Comparisons of the clinicopathological features and survival outcomes between lung cancer patients with adenocarcinoma and squamous cell carcinoma

Differences in postoperative prognosis between early-stage lung adenocarcinoma and squamous cell carcinoma

BACKGROUND

Although prognosis and treatments differ between small-cell- and nonsmall-cell carcinoma, comparisons of the histological types of NSCLC are uncommon. Thus, we investigated the oncological factors associated with the prognosis of early-stage adenocarcinoma and squamous cell carcinoma.

METHODS

We retrospectively compared the clinicopathological backgrounds and postoperative outcomes of patients diagnosed with pathological stage I-IIA adenocarcinoma and squamous cell carcinoma primary lung cancer completely resected at our department from January 2007 to December 2017. Multivariable Cox regression analysis for overall survival and recurrence-free survival was performed.

RESULTS

The median follow-up duration was 55.2 months. The cohort consisted of 532 adenocarcinoma and 96 squamous cell carcinoma patients. A significant difference in survival was observed between the two groups, with a 5-year overall survival rate of 90% (95% confidence interval 86-92%) for adenocarcinoma and 77% (95% CI 66-85%) for squamous cell carcinoma (P < 0.01) patients. Squamous cell carcinoma patients had worse outcomes compared to adenocarcinoma patients in stage IA disease, but there were no significant differences between the two groups in stage IB or IIA disease. In multivariate analysis, invasion diameter was associated with overall survival in adenocarcinoma (hazard ratio 1.76, 95% confidence interval 1.36-2.28), but there was no such association in squamous cell carcinoma (hazard ratio 0.73, 95% confidence interval 0.45-1.14).

CONCLUSIONS

The importance of tumor invasion diameter in postoperative outcomes was different between adenocarcinoma and squamous cell carcinoma. Thus, it is important to consider that nonsmall-cell carcinoma may have different prognoses depending on the histological type, even for the same stage.

First insight about the ability of specific glycerophospholipids to discriminate non-small cell lung cancer subtypes

Introduction: Discrimination between adenocarcinoma (ADC) and squamous cell carcinoma (SCC) subtypes in non-small cell lung cancer (NSCLC) patients is a significant challenge in oncology. Lipidomics analysis provides a promising approach for this differentiation. Methods: In an accompanying paper, we explored oxPCs levels in a cohort of 200 NSCLC patients. In this research, we utilized liquid chromatography coupled with mass spectrometry (LC-MS) to analyze the lipidomics profile of matching tissue and plasma samples from 25 NSCLC patients, comprising 11 ADC and 14 SCC cases. This study builds upon our previous findings, which highlighted the elevation of oxidised phosphatidylcholines (oxPCs) in NSCLC patients. Results: We identified eight lipid biomarkers that effectively differentiate between ADC and SCC subtypes using an untargeted approach. Notably, we observed a significant increase in plasma LPA 20:4, LPA 18:1, and LPA 18:2 levels in the ADC group compared to the SCC group. Conversely, tumour PC 16:0/18:2, PC 16:0/4:0; CHO, and plasma PC 16:0/18:2; OH, PC 18:0/20:4; OH, PC 16:0/20:4; OOH levels were significantly higher in the ADC group. Discussion: Our study is the first to report that plasma LPA levels can distinguish between ADC and SCC patients in NSCLC, suggesting a potential role for LPAs in NSCLC subtyping. This finding warrants further investigation into the mechanisms underlying these differences and their clinical implications.

Preoperative systemic immune-inflammation index-based nomogram for lung carcinoma following microwave ablation -a real world single center study

Background

The preoperative inflammatory condition significantly influences the prognosis of malignancies. We aimed to investigate the potential significance of preoperative inflammatory biomarkers in forecasting the long-term results of lung carcinoma after microwave ablation (MWA).

Method

This study included patients who received MWA treatment for lung carcinoma from Jan. 2012 to Dec. 2020. We collected demographic, clinical, laboratory, and outcome information. To assess the predictive capacity of inflammatory biomarkers, we utilized the area under the receiver operating characteristic curve (AUC-ROC) and assessed the predictive potential of inflammatory biomarkers in forecasting outcomes through both univariate and multivariate Cox proportional hazard analyses.

Results

A total of 354 individuals underwent MWA treatment, of which 265 cases were included in this study, whose average age was 69.1 ± 9.7 years. The AUC values for the Systemic Inflammatory Response Index (SIRI) to overall survival (OS) and disease-free survival (DFS) were 0.796 and 0.716, respectively. The Cox proportional hazards model demonstrated a significant independent association between a high SIRI and a decreased overall survival (hazard ratio [HR]=2.583, P<0.001). Furthermore, a high SIRI independently correlated with a lower DFS (HR=2.391, P<0.001). We developed nomograms utilizing various independent factors to forecast the extended prognosis of patients. These nomograms exhibited AUC of 0.900, 0.849, and 0.862 for predicting 1-year, 3-year, and 5-year OS, respectively. Additionally, the AUC values for predicting 1-year, 3-year, and 5-year DFS were 0.851, 0.873, and 0.883, respectively.

Conclusion

SIRI has shown promise as a valuable long-term prognostic indicator for forecasting the outcomes of lung carcinoma patients following MWA.

Influence of adjuvant chemotherapy on survival for patients with completely resected high-risk stage IB NSCLC

BACKGROUND

The use of adjuvant chemotherapy (ACT) in completely resected stage IB NSCLC is still controversial. This study aims to investigate the efficacy of ACT in pathological stage IB non-small cell lung cancer (NSCLC) with high risk factors.

METHODS

Patients with pT2aN0M0 stage IB NSCLC who underwent complete resection from 2013 to 2017 were retrospectively analyzed. Univariate and multivariable logistic regression analysis was used to assess potential independent risk factors associated with poor prognosis. To compare survival between patients who received ACT and those who did not.

RESULTS

In univariate and multivariate analyses, adenocarcinomas with predominantly micropapillary (MIP) and solid patterns (SOL), poorly differentiated squamous cell carcinoma (SCC), number of lymph nodes dissected less than 16 and tumor size larger than 36 mm were identified as high-risk factors for recurrence. In patients with high risk factors for recurrence, ACT resulted in significantly longer DFS (HR, 0.4689, 95%CI, 1.193-3.818; p = 0.0108) and OS (HR, 0.4696, 95%CI, 0.6578-6.895; p = 0.2073), although OS failed to reach statistically significance. After propensity score matching (PSM), 67 pairs of patients were 1:1 matched in the two groups and all baseline characteristics were well balanced. The results also demonstrated that ACT was associated with improved DFS (HR, 0.4776, 95%CI, 0.9779-4.484; p = 0.0440) while OS was not significantly different (92.5% vs. 91.0%; HR, 0.6167, 95%CI, 0.1688-2.038; p = 0.7458). In patients with low-risk factors for recurrence, DFS (HR, 0.4831, 95%CI, 0.03025-7.715; p = 0.6068) and OS (HR, 0.969, 95%CI, 0.08364-11.21; p = 0.9794) was not significantly different between those who received ACT and those who did not.

CONCLUSION

In patients with completely resected stage IB NSCLC, ACT can improve survival in patients with high risk for recurrence. Further large multicenter studies are needed to confirm these findings.

Non-invasively Discriminating the Pathological Subtypes of Non-small Cell Lung Cancer with Pretreatment 18F-FDG PET/CT Using Deep Learning

RATIONALE AND OBJECTIVES

To develop an end-to-end deep learning (DL) model for non-invasively predicting non-small cell lung cancer (NSCLC) pathological subtypes based on 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) images, and to explore the potential value of DL technology.

MATERIALS AND METHODS

Preoperative 18F-FDG PET/CT images of 189 patients with NSCLC were retrospectively collected. The whole cohort was randomly divided into a training cohort, a validation cohort, and an internal/extended test cohort at the ratio of 6:2:2 after preprocessing the images. In the training and validation cohorts, seven DL models-Shufflenet, VGG16, Googlenet, Inception v3, Resnet50, Densenet201, and Mobilenet v2-were trained and optimized. The generalization ability and clinical utility of the optimal model were evaluated in the internal and extended test cohorts. Moreover, Spearman's correlation analysis was used to evaluate the correlation between DL features and traditional radiological features such as tumor size and maximum standardized uptake values (SUVmax).

RESULTS

Some DL features were significantly correlated with SUVmax and tumor size (P < 0.05). The Mobilenet v2 model achieved the best performance during the model development and validation phases. In the internal test group (area under the receiver operating characteristic curve [AUC]: 0.744, area under the precision-recall curve [AP]: 0.759) and extended test group (AUC: 0.767, AP: 0.768), the Mobilenet v2 model showed good generalization ability and reproducibility. Meanwhile, the decision curve analysis revealed that patients can benefit from the decisions made based on the Mobilenet v2 model.

CONCLUSION

DL models offer great potential for classifying NSCLC pathological subtypes. Specifically, the Mobilenet v2 model performs well at end-to-end non-invasive pathological subtype stratification of NSCLC.

Clinical application of 18F-fluorodeoxyglucose positron emission tomography/computed tomography radiomics-based machine learning analyses in the field of oncology

Machine learning (ML) analyses using 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomics features have been applied in the field of oncology. The current review aimed to summarize the current clinical articles about 18F-FDG PET/CT radiomics-based ML analyses to solve issues in classifying or constructing prediction models for several types of tumors. In these studies, lung and mediastinal tumors were the most commonly evaluated lesions, followed by lymphatic, abdominal, head and neck, breast, gynecological, and other types of tumors. Previous studies have commonly shown that 18F-FDG PET radiomics-based ML analysis has good performance in differentiating benign from malignant tumors, predicting tumor characteristics and stage, therapeutic response, and prognosis by examining significant differences in the area under the receiver operating characteristic curves, accuracies, or concordance indices (> 0.70). However, these studies have reported several ML algorithms. Moreover, different ML models have been applied for the same purpose. Thus, various procedures were used in 18F-FDG PET/CT radiomics-based ML analysis in oncology, and 18F-FDG PET/CT radiomics-based ML models, which are easy and universally applied in clinical practice, would be expected to be established.

Immune-active tumor-adjacent tissues are associated with favorable prognosis in stage I lung squamous cell carcinoma

The immunogenomic features of tumor-adjacent lungs (TALs) in stage I lung squamous cell carcinoma (LUSC) are not clear. Multiomics analyses of tumor tissues and paired TALs from 59 stage I LUSC patients were performed. Compared to tumors, TALs exhibited a better-preserved immune contexture indicated by upregulation of immune pathways, increased immune infiltration, and higher expression of immune effector molecules. Notably, TALs had no mutations in PTEN and KEAP1, a lower incidence of human leukocyte antigen (HLA) loss and higher expression of HLA class I genes, major histocompatibility complex (MHC) I chaperones, and interferon (IFN)-γ-associated genes. Digital spatial profiling validated the generally higher immune infiltration in TALs and revealed a higher level of immune heterogeneity in LUSC tumors. Importantly, patients with higher immune infiltration in TALs had significantly longer survival, while high immune heterogeneity was associated with inferior patient survival. Our work can be considered in the selection of patients for adjuvant therapy, especially immunotherapy.

Advances in diagnosis and prediction for aggression of pure solid T1 lung cancer

A growing number of early-stage lung cancers presenting as malignant pulmonary nodules have been diagnosed because of the increased adoption of low-dose spiral computed tomography. But pure solid T1 lung cancer with ≤3 cm in the greatest dimension is not always at an early stage, despite its small size. This type of cancer can be highly aggressive and is associated with pathological involvement, metastasis, postoperative relapse, and even death. However, it is easily misdiagnosed or delay diagnosed in clinics and thus poses a serious threat to human health. The percentage of nodal or extrathoracic metastases has been reported to be >20% in T1 lung cancer. As such, understanding and identifying the aggressive characteristics of pure solid T1 lung cancer is crucial for prevention, diagnosis, and therapeutic strategies, and beneficial to improving the prognosis. With the widespread of lung cancer screening, these highly invasive pure solid T1 lung cancer will become the main advanced lung cancer in future. However, there is limited information regarding precision medicine on how to identify these "early-stage" aggressive lung cancers. To provide clinicians with new insights into early recognition and intervention of the highly invasive pure solid T1 lung cancer, this review summarizes its clinical characteristics, imaging, pathology, gene alterations, immune microenvironment, multi-omics, and current techniques for diagnosis and prediction.

Trends and Outcomes of Salvage Lobectomy for Early-stage Non-Small Cell Lung Cancer

OBJECTIVES

There is little data describing the outcomes for patients who develop local recurrences after stereotactic body radiation therapy (SBRT), a standard-of-care treatment for patients with early-stage non-small cell lung cancer. One emerging option is salvage lobectomy. We investigated trends in the use of salvage lobectomy after SBRT and described patient outcomes using a nationally representative sample.

METHODS

This is a retrospective study using the National Cancer Database of patients with non-small cell lung cancer diagnosed from 2004 to 2017. We used descriptive statistics to describe patients who underwent salvage lobectomy. Kaplan-Meier analysis was used to estimate overall survival (OS). Cox proportional modeling was used to identify factors associated with OS.

RESULTS

We identified 276 patients who underwent salvage lobectomy. Ninety-day mortality was 0%. The median survival time for the cohort was 50 months (95% CI, 44 to 58). Median follow-up was 65 months (Interquartile Range: 39 to 96). The factors associated with decreased OS include squamous cell histology (hazard ratio (HR)=1.72, P =0.005) and high grade (1.50, P =0.038). Increased OS was associated with lobectomy performed between 3 and 6 months after SBRT (HR=0.53, P =0.021), lobectomy performed >6 months after SBRT (HR=0.59, P =0.015), and female sex (HR=0.56, P =0.004).

CONCLUSIONS

Salvage lobectomy after local failures of SBRT was associated with no perioperative mortality and favorable long-term outcomes. Our data suggest that lobectomy performed within 3 months of SBRT is associated with worse OS.

Tumor hyaluronan as a novel biomarker in non-small cell lung cancer: A retrospective study

INTRODUCTION

Hyaluronan (HA) accumulation is associated with tumorigenesis and aggressive tumor behavior.

AIMS

We investigated the biomarker potential of HA in non-small cell lung cancer (NSCLC).

METHODS

HA levels were scored using affinity histochemistry in 137 NSCLC samples stratified by HA score ≤10, 11-20, 21-30, and >30 with HA-high defined as ≥25% expression in the extracellular matrix (ECM) of the tumor surface area. Overall survival (OS) and time to progression from initiation of taxane therapy (TTP) were compared using log-rank tests based on HA score.

RESULTS

Of 122 patients with recurrent/metastatic NSCLC, 93 had mean HA scores that were not significantly different across clinicopathologic variables. Frequency of HA-high tumors did not differ by histology (34/68 adenocarcinomas vs. 12/25 squamous tumors, Fisher's p = 1.0000). Median OS for recurrent/metastatic adenocarcinoma was 35.5 months (95%, 23.6-50.3) vs. 17.9 months for squamous (95%, 12.7-37.0, log-rank test, p = 0.0165). OS was not significantly different by HA quartiles, high or low (<25) HA score and tumor histology, and HA biopsy site (all p > 0.05). Median TTP (n = 98) significantly differed by HA quartile (2.8 months for HA score ≤10; 5.0 months for 11-20; 7.9 months for 21-30; 3.9 months for >30, p = 0.0265). Improved TTP trended in HA-high over HA-low tumors (n = 98, p = 0.0911).

CONCLUSION

In this NSCLC cohort, tumor HA level represents a potential biomarker for TTP, which remains a cornerstone of NSCLC therapy. Further validation is warranted to identify the HA accumulation threshold associated with clinical benefit.

Selection of the surgical approach for patients with cStage IA lung squamous cell carcinoma: A population-based propensity score matching analysis

Background

This study aimed to conduct a comparative analysis of the survival rates after segmentectomy, wedge resection, or lobectomy in patients with cStage IA lung squamous cell carcinoma (SCC).

Methods

We enrolled 4,316 patients who had cStage IA lung SCC from the Surveillance, Epidemiology, and End Results (SEER) database. The Cox proportional hazards model was conducted to recognize the potential risk factors for overall survival (OS) and lung cancer-specific survival (LCSS). To eliminate potential biases of included patients, the propensity score matching (PSM) method was used. OS and LCSS rates were compared among three groups stratified according to tumor size.

Results

Kaplan–Meier analyses revealed no statistical differences in the rates of OS and LCSS between wedge resection (WR) and segmentectomy (SG) groups for patients who had cStage IA cancers. In patients with tumors ≤ 1 cm, LCSS favored lobectomy (Lob) compared to segmentectomy (SG), but a similar survival rate was obtained for wedge resection (WR) and lobectomy (Lob). For patients with tumors sized 1.1 to 2 cm, lobectomy had improved OS and LCSS rates compared to the segmentectomy or wedge resection groups, with the exception of a similar OS rate for lobectomy and segmentectomy. For tumors sized 2.1 to 3 cm, lobectomy had a higher rate of OS or LCSS than wedge resection or segmentectomy, except that lobectomy conferred a similar LCSS rate compared to segmentectomy. Multivariable analyses showed that patients aged ≥75 and tumor sizes of &gt;2 to ≤3 cm were potential risk factors for OS and LCSS, while lobectomy and first malignant primary indicator were considered protective factors. The Cox proportional analysis also confirmed that male patients aged ≥65 to &lt;75 were independent prognostic factors that are indicative of a worse OS rate.

Conclusions

The tumor size can influence the surgical procedure recommended for individuals with cStage IA lung SCC. For patients with tumors ≤1 cm, lobectomy is the recommended approach, and wedge resection or segmentectomy might be an alternative for those who cannot tolerate lobectomy if adequate surgical margin is achievable and enough nodes are sampled. For tumors &gt;1 to ≤3 cm, lobectomy showed better survival outcomes than sublobar resection. Our findings require further validation by randomized controlled trial (RCT) or other evidence.

Squamous cell carcinoma predicts worse prognosis than adenocarcinoma in stage IA lung cancer patients: A population-based propensity score matching analysis

Background

Although numerous studies have reported the association between histological types and the prognosis of IA non-small-cell lung cancer (NSCLC) patients, few studies have deeply investigated the impact of pathology on the outcome of NSCLC patients. In this study, we comprehensively explored whether the type of histology influenced the outcome of IA-stage NSCLC patients.

Methods

The study population was obtained from the Surveillance, Epidemiology, and End Results (SEER) program, which is supported by the National Cancer Institute of the United States. To avoid potential bias, the method of propensity score matching (PSM) was used to obtain a balanced cohort for further analysis.

Results

The results from univariate and multivariate regression models showed that lung squamous cell carcinoma (LSQCC) patients were at a significantly greater risk of undergoing shorter overall survival (OS) and lung cancer–specific survival (LCSS). After PSM analysis, LSQCC was still closely associated with a reduction in OS and LCSS. All of these suggested that the histological type was an independent prognostic factor for OS and LCSS.

Conclusion

Our study demonstrated that squamous cell carcinoma predicted worse OS and LCSS in IA-stage NSCLC patients compared with lung adenocarcinoma (LUAD). We suggest that the outcomes of LSQCC and LUAD are very different and that the two histological types should be differently analyzed.

The Machine Learning Model for Distinguishing Pathological Subtypes of Non-Small Cell Lung Cancer

Purpose

Machine learning models were developed and validated to identify lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) using clinical factors, laboratory metrics, and 2-deoxy-2[¹⁸F]fluoro-D-glucose ([¹⁸F]F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomic features.

Methods

One hundred and twenty non-small cell lung cancer (NSCLC) patients (62 LUAD and 58 LUSC) were analyzed retrospectively and randomized into a training group (n = 85) and validation group (n = 35). A total of 99 feature parameters—four clinical factors, four laboratory indicators, and 91 [¹⁸F]F-FDG PET/CT radiomic features—were used for data analysis and model construction. The Boruta algorithm was used to screen the features. The retained minimum optimal feature subset was input into ten machine learning to construct a classifier for distinguishing between LUAD and LUSC. Univariate and multivariate analyses were used to identify the independent risk factors of the NSCLC subtype and constructed the Clinical model. Finally, the area under the receiver operating characteristic curve (AUC) values, sensitivity, specificity, and accuracy (ACC) was used to validate the machine learning model with the best performance effect and Clinical model in the validation group, and the DeLong test was used to compare the model performance.

Results

Boruta algorithm selected the optimal subset consisting of 13 features, including two clinical features, two laboratory indicators, and nine PEF/CT radiomic features. The Random Forest (RF) model and Support Vector Machine (SVM) model in the training group showed the best performance. Gender (P=0.018) and smoking status (P=0.011) construct the Clinical model. In the validation group, the SVM model (AUC: 0.876, ACC: 0.800) and RF model (AUC: 0.863, ACC: 0.800) performed well, while Clinical model (AUC:0.712, ACC: 0.686) performed moderately. There was no significant difference between the RF and Clinical models, but the SVM model was significantly better than the Clinical model. 

Conclusions

The proposed SVM and RF models successfully identified LUAD and LUSC. The results indicate that the proposed model is an accurate and noninvasive predictive tool that can assist clinical decision-making, especially for patients who cannot have biopsies or where a biopsy fails.

A Proposal to Modify the 8th IASLC System: Is it Suitable for T4N2M0 Lung Adenocarcinoma to Be Placed in Stage IIIB?

PURPOSE

The International Association for the Study of Lung Cancer (IASLC) of TNM staging system has been well accepted as a precise model. However, the latest American Joint Committee on Cancer (AJCC) staging system to solve the different survival and prognosis of lung adenocarcinoma in the same period is still controversial. Therefore, it is necessary to thoroughly explore the applicability between the new system and survival prediction in terms of lung adenocarcinoma.

METHODS

We recruited 52,517 patients with lung adenocarcinoma from the Surveillence, Epidemiology, and End Results database. Cox regression analysis was performed to determine survival related factors. The mortality rate per 1000 persons per year of the T4N2M0 lung adenocarcinoma stage and other stages were compared. Survival curves were obtained using the Kaplan-Meier analysis and log-rank test.

RESULTS

The results of Cox proportional hazards regression analysis showed that age at diagnosis, race, T stage, distant metastasis, extrathoracic extension, radiotherapy, chemotherapy, and surgery are independent factors related to cancer-specific survival (CSS) and all-cause survival. Furthermore, patients with stage IIIA disease (P<0.001) and IIIB disease (P<0.001) excluding stage at T4N2M0 had a significantly lower risk of CSS and all-cause survival than those staged with T4N2M0 disease. The mortality rates per 1000 person-years with patients staged at T4N2M0 lung adenocarcinoma had higher mortality than patients in the same period. The CSS curves of patients with stage T4N2M0 reflected an obvious decline compared with those of stages IIIA disease and IIIB excluding T4N2M0, and there is no significant difference between this curve and stage IIIC patients (P>0.05).

CONCLUSION

The survival rate of patients with T4N2M0 stage was significantly lower than that of patients with IIIA and IIIB stages excluding T4N2M0, there was no significant difference between T4N2M0 and IIIC. It was suggested that this group of patients with stage T4N2M0 were upgraded in the 8th IASLC system.

C-Reactive Protein to Albumin Ratio as Prognostic Marker in Locally Advanced Non-Small Cell Lung Cancer Treated with Chemoradiotherapy

Despite the implementation of consolidative immune checkpoint inhibition after definitive chemoradiotherapy (CRT), the prognosis for locally advanced non-small-cell lung cancer (NSCLC) remains poor. We assessed the impact of the C-reactive protein (CRP) to albumin ratio (CAR) as an inflammation-based prognostic score in patients with locally advanced NSCLC treated with CRT. We retrospectively identified and analyzed 52 patients with primary unresectable NSCLC (UICC Stage III) treated with definitive/neoadjuvant CRT between 2014 and 2019. CAR was calculated by dividing baseline CRP by baseline albumin levels and correlated with clinicopathologic parameters to evaluate prognostic impact. After dichotomizing patients by the median, univariate and multivariate Cox regression analyses were performed. An increased CAR was associated with advanced T-stage (p = 0.018) and poor performance status (p = 0.004). Patients with pre-therapeutic elevated CAR had significantly lower hemoglobin and higher leukocyte levels (hemoglobin p = 0.001, leukocytes p = 0.018). High baseline CAR was shown to be associated with worse local control (LPFS, p = 0.006), shorter progression-free survival (PFS, p = 0.038) and overall survival (OS, p = 0.022), but not distant metastasis-free survival (DMFS). Multivariate analysis confirmed an impaired outcome in patients with high CAR (LPFS: HR 3.562, 95% CI 1.294–9.802, p = 0.011). CAR is an easily available and independent prognostic marker after CRT in locally advanced NSCLC. CAR may be a useful biomarker for patient stratification to individualize treatment concepts.

End-to-End Non-Small-Cell Lung Cancer Prognostication Using Deep Learning Applied to Pretreatment Computed Tomography

PURPOSE

Clinical TNM staging is a key prognostic factor for patients with lung cancer and is used to inform treatment and monitoring. Computed tomography (CT) plays a central role in defining the stage of disease. Deep learning applied to pretreatment CTs may offer additional, individualized prognostic information to facilitate more precise mortality risk prediction and stratification.

METHODS

We developed a fully automated imaging-based prognostication technique (IPRO) using deep learning to predict 1-year, 2-year, and 5-year mortality from pretreatment CTs of patients with stage I-IV lung cancer. Using six publicly available data sets from The Cancer Imaging Archive, we performed a retrospective five-fold cross-validation using pretreatment CTs of 1,689 patients, of whom 1,110 were diagnosed with non-small-cell lung cancer and had available TNM staging information. We compared the association of IPRO and TNM staging with patients' survival status and assessed an Ensemble risk score that combines IPRO and TNM staging. Finally, we evaluated IPRO's ability to stratify patients within TNM stages using hazard ratios (HRs) and Kaplan-Meier curves.

RESULTS

IPRO showed similar prognostic power (concordance index [C-index] 1-year: 0.72, 2-year: 0.70, 5-year: 0.68) compared with that of TNM staging (C-index 1-year: 0.71, 2-year: 0.71, 5-year: 0.70) in predicting 1-year, 2-year, and 5-year mortality. The Ensemble risk score yielded superior performance across all time points (C-index 1-year: 0.77, 2-year: 0.77, 5-year: 0.76). IPRO stratified patients within TNM stages, discriminating between highest- and lowest-risk quintiles in stages I (HR: 8.60), II (HR: 5.03), III (HR: 3.18), and IV (HR: 1.91).

CONCLUSION

Deep learning applied to pretreatment CT combined with TNM staging enhances prognostication and risk stratification in patients with lung cancer.

The Prognostic Significance of the Histological Types in Patients With Nonsmall Cell Lung Cancer ≤2 cm

Background: Few studies attempt to investigate the impact of histology on the outcome of nonsmall-cell lung cancer (NSCLC) patients. In this study, we aim to determine whether the type of histology influenced the outcome of stage IA NSCLC patients with tumor size (TS) ≤20 mm. Methods: The data of the population in our study was collected from the Surveillance, Epidemiology, and End Results (SEER) program, which is supported by the National Cancer Institute of the United States. The primary outcome was overall survival (OS). Cox-regression proportional hazards models were performed to identify prognostic factors for OS. The secondary outcome was lung cancer-specific mortality (LCSM). A competing risk model was used to identify risk factors associated with LCSM. Results: A total of 4,424 eligible patients (T1a-bN0M0) who received sublobar resection [wedge resection (WR) and segmentectomy] were identified and included in the study for further analysis. For patients with TS ≤ 10 mm, multivariate Cox-regression analyses for OS showed that lung squamous cell carcinoma (LUSC) yielded poorer OS compared with lung adenocarcinoma (LUAD), and no difference was observed between LUSC and LUAD for LCSM in competing risk models. For patients with TS > 10 and ≤20 mm, multivariate analyses revealed that LUSC patients experienced poorer OS compared with that of LUAD; the univariate competing risk analysis indicated SCC pathology predicted an increased risk of death from lung cancer, whereas no difference is observed in the multivariate competing analysis. In addition, segmentectomy was associated with longer OS in patients with >10 and ≤20 mm but not in patients with ≤10 mm compared with WR. Conclusion: Our study demonstrated that squamous pathology was associated with the worse OS but not LCSM for patients with ≤20 mm compared with adenocarcinoma. Moreover, segmentectomy when compared to wedge resection appears to be associated with a better prognosis in patients with neoplasm >10 mm, but not in the case of nodule ≤10 mm.

Benefit of adjuvant chemotherapy for patients with stage IB non-small cell lung cancer: a systematic review and meta-analysis

Background

Adjuvant chemotherapy (ACT) is routinely the recommended treatment for patients with advanced non-small cell lung cancer (NSCLC) but remains a controversial option in stage IB patients. We therefore pooled the current evidence to determine the prognostic impact of ACT in stage IB NSCLC patients in the context of the eighth tumor, node, metastasis (TNM) staging system.

Methods

Five electronic databases were searched for eligible studies up to December 2020 without language restrictions. The primary and secondary outcomes were overall survival (OS) and disease-free survival (DFS). Search results were filtered by a set of eligibility criteria and analyzed in line with PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. The risk of bias was assessed independently using a modified set. Stata 16.0 was used for general data analysis and meta-analysis, and subgroup analyses were performed to investigate the source of interstudy heterogeneity.

Results

In all, 12 eligible studies were identified and 15,678 patients included. Our results demonstrated that ACT was associated with improved OS [n=11; hazard ratio (HR) =0.65; 95% confidence interval (CI): 0.60–0.70; P<0.001; I²=33.4%, P=0.131] and DFS (n=9; HR =0.73; 95% CI: 0.63–0.83; P<0.001; I²=66.7%, P=0.002) in stage IB NSCLC patients. Subgroup analysis by histology indicated that administration of ACT conferred more favorable survival to both stage IB squamous cell carcinoma (n=1; HR =0.56; 95% CI: 0.28–0.84; P<0.001) and adenocarcinoma (n=6; HR =0.59; 95% CI: 0.47–0.71; P<0.001; I²=31.0%, P=0.203). Meanwhile, both platinum-based ACT (n=7; HR =0.62; 95% CI: 0.51–0.74; P<0.001; I²=44.8%, P=0.093) and other regimens (n=2; HR =0.66; 95% CI: 0.61–0.72; P<0.001; I²=0.7%, P=0.316) could benefit patients with stage IB disease.

Discussion

ACT might provide survival benefits to patients with stage IB NSCLC irrespective of histology or regimens. Patient selection and time trend biases were inevitable due to the limitation of retrospective studies. More prospective studies should be initiated to investigate the optimal ACT regimens in different histologic types in stage IB NSCLC patients.

[Predicting the risk of tumor progression in patients with early stages of adenocarcinoma and squamous cell lung carcinoma based on laboratory parameters]

Non-small cell carcinoma (NSCLC) prevails in the structure of the incidence of lung cancer. In patients with I stage NSCLC, only 60-70% overcome the 5-year survival barrier, and at II stage it decreases to 35-40%. The reason for such a high mortality rate is almost always a relapse of the disease. The main histological forms of NSCLC - adenocarcinoma (AC) and squamous cell carcinoma (SCLC) - differ in the course, protocols and effectiveness of the treatment. Comparative survival data for AK and PCLC are controversial, and reliable biomarkers for determining the risk of tumor progression are lacking. In thus study we have investigated the possibility of using laboratory parameters characterizing the level of some blood proteins involved in carcinogenesis in patients with early stages of AC and SCLC to determine the risk of disease progression. We retrospectively analyzed the duration of the relapse-free period after surgical treatment for one year in 1250 patients (816 with stages I and II of adenocarcinoma, G1-3 and 434 with early stages of SCLC, G1-3). In 81 patients with AC and 36 - with SCLC (stages I-II, G1-3) the level of CYFRA 21-1 and SCC by electrochemiluminescent method, chemokines CXCL5, CXCL8, TPA, pyruvate kinase M2, HIF-1α and hyaluronic acid by enzyme immunoassay, receptors CXCR1, CXCR2, CD44v6 by flow cytometry were determined. Using the Kaplan-Meier graphical analysis, groups of low (stage I G1-2 + stage II G1) and high (stage I G3 + stage II G2-3) risk of tumor progression were identified. In the case of the one-year survival rate of patients with AC was higher than with SCLC. In patients with AC and a high risk of tumor recurrence, compared with a low one, the level of CYFRA 21-1, the mean intensity of fluorescence (MFI) of the CXCR1 receptor in granulocytes, and the relative content of the CXCR2 receptor in lymphocytes were higher. In the case of rapid progression of SCLC in patients, the relative content of the CXCR2 receptor in lymphocytes, the proportion of monocytes equipped with the CD44v6 receptor, and the SCC level were higher than with slow progression. Regression equations, including combinations of the above parameters (threshold value for AC - 0,512, for SCLC - 0,409, sensitivity - 91,9% and 90,0%, specificity - 90,0% and 87,5%, respectively), allow to predict the probability of tumor recurrence.

Impact of feature selection methods and subgroup factors on prognostic analysis with CT-based radiomics in non-small cell lung cancer patients

Background

Radiomics is a new technology to noninvasively predict survival prognosis with quantitative features extracted from medical images. Most radiomics-based prognostic studies of non-small-cell lung cancer (NSCLC) patients have used mixed datasets of different subgroups. Therefore, we investigated the radiomics-based survival prediction of NSCLC patients by focusing on subgroups with identical characteristics.

Methods

A total of 304 NSCLC (Stages I–IV) patients treated with radiotherapy in our hospital were used. We extracted 107 radiomic features (i.e., 14 shape features, 18 first-order statistical features, and 75 texture features) from the gross tumor volume drawn on the free breathing planning computed tomography image. Three feature selection methods [i.e., test–retest and multiple segmentation (FS1), Pearson's correlation analysis (FS2), and a method that combined FS1 and FS2 (FS3)] were used to clarify how they affect survival prediction performance. Subgroup analysis for each histological subtype and each T stage applied the best selection method for the analysis of All data. We used a least absolute shrinkage and selection operator Cox regression model for all analyses and evaluated prognostic performance using the concordance-index (C-index) and the Kaplan–Meier method. For subgroup analysis, fivefold cross-validation was applied to ensure model reliability.

Results

In the analysis of All data, the C-index for the test dataset is 0.62 (FS1), 0.63 (FS2), and 0.62 (FS3). The subgroup analysis indicated that the prediction model based on specific histological subtypes and T stages had a higher C-index for the test dataset than that based on All data (All data, 0.64 vs. SCC_all, 060; ADC_all, 0.69; T1, 0.68; T2, 0.65; T3, 0.66; T4, 0.70). In addition, the prediction models unified for each T stage in histological subtype showed a different trend in the C-index for the test dataset between ADC-related and SCC-related models (ADC_T1–ADC_T4, 0.72–0.83; SCC_T1–SCC_T4, 0.58–0.71).

Conclusions

Our results showed that feature selection methods moderately affected the survival prediction performance. In addition, prediction models based on specific subgroups may improve the prediction performance. These results may prove useful for determining the optimal radiomics-based predication model.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-021-01810-9.

Combining liquid biopsy and radiomics for personalized treatment of lung cancer patients. State of the art and new perspectives

Lung cancer has become a paradigm for precision medicine in oncology, and liquid biopsy (LB) together with radiomics may have a great potential in this scenario. They are both minimally invasive, easy to perform, and can be repeated during patient's follow-up. Also, increasing evidence suggest that LB and radiomics may provide an efficient way to screen and diagnose tumors at an early stage, including the monitoring of any change in the tumor molecular profile. This could allow treatment optimization, improvement of patients' quality of life, and healthcare-related costs reduction. Latest reports on lung cancer patients suggest a combination of these two strategies, along with cutting-edge data analysis, to decode valuable information regarding tumor type, aggressiveness, progression, and response to treatment. The approach seems more compatible with clinical practice than the current standard, and provides new diagnostic companions being able to suggest the best treatment strategy compared to conventional methods. To implement radiomics and liquid biopsy directly into clinical practice, an artificial intelligence (AI)-based system could help to link patients' clinical data together with tumor molecular profiles and imaging characteristics. AI could also solve problems and limitations related to LB and radiomics methodologies. Further work is needed, including new health policies and the access to large amounts of high-quality and well-organized data, allowing a complementary and synergistic combination of LB and imaging, to provide an attractive choice e in the personalized treatment of lung cancer.

An Artificial Intelligence Model for Predicting 1-Year Survival of Bone Metastases in Non-Small-Cell Lung Cancer Patients Based on XGBoost Algorithm

Non-small-cell lung cancer (NSCLC) patients often develop bone metastases (BM), and the overall survival for these patients is usually perishing. However, a model with high accuracy for predicting the survival of NSCLC with BM is still lacking. Here, we aimed to establish a model based on artificial intelligence for predicting the 1-year survival rate of NSCLC with BM by using extreme gradient boosting (XGBoost), a large-scale machine learning algorithm. We selected NSCLC patients with BM between 2010 and 2015 from the Surveillance, Epidemiology, and End Results database. In total, 5973 cases were enrolled and divided into the training (n = 4183) and validation (n = 1790) sets. XGBoost, random forest, support vector machine, and logistic algorithms were used to generate predictive models. Receiver operating characteristic curves were used to evaluate and compare the predictive performance of each model. The parameters including tumor size, age, race, sex, primary site, histological subtype, grade, laterality, T stage, N stage, surgery, radiotherapy, chemotherapy, distant metastases to other sites (lung, brain, and liver), and marital status were selected to construct all predictive models. The XGBoost model had a better performance in both training and validation sets as compared with other models in terms of accuracy. Our data suggested that the XGBoost model is the most precise and personalized tool for predicting the 1-year survival rate for NSCLC patients with BM. This model can help the clinicians to design more rational and effective therapeutic strategies.

Texture Analysis on [18F]FDG PET/CT in Non-Small-Cell Lung Cancer: Correlations Between PET Features, CT Features, and Histological Types

PURPOSE

The study aims to investigate the correlations between positron emission tomography (PET) texture features, X-ray computed tomography (CT) texture features, and histological subtypes in non-small-cell lung cancer evaluated with 2-deoxy-2-[¹⁸F]fluoro-D-glucose PET/CT.

PROCEDURES

We retrospectively evaluated the baseline PET/CT scans of 81 patients with histologically proven non-small-cell lung cancer. Feature extraction and statistical analysis were carried out on the Matlab platform (MathWorks, Natick, USA).

RESULTS

Intra-CT correlation analysis revealed a strong positive correlation between volume of the lesion (CT_vol) and maximum density (CT_max), and between kurtosis (CT_krt) and maximum density (CT_max). A moderate positive correlation was found between volume (CT_vol) and average density (CT_mean), and between kurtosis (CT_krt) and average density (CT_mean). Intra-PET analysis identified a strong positive correlation between the radiotracer uptake (SUV_max, SUV_mean) and its degree of variability/disorder throughout the lesion (SUV_std, SUV_ent). Conversely, there was a strong negative correlation between the uptake (SUV_max, SUV_mean) and its degree of uniformity (SUV_uni). There was a positive moderate correlation between the metabolic tumor volume (MTV) and radiotracer uptake (SUV_max, SUV_mean). Inter (PET-CT) correlation analysis identified a very strong positive correlation between the volume of the lesion at CT (CT_vol) and the metabolic volume (MTV), a moderate positive correlation between average tissue density (CT_mean) and radiotracer uptake (SUV_max, SUV_mean), and between kurtosis at CT (CT_krt) and metabolic tumor volume (MTV). Squamous cell carcinomas had larger volume higher uptake, stronger PET variability and lower uniformity than the other subtypes. By contrast, adenocarcinomas exhibited significantly lower uptake, lower variability and higher uniformity than the other subtypes.

CONCLUSIONS

Significant associations emerged between PET features, CT features, and histological type in NSCLC. Texture analysis on PET/CT shows potential to differentiate between histological types in patients with non-small-cell lung cancer.

Oncologic Outcomes of Surgery Versus SBRT for Non-Small-Cell Lung Carcinoma: A Systematic Review and Meta-analysis

BACKGROUND

The optimal treatment of stage I non-small-cell lung carcinoma is subject to debate. The aim of this study was to compare overall survival and oncologic outcomes of lobar resection (LR), sublobar resection (SR), and stereotactic body radiotherapy (SBRT).

METHODS

A systematic review and meta-analysis of oncologic outcomes of propensity matched comparative and noncomparative cohort studies was performed. Outcomes of interest were overall survival and disease-free survival. The inverse variance method and the random-effects method for meta-analysis were utilized to assess the pooled estimates.

RESULTS

A total of 100 studies with patients treated for clinical stage I non-small-cell lung carcinoma were included. Long-term overall and disease-free survival after LR was superior over SBRT in all comparisons, and for most comparisons, SR was superior to SBRT. Noncomparative studies showed superior long-term overall and disease-free survival for both LR and SR over SBRT. Although the papers were heterogeneous and of low quality, results remained essentially the same throughout a large number of stratifications and sensitivity analyses.

CONCLUSION

Results of this systematic review and meta-analysis showed that LR has superior outcomes compared to SBRT for cI non-small-cell lung carcinoma. New trials are underway evaluating long-term results of SBRT in potentially operable patients.

POLE2 Serves as a Prognostic Biomarker and Is Associated with Immune Infiltration in Squamous Cell Lung Cancer

Background

Squamous cell lung cancer is the main cause of cancer-associated mortality. The discovery of promising prognostic biomarkers for predicting the survival of patients with squamous cell lung cancer remains a challenge.

Material/Methods

Gene expression profiles of GSE33479 and GSE51855, including 42 squamous cell lung cancer tissues and 17 normal tissues, from the GEO database were assessed to find common differentially expressed genes (DEGs) via the GEO2R online tool and Venn diagram software. Then, gene ontology (GO) and Kyoto Encyclopedia of Gene and Genome (KEGG) pathway analyses were conducted. The key protein-protein interaction (PPI) network within those common DEGs was subsequently illustrated through a combination of Search Tool for Retrieval of Interacting Genes (STRING) and Cytoscape software. Finally, core genes associated with survival and levels of immune infiltration were demonstrated by the Kaplan-Meier plotter and Tumor Immune Estimation Resource (TIMER) online database, respectively.

Results

In total, 483 DEGs were involved, including 216 upregulated genes enriched in “cell division”, “DNA replication”, and “DNA repair pathway” and 267 downregulated genes enriched in “cell adhesion”, “oxidation-reduction process”, and “cell-cell signaling”. The 75 core genes were selected by Molecular Complex Detection applied in Cytoscape. Four genes – MND1, FOXM1, CDC6, and POLE2 – were found to be significantly associated with survival. Further analysis of the KEEG pathway and TIMER database revealed that only POLE2 was enriched in “DNA replication” and its higher expression was negatively associated with survival and immune infiltration.

Conclusions

Higher expression of POLE2 is a prognosis-related biomarker for worse survival and is negatively associated with immune infiltration in squamous cell lung cancer.

PET/CT Radiomics in Lung Cancer: An Overview

Quantitative extraction of imaging features from medical scans (‘radiomics’) has attracted a lot of research attention in the last few years. The literature has consistently emphasized the potential use of radiomics for computer-assisted diagnosis, as well as for predicting survival and response to treatment. Radiomics is appealing in that it enables full-field analysis of the lesion, provides nearly real-time results, and is non-invasive. Still, a lot of studies suffer from a series of drawbacks such as lack of standardization and repeatability. Such limitations, along with the unmet demand for large enough image datasets for training the algorithms, are major hurdles that still limit the application of radiomics on a large scale. In this paper, we review the current developments, potential applications, limitations, and perspectives of PET/CT radiomics with specific focus on the management of patients with lung cancer.

Differences in the early stage gene expression profiles of lung adenocarcinoma and lung squamous cell carcinoma

The discovery of lung carcinoma subtype-specific gene expression changes has the potential to elucidate the molecular differences and provide personalized therapeutic targets for these pathologies. The aim of the present study was to characterize the genetic profiles of the early stages (IA/IB) of two non-small cell lung cancer subtypes, adenocarcinoma (AD) and squamous cell carcinoma (SC). RNA-Seq gene expression data from The Cancer Genome Atlas was analyzed to compare the gene expression differences between AD and SC. The gene sets specific to each subtype were further analyzed to identify the enriched Gene Ontology terms, Kyoto Encyclopedia of Genes and Genomes pathways and biological functions. The results demonstrated that a unique set of genes (145 upregulated and 27 downregulated) was altered in AD, but not in SC; another set of genes (146 upregulated and 103 downregulated) was significantly altered in SC, but not in AD. Genes highly upregulated specifically in AD included albumin (1,732-fold), protein lin-28 homolog A, which is a positive regulator of cyclin-dependent kinase 2 (150-fold) and gastric lipase (81-fold). Genes highly upregulated specifically in SC included amelotin (618-fold), alcohol dehydrogenase 7 (57-fold), aclerosteosis (55-fold) and claudin-22 (54-fold). Several cancer/testis antigen family genes were notably upregulated in SC, but not in AD, whereas mucins were upregulated only in AD. Functional pathway analysis demonstrated that the dysregulation of genes associated with retinoid X receptors was common in AD and SC, genes associated with ‘lipid metabolism’ and ‘drug metabolism’ were dysregulated only in SC, whereas genes associated with ‘molecular transport’ and ‘cellular growth and proliferation’ were significantly enriched in AD specifically. These results reveal fundamental differences in the gene expression profiles of early-stage AD and SC. In addition, the present study identified molecular pathways that are uniquely associated with the pathogenesis of these subtypes.

A Proposal to Reflect Survival Difference and Modify the Staging System for Lung Adenocarcinoma and Squamous Cell Carcinoma: Based on the Machine Learning

Objective: To propose modifications to refine prognostication over anatomic extent of the current tumor, node, and metastasis (TNM) staging system of non-small cell lung cancer (NSCLC) for a better distinction, and reflect survival differences of lung adenocarcinoma and squamous cell carcinoma. Study Design: Three large cohorts were included in this study. The training cohort consisted of 124,788 patients in the Surveillance, Epidemiology, and End Results (SEER) database (2006-2015). The validation cohort consisted of 4,247 patients from the Zhongshan Hospital, Fudan University (FDZSH; 2005-2014), and People's Hospital, Peking University (PKUPH; 2000-2017). The algorithm generated a hierarchical clustering model based on the unsupervised learning for survival data using Kaplan-Meier curves and log-rank test statistics for recursive partitioning and selection of the principal groupings. Results: In the modified staging system, adenocarcinoma cases are usually at a lower stage than the squamous cell carcinoma cases of the same TNM, reflecting a better outcome of adenocarcinoma than that of squamous cell carcinoma. The C-index of the modified staging system was significantly superior to that of the staging system [SEER cohort: 0.722, 95% CI, (0.721-0.723) vs. 0.643, 95% CI, (0.640-0.647); FDZSH cohort: 0.720, 95% CI, (0.709-0.731) vs. 0.519, 95% CI, (0.450-0.586); and PKUPH cohort: 0.730, 95% CI, (0.705-0.735) vs. 0.728, 95% CI, (0.703-0.753)]. Conclusion: Survival differences between lung adenocarcinoma and squamous cell carcinoma have been reflected accurately and reliably in the modified staging system based on the machine learning. It may refine prognostication over anatomic extent.

Meta-analysis of comparing part-solid and pure-solid tumors in patients with clinical stage IA non-small-cell lung cancer in the eighth edition TNM classification

Objective: The aim of the study was to compare the prognoses between part-solid and pure-solid tumors for clinical stage IA non-small-cell lung cancer (NSCLC) patients in the eighth edition TNM classification.

Methods: We searched the literature in PubMed and Web of Science for all eligible articles published before November 31, 2018. The pooled data included overall survival (OS), disease-free survival (DFS) and recurrence-free survival (RFS). The hazard ratio (HR) of OS (pure-solid/part-solid) was used as the measure of differential effects. Pure-solid or part-solid tumors in all studies included were matched according to the solid component size or according to the eighth edition TNM classification.

Results: Seven studies including 2,037 patients with c-stage IA NSCLC were pooled in the meta-analysis. Patients with pure-solid tumors had significantly poorer OS (HR 1.69, 95% CI 1.21‒2.35, P=0.002), DFS (HR 1.27, 95% CI 1.07‒1.51, P=0.006) and RFS (HR 1.74, 95% CI 1.08‒2.80, P=0.020). In subgroup analyses, when the meta-analysis was limited to T1a-1b (≤2 cm) lung cancer, the prognosis for pure-solid tumors was inferior to that for part-solid tumors regarding both OS and RFS. In adenocarcinoma subgroup, there was no difference between the two groups in terms of OS and RFS, but we detected a meaningful difference in DFS.

Conclusion: Part-solid tumors may have a better prognosis than pure-solid tumors in clinical stage IA patients according to the eighth edition TNM classification, and similar results were found for the T1a-1b (≤2 cm) subgroup. There were no substantial differences in OS and RFS between two groups in lung adenocarcinoma. However, we detected a meaningful difference in DFS, which might also suggest a superior prognosis for part-solid tumors. We propose that the part-solid and pure-solid tumors in the same T component category be considered separately.

Radiomics for Classifying Histological Subtypes of Lung Cancer Based on Multiphasic Contrast-Enhanced Computed Tomography

OBJECTIVES

The aim of this study was to evaluate the performance of the radiomics method in classifying lung cancer histological subtypes based on multiphasic contrast-enhanced computed tomography (CT) images.

METHODS

A total of 229 patients with pathologically confirmed lung cancer were retrospectively recruited. All recruited patients underwent nonenhanced and dual-phase chest contrast-enhanced CT; 1160 quantitative radiomics features were calculated to build a radiomics classification model. The performance of the classification models was evaluated by the receiver operating characteristic curve.

RESULTS

The areas under the curve of radiomics models in classifying adenocarcinoma and squamous cell carcinoma, adenocarcinoma and small cell lung cancer, and squamous cell carcinoma and small cell lung cancer were 0.801, 0.857, and 0.657 (nonenhanced); 0.834, 0.855, and 0.619 (arterial phase); and 0.864, 0.864, and 0.664 (venous phase), respectively. Moreover, the application of contrast-enhanced CT may affect the selection of radiomics features.

CONCLUSIONS

Our study indicates that radiomics may be a promising tool for noninvasive predicting histological subtypes of lung cancer based on the multiphasic contrast-enhanced CT images.

Choice of the surgical approach for patients with stage I lung squamous cell carcinoma ≤3 cm

Background

We tried to explore the surgical procedures for stage I squamous cell carcinoma (SCC) with a size of ≤3 cm by using the Surveillance, Epidemiology, and End Results (SEER) database. Furthermore, we investigated the relationships between the chosen surgical option and the size of SCC.

Methods

In total, 1,147 patient data sets were collected from 2010 to 2011 using the SEER database. Afterwards, 849 patients with a pT1-2aN0M0 SCC with a size of ≤3 cm after a lobectomy or sublobectomy procedure were identified. Kaplan-Meier curves were conducted to compare the overall survival (OS) rates and the lung cancer-specific survival (LCSS) rates between the two surgical approaches. Cox proportional hazards regressions were performed to discover the independent risk factors for both the OS and LCSS rates. Lastly, subgroup analysis was stratified by the size of the SCC and then classified by the 8^th edition T category.

Results

The sublobectomy procedure did not demonstrate a difference for the OS rate. Additionally, it demonstrated a worse LCSS rate when compared with a lobectomy for stage I SCC. In the subgroup analysis, a lobectomy was shown to have a better survival outcome only when the SCC was >2 and ≤3 cm. Multivariable analysis showed that a size of >2 to ≤3 cm, and an age of >60 were independently associated with poorer OS while the sublobectomy procedure and pleural invasions (PI) were related with a poorer LCSS rate. In the stratification of data for the tumor size, the cox proportional analysis still confirmed the protective effects of the lobectomy in subgroups of SCCs with sizes between >2 to ≤3 cm as well as the T1c category.

Conclusions

The choice of the SCC surgery can be recommended based on the tumor size. A lobectomy procedure demonstrated a better LCSS against the sublobectomy in stage I SCC. SCC with sizes of >2 to ≤3 cm could become a pretty good indicator for lobectomy, while a sublobectomy may be an adequate substitute when the SCC size is ≤2 cm, especially for patients who cannot tolerate a lobectomy. T1c category can also suggest a lobectomy instead of sublobectomy for stage I SCC patients.

Adjuvant Chemotherapy Improves Survival in Surgically Resected Stage IB Squamous Lung Cancer

BACKGROUND

At present there is a significant lack of clinical data for patients with surgically resected stage I squamous lung cancer. The purpose of this study was to investigate the impact of postoperative chemotherapy in this specific population.

METHODS

We retrospectively identified patients who had undergone complete squamous lung cancer resection at the Shanghai Chest Hospital between January 2008 and January 2014.

RESULTS

A total of 596 patients (236 stage IA, 360 stage IB) were included in this study. Results demonstrated that adjuvant chemotherapy (ACT) could provide longer overall survival for patients with p-stage IB disease (hazard ratio [HR], 0.56; 95% confidence interval [CI], 0.34-0.90; p = 0.017). Among p-stage IB patients the ACT-treated cohort trended toward a benefit (HR, 0.69; 95% CI, 0.45-1.04) in recurrence-free survival but failed to reach statistical significance (p = 0.076). After propensity score matching the HRs of recurrence-free survival and overall survival were 0.58 (95% CI, 0.35-0.96; p = 0.033) and 0.49 (95% CI, 0.27-0.88; p = 0.017), respectively. With regards to patients with p-stage IA disease, neither overall survival (HR, 0.87; 95% CI, 0.34-2.27; p = 0.783) nor recurrence-free survival (HR, 0.79; 95% CI, 0.38-1.65; p = 0.534) was significantly different when compared between patients receiving ACT and those who did not. Similar results were also achieved after propensity score matching.

CONCLUSIONS

The data presented herein demonstrated that ACT might provide survival benefits for squamous lung cancer patients with p-stage IB disease.

Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer

OBJECTIVES

To distinguish squamous cell carcinoma (SCC) from lung adenocarcinoma (ADC) based on a radiomic signature METHODS: This study involved 129 patients with non-small cell lung cancer (NSCLC) (81 in the training cohort and 48 in the independent validation cohort). Approximately 485 features were extracted from a manually outlined tumor region. The LASSO logistic regression model selected the key features of a radiomic signature. Receiver operating characteristic curve and area under the curve (AUC) were used to evaluate the performance of the radiomic signature in the training and validation cohorts.

RESULTS

Five features were selected to construct the radiomic signature for histologic subtype classification. The performance of the radiomic signature to distinguish between lung ADC and SCC in both training and validation cohorts was good, with an AUC of 0.905 (95% confidence interval [CI]: 0.838 to 0.971), sensitivity of 0.830, and specificity of 0.929. In the validation cohort, the radiomic signature showed an AUC of 0.893 (95% CI: 0.789 to 0.996), sensitivity of 0.828, and specificity of 0.900.

CONCLUSIONS

A unique radiomic signature was constructed for use as a diagnostic factor for discriminating lung ADC from SCC. Patients with NSCLC will benefit from the proposed radiomic signature.

KEY POINTS

• Machine learning can be used for auxiliary distinguish in lung cancer. • Radiomic signature can discriminate lung ADC from SCC. • Radiomics can help to achieve precision medical treatment.

Prognostic impact of controlling nutritional status score in resected lung squamous cell carcinoma

Background

The preoperative immune-nutritional status has been shown to predict the postoperative prognosis in various types of cancer; however, the prognostic significance of the controlling nutritional status (CONUT) score in resected lung squamous cell carcinoma (SCC) has yet to be elucidated.

Methods

A total of 108 patients with resected lung SCC were analyzed for their clinicopathological factors, including the CONUT score, which can be calculated from the serum albumin, total cholesterol, and total peripheral lymphocyte count. The patients were divided into two groups: CONUT low (0 or 1) or high (≥2).

Results

Among 108 patients, 76 (70.4%) were CONUT low, while 32 (29.6%) were CONUT high. No significant association between the CONUT score and the clinicopathological factors was found. Patients with CONUT high exhibited significantly shorter disease-free and overall survivals (DFS and OS) than those with CONUT low (P=0.016 and P=0.006, respectively). Multivariate analyses showed that the CONUT score [hazard ratio (HR): 1.902, 95% confidence interval (CI): 1.045-3.373, P=0.036], age (HR: 2.286, 95% CI: 1.246-4.304, P=0.007), pathological stage (HR: 2.527, 95% CI: 1.391-4.644, P=0.002), and lymphatic invasion (HR: 2.321, 95% CI: 1.110-4.493, P=0.027) were independent prognostic factors for the DFS. Furthermore, in a multivariate analysis, the CONUT score (HR: 1.909, 95% CI: 0.902-3.860, P=0.081), age (HR: 2.455, 95% CI: 1.208-5.178, P=0.013), pathological stage (HR: 2.488, 95% CI: 1.201-5.306, P=0.014), and lymphatic invasion (HR: 3.409, 95% CI: 1.532-7.240, P=0.004) were shown to be independent prognostic factors for the OS.

Conclusions

The current study showed that the CONUT score was an independent prognostic factor for the DFS and OS in patients with resected lung SCC.

Platinum-Based Adjuvant Chemotherapy for Stage II and Stage III Squamous Cell Carcinoma of the Lung

INTRODUCTION

The efficacy of platinum-based adjuvant chemotherapy (PBAC) for pathological stage II and stage III squamous cell carcinoma (SCC) of the lung was analyzed retrospectively.

MATERIALS AND METHODS

The prognoses of 94 patients with stage II and stage III SCC with or without PBAC (more than three courses of cisplatin-, carboplatin-, and nedaplatin-based adjuvant chemotherapy) were compared.

RESULTS

The mean observation period was 46.1 months. PBAC was not administered for the following reasons: 39 (55.7%) patients had comorbidities, 25 (35.7%) were older than 75 years, 19 (27.1%) patients underwent surgery before the approval of PBAC, and 3 (4.3%) patients could not continue PBAC (≤2 cycles) because of adverse events. PBAC patients (n = 24) were significantly younger than non-PBAC patients (n = 70; 66.3 vs 69.6 years old, respectively; p = 0.043). Disease-free survival (DFS) did not differ between PBAC and non-PBAC patients (55.0% and 67.1%, respectively; p = 0.266). PBAC patients tended to have worse overall survival (OS) than non-PBAC patients (56.1% and 70.2%, respectively; p = 0.138). PBAC was not prognostic for OS (hazard ratio (HR), 2.11; 95% confidence interval (CI), 0.82%-5.40%; p = 0.120).

CONCLUSION

PBAC did not improve the prognoses of patients with pathological stage II or stage III SCC in the single institution experience.