Serum tumor markers level and their predictive values for solid and micropapillary components in lung adenocarcinoma

18F-FDG PET/CT-based deep learning models and a clinical-metabolic nomogram for predicting high-grade patterns in lung adenocarcinoma

BACKGROUND

To develop and validate deep learning (DL) and traditional clinical-metabolic (CM) models based on 18 F-FDG PET/CT images for noninvasively predicting high-grade patterns (HGPs) of invasive lung adenocarcinoma (LUAD).

METHODS

A total of 303 patients with invasive LUAD were enrolled in this retrospective study; these patients were randomly divided into training, validation and test sets at a ratio of 7:1:2. DL models were trained and optimized on PET, CT and PET/CT fusion images, respectively. CM model was built from clinical and PET/CT metabolic parameters via backwards stepwise logistic regression and visualized via a nomogram. The prediction performance of the models was evaluated mainly by the area under the curve (AUC). We also compared the AUCs of different models for the test set.

RESULTS

CM model was established upon clinical stage (OR: 7.30; 95% CI: 2.46-26.37), cytokeratin 19 fragment 21 - 1 (CYFRA 21-1, OR: 1.18; 95% CI: 0.96-1.57), mean standardized uptake value (SUVmean, OR: 1.31; 95% CI: 1.17-1.49), total lesion glycolysis (TLG, OR: 0.994; 95% CI: 0.990-1.000) and size (OR: 1.37; 95% CI: 0.95-2.02). Both the DL and CM models exhibited good prediction efficacy in the three cohorts, with AUCs ranging from 0.817 to 0.977. For the test set, the highest AUC was yielded by the CT-DL model (0.895), followed by the PET/CT-DL model (0.882), CM model (0.879) and PET-DL model (0.817), but no significant difference was revealed between any two models.

CONCLUSIONS

Deep learning and clinical-metabolic models based on the 18F-FDG PET/CT model could effectively identify LUAD patients with HGP. These models could aid in treatment planning and precision medicine.

CLINICAL TRIAL NUMBER

Not applicable.

Prognostic implications of tumor volume reduction during radiotherapy in locally advanced cervical cancer: a risk-stratified analysis

BACKGROUND

This study aimed to identify key risk factors in locally advanced cervical cancer (LACC) patients receiving radical radiotherapy and to evaluate the prognostic significance of MRI-determined tumor volume regression (TVR) among varying risk groups.

METHODS

We retrospectively analyzed a cohort of 176 cervical cancer patients (stages IIA-IVA) treated with intensity-modulated radiotherapy from January 2012 to December 2020. Three-dimensional MRI scans were utilized to measure TVR and lymph node volume regression (NVR). Kaplan-Meier analysis was employed to assess overall survival (OS), progression-free survival (PFS), local relapse-free survival (LRFS), and distant metastasis-free survival (DMFS). Prognostic factors were further analyzed using Cox proportional hazards models.

RESULTS

A tumor TVR of ≥ 94% was significantly associated with improved 5-year overall survival (OS; 82.7% vs. 49.8%, p < 0.001) and progression-free survival (PFS; 82.5% vs. 51.1%, p < 0.001). Patients with TVR ≥ 94% also demonstrated superior LRFS and DMFS compared to those with TVR < 94% (p < 0.001 and p = 0.012, respectively). In the concurrent chemoradiotherapy (CCRT) subgroup, higher TVR correlated with better prognosis, whereas in patients receiving radiotherapy alone, an increased TVR did not significantly impact OS. Notably, the prognostic value of TVR was most evident in patients with CYFRA21-1 levels below 7.7 ng/ml. In the NVR ≥ 94% subgroup, OS, PFS, and LRFS were significantly better than in patients with NVR < 94% (p < 0.01), with a trend towards improved DMFS observed (p = 0.138).

CONCLUSION

TVR serves as a pivotal prognostic marker in LACC patients with CYFRA21-1 levels below 7.7 ng/ml undergoing CCRT. Additionally, within the lymph node metastasis subgroup, patients achieving a NVR of ≥ 94% demonstrated a notably improved prognosis.

Tumor marker-based RecistTM is superior to RECIST as criteria to predict the long-term benefits of targeted therapy in advanced non-small-cell lung cancer with driver gene mutations

BACKGROUND

Tyrosine kinase inhibitors (TKIs) are standard first-line treatments for advanced non-small-cell lung cancer (NSCLC) with driver gene mutations. The Response Evaluation Criteria in Solid Tumors (RECIST) are limited in predicting long-term patient benefits. A tumour marker-based evaluation criteria, RecistTM, was used to investigate the potential for assessing targeted-therapy efficacy in lung cancer treatment.

METHODS

We retrospectively analysed patients with stage IIIA-IV NSCLC and driver gene mutations, whose baseline tumour marker levels exceeded the pre-treatment cut-off value three-fold and who received TKI-targeted therapy as a first-line treatment. We compared efficacy, progression-free survival (PFS), and overall survival (OS) between RecistTM and RECIST.

FINDINGS

The median PFS and OS differed significantly among treatment-response subgroups based on RecistTM but not RECIST. The predicted 1-, 2-, and 3-year disease-progression risk, according to area under the receiver operating characteristic curve, as well as the 1-, 3-, and 5-year mortality risk, differed significantly between RecistTM and RECIST. The median PFS and OS of tmCR according to RecistTM, was significantly longer than (CR+PR) according to RECIST. Imaging analysis revealed that the ΔPFS was 11.27 and 6.17 months in the intervention and non-intervention groups, respectively, suggesting that earlier intervention could extend patients' PFS.

INTERPRETATION

RecistTM can assess targeted-therapy efficacy in patients with advanced NSCLC and driver gene mutations, along with tumour marker abnormalities. RecistTM surpasses RECIST in predicting short- and long-term patient benefits, and allows the early identification of patients resistant to targeted drugs, enabling prompt intervention and extending the imaging-demonstrated time to progression.

Evaluation of the preoperative neutrophil-to-lymphocyte ratio as a predictor of the micropapillary component of stage IA lung adenocarcinoma

OBJECTIVE

To assess the ability of markers of inflammation to identify the solid or micropapillary components of stage IA lung adenocarcinoma and their effects on prognosis.

METHODS

We performed a retrospective study of clinicopathologic data from 654 patients with stage IA lung adenocarcinoma collected between 2013 and 2019. Logistic regression analysis was used to identify independent predictors of these components, and we also evaluated the relationship between markers of inflammation and recurrence.

RESULTS

Micropapillary-positive participants had high preoperative neutrophil-to-lymphocyte ratios. There were no significant differences in the levels of markers of systemic inflammation between the participants with or without a solid component. Multivariate analysis showed that preoperative neutrophil-to-lymphocyte ratio (odds ratio [OR] = 2.094; 95% confidence interval [CI], 1.668-2.628), tumor size (OR = 1.386; 95% CI, 1.044-1.842), and carcinoembryonic antigen concentration (OR = 1.067; 95% CI, 1.017-1.119) were independent predictors of a micropapillary component. There were no significant correlations between markers of systemic inflammation and the recurrence of stage IA lung adenocarcinoma.

CONCLUSIONS

Preoperative neutrophil-to-lymphocyte ratio independently predicts a micropapillary component of stage IA lung adenocarcinoma. Therefore, the potential use of preoperative neutrophil-to-lymphocyte ratio in the optimization of surgical strategies for the treatment of stage IA lung adenocarcinoma should be further studied.

The value of intratumoral and peritumoral radiomics features in differentiating early-stage lung invasive adenocarcinoma (≤3 cm) subtypes

Background

The identification of different subtypes of early-stage lung invasive adenocarcinoma before surgery contributes to the precision treatment. Radiomics could be one of the effective and noninvasive identification methods. The value of peritumoral radiomics in predicting the subtypes of early-stage lung invasive adenocarcinoma perhaps clinically useful.

Methods

This retrospective study included 937 lung adenocarcinomas which were randomly divided into the training set (n=655) and testing set (n=282) with a ratio of 7:3. This study used the univariate and multivariate analysis to choose independent clinical predictors. Radiomics features were extracted from 18 regions of interest (1 intratumoral region and 17 peritumoral regions). Independent and conjoint prediction models were constructed based on radiomics and clinical features. The performance of the models was evaluated using receiver operating characteristic (ROC) curves, accuracy (ACC), sensitivity (SEN), and specificity (SPE). Significant differences between areas under the ROC (AUCs) were estimated using in the Delong test.

Results

Patient age, smoking history, carcinoembryonic antigen (CEA), lesion location, length, width and clinic behavior were the independent predictors of differentiating early-stage lung invasive adenocarcinoma (≤3 cm) subtypes. The highest AUC value among the 19 independent models was obtained for the PTV0~+3 radiomics model with 0.849 for the training set and 0.854 for the testing set. As the peritumoral distance increased, the predictive power of the models decreased. The radiomics-clinical conjoint model was statistically significantly different from the other models in the Delong test (P<0.05).

Conclusions

The intratumoral and peritumoral regions contained a wealth of clinical information. The diagnostic efficacy of intra-peritumoral radiomics combined clinical model was further improved, which was particularly important for preoperative staging and treatment decision-making.

A pretreatment prediction model of grade 3 tumors classed by the IASLC grading system in lung adenocarcinoma

PURPOSE

The new grading system for invasive nonmucinous lung adenocarcinoma (LUAD) in the 2021 World Health Organization Classification of Thoracic Tumors was based on a combination of histologically predominant subtypes and high-grade components. In this study, a model for the pretreatment prediction of grade 3 tumors was established according to new grading standards.

METHODS

We retrospectively collected 399 cases of clinical stage I (cStage-I) LUAD surgically treated in Tianjin Chest Hospital from 2015 to 2018 as the training cohort. Besides, the validation cohort consists of 216 patients who were collected from 2019 to 2020. These patients were also diagnosed with clinical cStage-I LUAD and underwent surgical treatment at Tianjin Chest Hospital. Univariable and multivariable logistic regression analyses were used to select independent risk factors for grade 3 adenocarcinomas in the training cohort. The nomogram prediction model of grade 3 tumors was established by R software.

RESULTS

In the training cohort, there were 155 grade 3 tumors (38.85%), the recurrence-free survival of which in the lobectomy subgroup was better than that in the sublobectomy subgroup (P = 0.034). After univariable and multivariable analysis, four predictors including consolidation-to-tumor ratio, CEA level, lobulation, and smoking history were incorporated into the model. A nomogram was established and internally validated by bootstrapping. The Hosmer-Lemeshow test result was χ2 = 7.052 (P = 0.531). The C-index and area under the receiver operating characteristic curve were 0.708 (95% CI: 0.6563-0.7586) for the training cohort and 0.713 (95% CI: 0.6426-0.7839) for the external validation cohort.

CONCLUSIONS

The nomogram prediction model of grade 3 LUAD was well fitted and can be used to assist in surgical or adjuvant treatment decision-making.

Construction of IL-1 signalling pathway correlation model in lung adenocarcinoma and association with immune microenvironment prognosis and immunotherapy: Multi-data validation

Numerous studies have confirmed the inextricable link between inflammation and malignancy, which is also involved in developing lung adenocarcinoma, where IL-1 signalling is crucial. However, the predictive role of single gene biomarkers is insufficient, and more accurate prognostic models are needed. We downloaded data related to lung adenocarcinoma patients from the GDC, GEO, TISCH2 and TCGA databases for data analysis, model construction and differential gene expression analysis. The genes of IL-1 signalling-related factors were screened from published papers for subgroup typing and predictive correlation analysis. Five prognostic genes associated with IL-1 signalling were finally identified to construct prognostic prediction models. The K-M curves indicated that the prognostic models had significant predictive efficacy. Further immune infiltration scores showed that IL-1 signalling was mainly associated with enhanced immune cells, drug sensitivity of model genes was analysed using the GDSC database, and correlation of critical memories with cell subpopulation components was observed using single-cell analysis. In conclusion, we propose a predictive model based on IL-1 signalling-related factors, a non-invasive predictive approach for genomic characterisation, in predicting patients' survival outcomes. The therapeutic response has shown satisfactory and effective performance. More interdisciplinary areas combining medicine and electronics will be explored in the future.

A Novel Secreted Protein-Related Gene Signature Predicts Overall Survival and Is Associated With Tumor Immunity in Patients With Lung Adenocarcinoma

Secreted proteins are important proteins in the human proteome, accounting for approximately one-tenth of the proteome. However, the prognostic value of secreted protein-related genes has not been comprehensively explored in lung adenocarcinoma (LUAD). In this study, we screened 379 differentially expressed secretory protein genes (DESPRGs) by analyzing the expression profile in patients with LUAD from The Cancer Genome Atlas database. Following univariate Cox regression and least absolute shrinkage and selection operator method regression analysis, 9 prognostic SPRGs were selected to develop secreted protein-related risk score (SPRrisk), including CLEC3B, C1QTNF6, TCN1, F2, FETUB, IGFBP1, ANGPTL4, IFNE, and CCL20. The prediction accuracy of the prognostic models was determined by Kaplan–Meier survival curve analysis and receiver operating characteristic curve analysis. Moreover, a nomogram with improved accuracy for predicting overall survival was established based on independent prognostic factors (SPRrisk and clinical stage). The DESPRGs were validated by quantitative real-time PCR and enzyme-linked immunosorbent assay by using our clinical samples and datasets. Our results demonstrated that SPRrisk can accurately predict the prognosis of patients with LUAD. Patients with a higher risk had lower immune, stromal, and ESTIMATE scores and higher tumor purity. A higher SPRrisk was also negatively associated with the abundance of CD8⁺ T cells and M1 macrophages. In addition, several genes of the human leukocyte antigen family and immune checkpoints were expressed in low levels in the high-SPRrisk group. Our results provided some insights into assessing individual prognosis and choosing personalized treatment modalities.