreement) between the reviewers was 0.87. A high risk of bias was detected in a few articles (3/14) in terms of patient selection (1/14) and reference standards (2/14); however, the overall quality of the publications was satisfactory (Fig. 2).
NMA
NMA evaluated the relative risk (RR) values and 95% confidence intervals (CI) across different predictive models in terms of accuracy, SEN and SPE for STAS in LUAD.
Pairwise meta-analysis
NMA graph illustrates the comparative accuracy, SEN and SPE of predictive models (Fig. 3). Notably, CT_feature model group encompassed the largest sample size, followed by the ML_Peri_tumour model. Specifically, two studies directly compared the CT_feature and ML_Peri_tumour model, and one study contrasted the CT_feature model with ML_Tumour model (Fig. 3). Furthermore, the comprehensive evaluation of the included studies spanned all domains. Potential publication bias was assessed using funnel plots (Fig. 4). The roughly symmetric distribution suggested a negligible presence of publication bias or other forms of bias within the studies. This symmetry bolstered the reliability of findings.
Accuracy
Using the SUCRA, the accuracy of several predictive models for STAS was evaluated. Models ranked in descending order of accuracy were as follows: Control (100.0%); ML_Peri_tumour (56.5%); ML_Tumour (41.8%); pet_CT (41.4%) and Features_CT (10.3%; Fig. 5A). A detailed two-by-two comparative analysis is presented in Table IIIA, highlighting the predictive efficacy of these models. ML_Peri_tumour model demonstrated superior accuracy, particularly compared with Features_CT (RR=1.14; 95% CI, 0.99–1.32), ML_Tumour (RR=1.04; 95% CI, 0.83–1.30) and pet_CT (RR=1.04; 95% CI, 0.84–1.29). A heterogeneity test revealed I2 value of 20.4%. Consistently, the forest plot demonstrated the highest predictive accuracy for ML_Peri_tumour model (Fig. 6A).
SEN
SEN for different predictive models for STAS, derived from the SUCRA was as follows: Control (99.9%); Features_CT (51.9%); ML_Peri_tumour (49.9%); ML_Tumour (42.8%); and pet_CT (5.5%; Fig. 5B). Table IIIB shows a comparative league table for a two-by-two analysis of these models. Features_CT model exhibited superior SEN, especially compared with ML_Peri_tumour (RR=1.00; 95% CI, 0.89–1.13), ML_Tumour (RR=1.02; 95% CI, 0.88–1.18) and pet_CT (RR=1.17; 95% CI, 0.97–1.40). The heterogeneity test indicated an I2 of 17.8%. Additionally, forest plot highlighted the superior predictive SEN of the Features_CT model (Fig. 6B).
SPE
SPE of different predictive models for STAS, ascertained using the SUCRA, was as follows: Control (99.7%); pet_CT (53.9%); ML_Peri_tumour (48.0%); ML_Tumour (42.7%); and Features_CT (5.7%; Fig. 5C). A comprehensive league table in Table IIIC compares these models in a two-by-two format. The pet_CT model showed enhanced SPE, particularly against ML_Peri_tumour (RR=1.03; 95% CI, 0.77–1.39), ML_Tumour (RR=1.05; 95% CI, 0.74–1.50) and Features_CT (RR=1.24; 95% CI, 0.95–1.62). The heterogeneity test yielded I2 of 9.1%. The forest plot indicated the superior predictive SPE of the pet_CT model (Fig. 6C).
Subgroup diagnostic MA
Diagnostic MA scrutinized the predictive capabilities of the ML_Peri_tumour and Features_CT models. AUC of the sROC for the ML_Peri_tumour model was 0.86 (95% CI, 0.82–0.88), while for the Features_CT model it was 0.81 (95% CI, 0.77–0.84; Fig. 7A and B, respectively). Fagan plot analysis, which assessed the predictive potency of models, demonstrated the relative superiority of the ML_Peri_tumour model (Fig. 7C and D).
Discussion
The present MA evaluated predictive accuracy of several models for STAS in LUAD. Analyzing 14 studies encompassing 3,734 patients, four predictive models were assessed. Among these, the ML_Peri_tumour model, using ML to analyze tumor and peritumor radiographic features, was the most effective. This model demonstrated superior performance in accuracy, SEN and SPE, evidenced by its SUCRA values of 56.5, 49.9 and 48.0, respectively. Furthermore, a diagnostic MA supported the efficacy of the ML_Peri_tumour model, indicating a pooled AUC of 0.86 (95% CI, 0.82–0.88).
Previous studies have substantially deepened understanding of STAS in LUAD, especially regarding its prediction via radiological and pathological features (36,37). Investigations into predictive CT characteristics for STAS in small-sized LUAD have reported that attributes such as consolidation tumor ratio, spiculation, satellites, ground glass ribbon sign, pleural attachment and unclear tumor-lung interface are effective predictors of STAS (30,38). This aligns with the present accuracy of the ML_Peri_tumour and other ML-based models, underscoring the significance of CT features in these models.
The evolving understanding of the association between tumor stromal cells and STAS, along with the role of stromal cells in STAS pathogenesis, is noteworthy. Advanced medical information technology, including three-dimensional space convolution and fuzzy neural networks, has demonstrated potential in enhancing diagnostic SEN and SPE for lung cancer, suggesting promising avenues for future STAS prediction models (39).
Another notable development is the association between fluorodeoxyglucose (FDG) metabolic tumor burden, measured by PET/CT and STAS. Studies using PET/CT metrics such as standardized uptake value and total lesion glycolysis have reported that LUAD with low FDG uptake is associated with a lower incidence of STAS, whilst subtypes with higher FDG uptake, such as solid predominant adenocarcinoma, show a higher incidence of STAS (34,35). Furthermore, integration of ML techniques for analyzing radiological data for tumor and peritumor features has resulted in models with improved predictive accuracy for STAS. A study by Liao et al (5) involving 256 patients, integrated tumor radiomic signature (TRS) with peritumoral radiomic signatures (PRS) and developed an effective gross radiomic signature model. Particularly, TRS combined with the PRS-15 mm model exhibited substantial predictive accuracy, achieving an AUC of 0.854 in the development and 0.870 in the validation cohort. The focus on the peritumoral environment represents a notable advancement over prior research (28), which predominantly concentrated on the primary tumor alone. The success of the ML_Peri_tumour model in the present study highlights the potential of merging radiomic features from both tumor and peritumor regions, providing a more comprehensive approach to STAS prediction. This is relevant since STAS, typically found at the tumor periphery, may be more accurately predicted using preoperative CT images of tumor margins (26,33).
The present analysis revealed that the majority of radiomics studies on STAS prediction were in early or intermediate stages of research. The rigorous design of these studies is vital for validating the feasibility of radiological approaches. The present study identified limitations, including a lack of reproducibility analysis, internal validation and comprehensive performance evaluation of models. Notably, none of the included studies performed phantom or test-retest analyses for validating feature robustness (40,41) and only three studies addressed calibration, which is a key metric for evaluating prediction consistency with actual outcomes (5,15,32). To advance clinical application and practicality of radiomics, attention must be paid to external validation, cost-effectiveness and availability of open data. Validation with data from other institutions or different time periods is key for confirming model generalizability (42). However, only one study in the present analysis validated radiomic signatures with external data (15). Furthermore, a lack of open data and code availability, essential for assessing reproducibility, was a common limitation across studies (43). In the present NMA, included studies encompassed two different regression methods for constructing predictive models: ML (6/14) and binary logistic regression (8/14). ML focuses on the accuracy of the final model, while binary logistic regression also pays attention to metrics such as the odds ratio for each variable (44). The present research did not reveal any heterogeneity between different types of regression method. However, the comprehensive analysis indicated that the ML_Peri_tumour model held greater value in predicting STAS, potentially due to its consideration of radiomic signatures in the peritumoral region. Nevertheless, use of models developed using diverse regression methods is a limitation of the present study. To enhance robustness and comprehensiveness of results of the present study, the incorporation of additional studies for detailed subgroup analyses is key. Additionally, 8/14 studies reviewed focused on the occurrence of STAS in patients with stage I LUAD. However, the MA did not demonstrate inter-study heterogeneity in this aspect. There is need for more research to evaluate the predictive efficiency of radiomic models for STAS in early-stage LUAD, where accurate diagnosis is of paramount importance. Assessing STAS status prior to developing a surgical plan is key, as it significantly influences the selection of surgical strategies.
In conclusion, the present study is the first NMA to integrate several predictive models, to the best of our knowledge. The findings underscore the superior predictive efficacy of tumor and peritumor-based radiological models. Nonetheless, research in radiological features for STAS prediction is in its early stages, and significant enhancements are needed, particularly in technical reproducibility and comprehensive model evaluation. The reliability of these studies requires experimental verification due to limited external validation. Additionally, the scarcity of direct model comparisons in the analyzed studies, primarily relying on indirect comparisons, may affect quality assessment results, underscoring the need for more direct model comparisons in future. The ethnographic and geographic applicability of these findings, primarily contributed to by researchers in Asia, also needs further validation.
Acknowledgements
Not applicable.
Funding
The present study was supported by the Clinical Medicine Science and Technology Development Foundation of Jiangsu University (grant no. JLY2021082) and Xuzhou Science and Technology Bureau (grant no. KC23229).
Availability of data and materials
The data generated in the present study may be requested from the corresponding author.
Authors' contributions
XL designed the study and revised the manuscript. CL performed statistical analysis and wrote the manuscript. CL and PW performed the literature review and quality assessment. PW, YW, FG and ZS interpreted the data. CL and XL confirm the authenticity of all the raw data. HZ and QW were involved in the study design and critically revised the manuscript. All authors have read and approved the final manuscript.
Ethics approval and consent to participate
Not applicable.
Patient consent for publication
Not applicable.
Competing interests
The authors declare that they have no competing interests.
References
|
Zhuo Y, Feng M, Yang S, Zhou L, Ge D, Lu S, Liu L, Shan F and Zhang Z: Radiomics nomograms of tumors and peritumoral regions for the preoperative prediction of spread through air spaces in lung adenocarcinoma. Transl Oncol. 13:1008202020. View Article : Google Scholar : PubMed/NCBI | |
|
Blaauwgeers H, Flieder D, Warth A, Harms A, Monkhorst K, Witte B and Thunnissen E: A prospective study of loose tissue fragments in non-small cell lung cancer resection specimens: An alternative view to ‘spread through air spaces’. Am J Surg Pathol. 41:1226–1230. 2017. View Article : Google Scholar : PubMed/NCBI | |
|
Kadota K, Nitadori JI, Sima CS, Ujiie H, Rizk NP, Jones DR, Adusumilli PS and Travis WD: Tumor spread through air spaces is an important pattern of invasion and impacts the frequency and location of recurrences after limited resection for small stage I lung adenocarcinomas. J Thorac Oncol. 10:806–814. 2015. View Article : Google Scholar : PubMed/NCBI | |
|
Travis WD, Brambilla E, Nicholson AG, Yatabe Y, Austin JHM, Beasley MB, Chirieac LR, Dacic S, Duhig E, Flieder DB, et al: The 2015 world health organization classification of lung tumors: Impact of genetic, clinical and radiologic advances since the 2004 classification. J Thorac Oncol. 10:1243–1260. 2015. View Article : Google Scholar : PubMed/NCBI | |
|
Liao G, Huang L, Wu S, Zhang P, Xie D, Yao L, Zhang Z, Yao S, Shanshan L, Wang S, et al: Preoperative CT-based peritumoral and tumoral radiomic features prediction for tumor spread through air spaces in clinical stage I lung adenocarcinoma. Lung Cancer. 163:87–95. 2022. View Article : Google Scholar : PubMed/NCBI | |
|
Terada Y, Takahashi T, Morita S, Kashiwabara K, Nagayama K, Nitadori JI, Anraku M, Sato M, Shinozaki-Ushiku A and Nakajima J: Spread through air spaces is an independent predictor of recurrence in stage III (N2) lung adenocarcinoma. Interact Cardiovasc Thorac Surg. 29:442–448. 2019. View Article : Google Scholar : PubMed/NCBI | |
|
Niu Y, Han X, Zeng Y, Nanding A, Bai Q, Guo S, Hou Y, Yu Y, Zhang Q and Li X: The significance of spread through air spaces in the prognostic assessment model of stage I lung adenocarcinoma and the exploration of its invasion mechanism. J Cancer Res Clin Oncol. 149:7125–7138. 2023. View Article : Google Scholar : PubMed/NCBI | |
|
Eguchi T, Kameda K, Lu S, Bott MJ, Tan KS, Montecalvo J, Chang JC, Rekhtman N, Jones DR, Travis WD and Adusumilli PS: Lobectomy is associated with better outcomes than sublobar resection in spread through air spaces (STAS)-positive T1 lung adenocarcinoma: A propensity score-matched analysis. J Thorac Oncol. 14:87–98. 2019. View Article : Google Scholar : PubMed/NCBI | |
|
Ji GW, Zhang YD, Zhang H, Zhu FP, Wang K, Xia YX, Zhang YD, Jiang WJ, Li XC and Wang XH: Biliary tract cancer at CT: A radiomics-based model to predict lymph node metastasis and survival outcomes. Radiology. 290:90–98. 2019. View Article : Google Scholar : PubMed/NCBI | |
|
Autorino R, Gui B, Panza G, Boldrini L, Cusumano D, Russo L, Nardangeli A, Persiani S, Campitelli M, Ferrandina G, et al: Radiomics-based prediction of two-year clinical outcome in locally advanced cervical cancer patients undergoing neoadjuvant chemoradiotherapy. Radiol Med. 127:498–506. 2022. View Article : Google Scholar : PubMed/NCBI | |
|
Cong H, Peng W, Tian Z, Vallières M, Chuanpei X, Aijun Z and Benxin Z: FDG-PET/CT radiomics models for the early prediction of locoregional recurrence in head and neck cancer. Curr Med Imaging. 17:374–383. 2021. View Article : Google Scholar : PubMed/NCBI | |
|
Jiang C, Luo Y, Yuan J, You S, Chen Z, Wu M, Wang G and Gong J: CT-based radiomics and machine learning to predict spread through air space in lung adenocarcinoma. Eur Radiol. 30:4050–4057. 2020. View Article : Google Scholar : PubMed/NCBI | |
|
Li C, Jiang C, Gong J, Wu X, Luo Y and Sun G: A CT-based logistic regression model to predict spread through air space in lung adenocarcinoma. Quant Imaging Med Surg. 10:1984–1993. 2020. View Article : Google Scholar : PubMed/NCBI | |
|
Liu A, Sun X, Xu J, Xuan Y, Zhao Y, Qiu T, Hou F, Qin Y, Wang Y, Lu T, et al: Relevance and prognostic ability of Twist, Slug and tumor spread through air spaces in lung adenocarcinoma. Cancer Med. 9:1986–1998. 2020. View Article : Google Scholar : PubMed/NCBI | |
|
Chen Y, Jiang C, Kang W, Gong J, Luo D, You S, Cheng Z, Luo Y and Wu K: Development and validation of a CT-based nomogram to predict spread through air space (STAS) in peripheral stage IA lung adenocarcinoma. Jpn J Radiol. 40:586–594. 2022. View Article : Google Scholar : PubMed/NCBI | |
|
Nishimori M, Iwasa H, Miyatake K, Nitta N, Nakaji K, Matsumoto T, Yamanishi T, Yoshimatsu R, Iguchi M, Tamura M and Yamagami T: 18F FDG-PET/CT analysis of spread through air spaces (STAS) in clinical stage I lung adenocarcinoma. Ann Nucl Med. 36:897–903. 2022. View Article : Google Scholar : PubMed/NCBI | |
|
Shea BJ, Reeves BC, Wells G, Thuku M, Hamel C, Moran J, Moher D, Tugwell P, Welch V, Kristjansson E and Henry DA: AMSTAR 2: A critical appraisal tool for systematic reviews that include randomised or non-randomised studies of healthcare interventions, or both. BMJ. 358:j40082017. View Article : Google Scholar : PubMed/NCBI | |
|
Higgins JPT, Thomas J, Chandler J, Cumpston M, Li T, Page MJ and Welch VA: Cochrane handbook for systematic reviews of interventions version 6.4 (updated August 2023). Cochrane; 2023 | |
|
Whiting PF, Rutjes AW, Westwood ME, Mallett S, Deeks JJ, Reitsma JB, Leeflang MM, Sterne JA and Bossuyt PM; QUADAS-2 group, : QUADAS-2: A revised tool for the quality assessment of diagnostic accuracy studies. Ann Intern Med. 155:529–536. 2011. View Article : Google Scholar : PubMed/NCBI | |
|
Wang SR, Li QL, Tian F, Li J, Li WX, Chen M, Sang T, Cao CL and Shi LN: Diagnostic value of multiple diagnostic methods for lymph node metastases of papillary thyroid carcinoma: A systematic review and meta-analysis. Front Oncol. 12:9906032022. View Article : Google Scholar : PubMed/NCBI | |
|
Kutob L and Schneider F: Lung cancer staging. Surg Pathol Clin. 13:57–71. 2020. View Article : Google Scholar : PubMed/NCBI | |
|
Heinecke A, Tallarita M and De Iorio M: Bayesian splines versus fractional polynomials in network meta-analysis. BMC Med Res Methodol. 20:2612020. View Article : Google Scholar : PubMed/NCBI | |
|
Hutton B, Salanti G, Caldwell DM, Chaimani A, Schmid CH, Cameron C, Ioannidis JP, Straus S, Thorlund K, Jansen JP, et al: The PRISMA extension statement for reporting of systematic reviews incorporating network meta-analyses of health care interventions: Checklist and explanations. Ann Intern Med. 162:777–784. 2015. View Article : Google Scholar : PubMed/NCBI | |
|
Kapor S, Rankovic MJ, Khazaei Y, Crispin A, Schüler I, Krause F, Lussi A, Neuhaus K, Eggmann F, Michou S, et al: Systematic review and meta-analysis of diagnostic methods for occlusal surface caries. Clin Oral Investig. 25:4801–4815. 2021. View Article : Google Scholar : PubMed/NCBI | |
|
Bassi M, Russomando A, Vannucci J, Ciardiello A, Dolciami M, Ricci P, Pernazza A, D'Amati G, Terracciano CM, Faccini R, et al: Role of radiomics in predicting lung cancer spread through air spaces in a heterogeneous dataset. Transl Lung Cancer Res. 11:560–571. 2022. View Article : Google Scholar : PubMed/NCBI | |
|
Qi L, Li X, He L, Cheng G, Cai Y, Xue K and Li M: Comparison of diagnostic performance of spread through airspaces of lung adenocarcinoma based on morphological analysis and perinodular and intranodular radiomic features on chest CT images. Front Oncol. 11:6544132021. View Article : Google Scholar : PubMed/NCBI | |
|
Chen LW, Lin MW, Hsieh MS, Yang SM, Wang HJ, Chen YC, Chen HY, Hu YH, Lee CE, Chen JS, et al: Radiomic values from high-grade subtypes to predict spread through air spaces in lung adenocarcinoma. Ann Thorac Surg. 114:999–1006. 2022. View Article : Google Scholar : PubMed/NCBI | |
|
Kim SK, Kim TJ, Chung MJ, Kim TS, Lee KS, Zo JI and Shim YM: Lung Adenocarcinoma: CT features associated with spread through air spaces. Radiology. 289:831–840. 2018. View Article : Google Scholar : PubMed/NCBI | |
|
Qin L, Sun Y, Zhu R, Hu B and Wu J: Clinicopathological and CT features of tumor spread through air space in invasive lung adenocarcinoma. Front Oncol. 12:9591132022. View Article : Google Scholar : PubMed/NCBI | |
|
Qi L, Xue K, Cai Y, Lu J, Li X and Li M: Predictors of CT morphologic features to identify spread through air spaces preoperatively in small-sized lung adenocarcinoma. Front Oncol. 10:5484302020. View Article : Google Scholar : PubMed/NCBI | |
|
Zhang Z, Liu Z, Feng H, Xiao F, Shao W, Liang C, Sun H, Gu X and Liu D: Predictive value of radiological features on spread through air space in stage cIA lung adenocarcinoma. J Thorac Dis. 12:6494–6504. 2020. View Article : Google Scholar : PubMed/NCBI | |
|
Han X, Fan J, Zheng Y, Ding C, Zhang X, Zhang K, Wang N, Jia X, Li Y, Liu J, et al: The value of CT-based radiomics for predicting spread through air spaces in stage IA lung adenocarcinoma. Front Oncol. 12:7573892022. View Article : Google Scholar : PubMed/NCBI | |
|
Takehana K, Sakamoto R, Fujimoto K, Matsuo Y, Nakajima N, Yoshizawa A, Menju T, Nakamura M, Yamada R, Mizowaki T and Nakamoto Y: Peritumoral radiomics features on preoperative thin-slice CT images can predict the spread through air spaces of lung adenocarcinoma. Sci Rep. 12:103232022. View Article : Google Scholar : PubMed/NCBI | |
|
Wang XY, Zhao YF, Yang L, Liu Y, Yang YK and Wu N: Correlation analysis between metabolic tumor burden measured by positron emission tomography/computed tomography and the 2015 World Health Organization classification of lung adenocarcinoma, with a risk prediction model of tumor spread through air spaces. Transl Cancer Res. 9:6412–6422. 2020. View Article : Google Scholar : PubMed/NCBI | |
|
Falay O, Selçukbiricik F, Tanju S, Erus S, Kapdağli M, Cesur E, Yavuz Ö, Bulutay P, Firat P, Mandel NM and Dilege Ş: The prediction of spread through air spaces with preoperative 18F-FDG PET/CT in cases with primary lung adenocarcinoma, its effect on the decision for an adjuvant treatment and its prognostic role. Nucl Med Commun. 42:922–927. 2021. View Article : Google Scholar : PubMed/NCBI | |
|
Wang S, Shou H, Wen H, Wang X, Wang H, Lu C, Gu J, Xu F, Zhu Q, Wang L and Ge D: An individual nomogram can reliably predict tumor spread through air spaces in non-small-cell lung cancer. BMC Pulm Med. 22:2092022. View Article : Google Scholar : PubMed/NCBI | |
|
Toki MI, Harrington K and Syrigos KN: The role of spread through air spaces (STAS) in lung adenocarcinoma prognosis and therapeutic decision making. Lung Cancer. 146:127–133. 2020. View Article : Google Scholar : PubMed/NCBI | |
|
Sun F, Huang Y, Yang X, Zhan C, Xi J, Lin Z, Shi Y, Jiang W and Wang Q: Solid component ratio influences prognosis of GGO-featured IA stage invasive lung adenocarcinoma. Cancer Imagin. 20:872020. View Article : Google Scholar | |
|
Bai S, Wang Z, Sun Z and Liu Z: Study on the relationship between lung cancer stromal cells and air cavity diffusion based on an image acquisition system. Contrast Media Mol Imaging. 2022:24921242022. View Article : Google Scholar : PubMed/NCBI | |
|
Li Y, Reyhan M, Zhang Y, Wang X, Zhou J, Zhang Y, Yue NJ and Nie K: The impact of phantom design and material-dependence on repeatability and reproducibility of CT-based radiomics features. Med Phys. 49:1648–1659. 2022. View Article : Google Scholar : PubMed/NCBI | |
|
Steyerberg EW, Vickers AJ, Cook NR, Gerds T, Gonen M, Obuchowski N, Pencina MJ and Kattan MW: Assessing the performance of prediction models: A framework for traditional and novel measures. Epidemiology. 21:128–138. 2010. View Article : Google Scholar : PubMed/NCBI | |
|
Sauerbrei W, Taube SE, McShane LM, Cavenagh MM and Altman DG: Reporting recommendations for tumor marker prognostic studies (REMARK): An abridged explanation and elaboration. J Natl Cancer Inst. 110:803–811. 2018. View Article : Google Scholar : PubMed/NCBI | |
|
Nagendran M, Chen Y, Lovejoy CA, Gordon AC, Komorowski M, Harvey H, Topol EJ, Ioannidis JPA, Collins GS and Maruthappu M: Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies. BMJ. 368:m6892020. View Article : Google Scholar : PubMed/NCBI | |
|
Christodoulou E, Ma J, Collins GS, Steyerberg EW, Verbakel JY and Van Calster B: A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. J Clin Epidemiol. 110:12–22. 2019. View Article : Google Scholar : PubMed/NCBI |
