Comparison of prognostic impact of lymphovascular invasion in stage IA non-small cell lung cancer after lobectomy versus sublobar resection: A propensity score-matched analysis

Development and validation of a deep learning signature for predicting lymphovascular invasion and survival outcomes in clinical stage IA lung adenocarcinoma: A multicenter retrospective cohort study

PURPOSE

The presence of lymphovascular invasion (LVI) influences the management and outcomes of patients with clinical stage IA lung adenocarcinoma. The objective was the development of a deep learning (DL) signature for the prediction of LVI and stratification of prognosis.

METHODS

A total of 2077 patients from three centers were retrospectively enrolled and divided into a training set (n = 1515), an internal validation set (n = 381), and an external set (n = 181). A -three-dimensional residual neural network was used to extract the DL signature and three models, namely, the clinical, DL, and combined models, were developed. Diagnostic efficiency was assessed by ROC curves and AUC values. Kaplan-Meier curves and Cox proportional hazards regression analyses were conducted to evaluate links between various factors and disease-free survival.

RESULTS

The DL model could effectively predict LVI, shown by AUC values of 0.72 (95 %CI: 0.68-0.76) and 0.63 (0.54-0.73) in the internal and external validation sets, respectively. The incorporation of DL signature and clinical-radiological factors increased the AUC to 0.74 (0.71-0.78) and 0.77 (0.70-0.84) in comparison with the DL and clinical models (AUC of 0.71 [0.68-0.75], 0.71 [0.61-0.81]) in the internal and external validation sets, respectively. Pathologic LVI, LVI predicted by both DL and combined models were associated with unfavorable prognosis (all p < 0.05).

CONCLUSION

The effectiveness of the DL signature in the diagnosis of LVI and prognosis prediction in patients with clinical stage IA lung adenocarcinoma was demonstrated. These findings suggest the potential of the model in clinical decision-making.

Sublobar resection in non-small cell lung cancer: patient selection criteria and risk factors for recurrence

OBJECTIVE

To validate selection criteria for sublobar resection in patients with lung cancer with respect to recurrence, and to investigate predictors for recurrence in patients for whom the criteria are not suitable.

METHODS

Patients who underwent sublobar resection for lung cancer between July 2010 and December 2018 were retrospectively included. The criteria for curative sublobar resection were consolidation-to-tumor ratio ≤0.50 and size ≤3.0 cm in tumors with a ground-glass opacity (GGO) component (GGO group), and size of ≤2.0 cm and volume doubling time ≥400 days in solid tumors (solid group). Cox regression was used to identify predictors for time-to-recurrence (TTR) in tumors outside of these criteria (non-curative group).

RESULTS

Out of 530 patients, 353 were classified into the GGO group and 177 into the solid group. In the GGO group, the 2-year recurrence rates in curative and non-curative groups were 2.1 and 7.7%, respectively (p = 0.054). In the solid group, the 2-year recurrence rates in curative and non-curative groups were 0.0 and 28.6%, respectively (p = 0.03). Predictors of 2-year TTR after non-curative sublobar resection were pathological nodal metastasis (hazard ratio [HR], 6.63; p = 0.02) and lymphovascular invasion (LVI; HR, 3.28; p = 0.03) in the GGO group, and LVI (HR, 4.37; p < 0.001) and fibrosis (HR, 3.18; p = 0.006) in the solid group.

CONCLUSION

The current patient selection criteria for sublobar resection are satisfactory. LVI was a predictor for recurrence after non-curative resection.

ADVANCES IN KNOWLEDGE

This result supports selection criteria of patients for sublobar resection. LVI may help predict recurrence after non-curative sublobar resection.

The American Association for Thoracic Surgery (AATS) 2023 Expert Consensus Document: Staging and multidisciplinary management of patients with early-stage non-small cell lung cancer

Novel targeted therapy and immunotherapy drugs have recently been approved for use in patients with surgically resectable lung cancer. Accurate staging, early molecular testing, and knowledge of recent trials are critical to optimize oncologic outcomes in these patients.

Intratumoral and peritumoral radiomics nomograms for the preoperative prediction of lymphovascular invasion and overall survival in non-small cell lung cancer

OBJECTIVES

To evaluate the predictive value of intratumoral and peritumoral radiomics and radiomics nomogram for preoperative lymphovascular invasion (LVI) status and overall survival (OS) in patients with non-small cell lung cancer (NSCLC).

METHODS

In total, 240 NSCLC patients from our institution were randomly divided into the training cohort (n = 145) and internal validation cohort (n = 95) with a ratio of 6:4, and 65 patients from the Cancer Imaging Archive were enrolled as the external validation cohort. We extracted 1217 CT-based radiomics features from the gross tumor volume (GTV) and gross tumor volume incorporating peritumoral 3, 6, and 9 mm regions (GPTV₃, GPTV₆, GPTV₉). A radiomics nomogram based on clinical independent predictors and radiomics score (Radscore) of the best radiomics model was constructed. The correlation between factors and OS was evaluated with the Kaplan-Meier survival analysis and Cox proportional hazards regression analysis.

RESULTS

Compared with GTV, GPTV₃, and GPTV₆ radiomics models, GPTV₉ radiomics model exhibited better prediction performance with the AUCs of 0.82, 0.75, and 0.67 in the training, internal validation, and external validation cohorts, respectively. In the clinical model, smoking and clinical stage were independent predictors. The nomogram incorporating independent predictors and GPTV₉-Radscore was clinically useful, with the AUCs of 0.89, 0.83, and 0.66 in three cohorts. Pathological LVI, GPTV₉-Radscore-predicted, and Nomoscore-predicted LVI were associated with poor OS (p < 0.05).

CONCLUSIONS

CT-based radiomics nomogram can predict LVI and OS in patients with NSCLC and may help in making personalized treatment strategies before surgery.

KEY POINTS

• Compared with GTV, GPTV₃, and GPTV₆ radiomics models, GPTV₉ radiomics model showed better prediction performance for LVI status in NSCLC. • The radiomics nomogram based on GPTV₉ radiomics features and clinical independent predictors could effectively predict LVI status and OS in NSCLC and outperformed the clinical model. • The radiomics nomogram had a wider scope of clinical application.

Lymphovascular invasion: A non-sized T descriptor for stage IA non-small cell lung cancer

Background

Lymphovascular invasion (LVI) has not been included in the tumor‐node‐metastasis (TNM) staging manual of non‐small‐cell lung cancer (NSCLC). We aimed to investigate the predictive value of LVI on stage IA NSCLC and proposed a method of incorporating LVI into the T category based on the latest TNM staging manual.

Methods

The least absolute shrinkage and selection operator (LASSO)‐penalized Cox multivariable regression model was performed to identify prognostic factors. The Kaplan–Meier method was used to compare overall survival (OS) and disease‐free survival (DFS) between groups. Propensity score matching (PSM) was used to minimize bias.

Results

A total of 1452 eligible stage I NSCLC cases (stage IA without LVI, 1022 cases; stage IA with LVI, 120 cases; stage IB, 310 cases) were included. LASSO‐penalized multivariable Cox analysis revealed that LVI was an independent prognostic factor for both OS and DFS. Survival analysis demonstrated that the survivals of stage IA NSCLCs without LVI were better than those of stage IA with LVI and stage IB NSCLCs. In the matched cohort, the survivals of stage IA NSCLCs with LVI were comparable to those of stage IB NSCLCs.

Conclusions

Stage IA NSCLCs with LVI and stage IB NSCLCs had similar survivals, and we proposed that LVI might be a non‐sized T descriptor that upstaged stage IA diseases to stage IB.

Sublobar Resection in Stage IA Non-Small Cell Lung Cancer: Role of Preoperative CT Features in Predicting Pathologic Lymphovascular Invasion and Postoperative Recurrence

BACKGROUND. Prognostic factors on preoperative CT in stage IA non-small cell lung cancer (NSCLC) may help select patients for sublobar resection or lobectomy. OBJECTIVE. The purpose of this study was to identify CT features predictive of pathologic lymphovascular invasion (LVI) in stage IA NSCLC and to evaluate the features' prognostic value in patients who undergo sublobar resection. METHODS. This retrospective study included 904 patients (mean age, 62.0 years; 453 men, 451 women) who underwent lobectomy (n = 574) or sublobar resection (n = 330) for stage IA NSCLC. Two thoracic radiologists independently evaluated findings on pre-operative chest CT and then resolved discrepancies. Recurrences were identified from medical record review. Multivariable logistic regression was used to identify independent predictors of pathologic LVI. Multivariable Cox proportional hazards models were used to identify prognostic features. Interreader agreement was assessed. RESULTS. Pathologic LVI was present in 10.2% (92/904) of patients. It was present only in solid-dominant part-solid nodules (PSNs) and solid nodules and only in nodules with a solid portion diameter over 10 mm. Among solid-dominant PSNs and solid nodules with a solid portion diameter over 10 mm, independent (p < .05) predictors of pathologic LVI were peritumoral interstitial thickening (odds ratio [OR], 13.22) and pleural contact (defined as pleural contact measuring over one-quarter of the circumference of the nodule's solid portion) (OR, 2.45). Also among such nodules, peritumoral interstitial thickening achieved 80.4% sensitivity, 76.7% specificity, and 77.4% accuracy; pleural contact achieved 35.9% sensitivity, 82.5% specificity, and 74.3% accuracy; and presence of either feature achieved 90.2% sensitivity, 64.3% specificity, and 68.9% accuracy for predicting pathologic LVI. In patients undergoing sublobar resection, after adjusting for T category and operative type, recurrence-free survival (RFS) was independently (p < .05) predicted by solid-dominant PSN or solid nodule with a solid portion diameter over 10 mm also showing peritumoral interstitial thickening (hazard ratio [HR], 5.37) or also showing either peritumoral interstitial thickening or pleural contact (HR, 6.05). The interreader agreement kappa values were 0.67 for peritumoral interstitial thickening and 0.77 for pleural contact. CONCLUSION. Pathologic LVI occurred only in solid-dominant PSNs and solid nodules with solid portion over 10 mm. Among such nodules, peritumoral interstitial thickening and pleural contact independently predicted pathologic LVI and RFS. CLINICAL IMPACT. CT features may help select patients with stage IA NSCLC for sublobar resection rather than more extensive surgery.

Association of postoperative recurrence with radiological and clinicopathological features in patients with stage IA-IIA lung adenocarcinoma

OBJECTIVES

To retrospectively investigate whether radiological and clinicopathological characteristics were associated with the presence of stage IA-IIA lung adenocarcinoma in patients at high risk for a postoperative recurrence.

MATERIALS AND METHODS

Three hundred twelve patients with biopsy-proven node-negative early-stage (IA-IIA) lung adenocarcinoma met the inclusion criteria for this study. Demographics data and histopathological findings were collected from medical records. Computed tomography (CT) performed approximately 1 month before surgery was manually scored using 23 CT descriptors. Univariate analyses were applied to demonstrate an association between clinicopathological and radiological features and 2-/5-year recurrences. Multivariate logistic regression was performed to assess the ability of radiological and clinicopathological features to discriminate low and high-risk factors for recurrence. A ROC curve was used to evaluate prediction performance.

RESULTS

Univariate analysis revealed that the 2-year recurrence was associated with six radiological features and two clinicopathological features, while 5-year recurrence was associated with five radiological features and two clinicopathological features. A multivariate logistic regression model of combined clinicopathological and radiological features showed that stage IIA (OR = 2.87), solid texture (solid part > 50 %: OR = 4.81; solid part = 100 %: OR = 3.61), pleural attachment (OR = 3.97) and bronchovascular bundle thickening (OR = 2.16) were associated with the independent predictors of 2-year recurrence, and stage IIA (OR = 3.52), solid texture (solid part > 50 %: OR = 3.56; solid part = 100 %: OR = 2.44) and pleural attachment (OR = 4.57) were associated with 5-year recurrence. Combined radiological and clinicopathological features could be significant indicators of 2- and 5-year recurrences (AUC = 0.784 and AUC = 0.815, respectively).

CONCLUSIONS

The combination of radiological and clinicopathological features has the potential to help predict postoperative recurrence in patients with stage IA-IIA lung adenocarcinomas and guide oncologists and patients whether to undergo additional treatment after surgery.

Blood Vessel Invasion Predicts Postoperative Survival Outcomes and Systemic Recurrence Regardless of Location or Blood Vessel Type in Patients with Lung Adenocarcinoma

BACKGROUND

Presence of blood vessel invasion (BVI) is one of the prognostic indicators for lung cancer patients with surgical resection. However, prognostic roles of the location and the type of the involved blood vessel have not been fully evaluated yet.

PATIENTS AND METHODS

We retrieved the data of 217 cases of surgically resected lung adenocarcinoma from Asan Medical Center. Clinicopathologic features, including BVI, were reassessed. The location (tumor center and/or periphery) and involved blood vessel types (large and/or small vessels; arteries and/or veins) of BVI were separately examined on standard hematoxylin-eosin slides and confirmed by van Gieson elastic staining.

RESULTS

BVI was identified in 35% of cases (76/217), with the tumor center (intratumoral) as the location in more than half of the cases (42/76, 55.3%). The presence of BVI was significantly associated with higher pathologic stage, increased size of invasive components, frequent pleural invasion, lymphatic permeation, and spread through alveolar spaces. BVI was significantly associated with poor overall survival (OS) and recurrence-free survival (RFS) both in univariate and multivariate survival analyses [for OS, hazard ratio (HR) 1.92, 95% confidence interval (CI) 1.06-3.48, P = 0.031; for RFS, HR 2.65, 95% CI 1.64-4.28; P < 0.001]. BVI subgroups, according to location and type of the involved blood vessels, invariably displayed significantly poor RFS; however, the results for OS varied.

CONCLUSION

Regardless of their location or blood vessel type, presence of BVI is a useful predictor for postoperative survival outcomes, which should be carefully evaluated on pathologic examination.

Utility of Volumetric Metabolic Parameters on Preoperative FDG PET/CT for Predicting Tumor Lymphovascular Invasion in Non-Small Cell Lung Cancer

Background: Lymphovascular invasion (LVI) is an adverse prognostic indicator in non-small cell lung cancer (NSCLC) and serves as an indication for postoperative adjuvant chemotherapy recommendation after resection. Objective: To assess the utility of clinicopathologic factors and volumetric metabolic parameters from preoperative FDG PET/CT in predicting primary tumor LVI in NSCLC. Methods: This retrospective study included 161 patients (mean age, 61.8±8.1 years; 111 men, 50 women) with surgically-confirmed NSCLC who underwent preoperative FDG PET/CT between January 2018 and November 2020. Two nuclear medicine physicians used software to place automated volumes of interest delineating each tumor to record metabolic indices (SUVmax, SUVmean, and metabolictumor volume [MTV]), which in turn were used to calculate total lesion glycolysis (TLG). Measurements were first performed independently to determine interobserver agreement using intraclass correlation coefficients (ICCs) and then repeated in consensus. Associations of clinicopathologic and metabolic parameters with tumor LVI status were assessed using t test, Mann-Whitney U test, and chi-squared test. Diagnostic performance was assessed using ROC analysis. Multivariable logistic regression analysis was performed to identify independent predictors of tumor LVI. Results: A total of 23.6% (38/161) of patients had LVI. Interobserver agreement was ICC=1.000 for SUVmax, ICC=0.997 for SUVmean, and 0.999 for MTV. Tumors with LVI, compared with tumors without LVI, exhibited higher SUVmax (15.4±5.9 vs 11.7±7.5, p=.006), SUVmean (6.0±1.6 vs 5.1±2.0, p=.009), MTV (median 15.8 cm3 vs 5.5 cm3, p<.001), and TLG (median 88.8 vs 24.5, p<.001). Among the metabolic parameters, AUC was highest for MTV (0.704), with optimal MTV cutoff of 6.4 cm3 yielding sensitivity 92.1% (35/38), specificity 56.1% (69/123), PPV 39.3% (35/89), and NPV 95.8% (69/72) for LVI. Independent predictors (p<.05) of LVI were MTV (≥6.4 cm3, odds ratio [OR]=6.5), N1 (OR=6.4) or N2 (OR=4.0) disease, and T2 disease (OR=3.6). These factors combined achieved AUC of 0.854 for LVI. Conclusion: The volumetric metabolic parameter MTV from preoperative FDG PET/CT is an independent predictor of tumor LVI in NSCLC. Clinical Impact: Further studies are warranted to assess the potential role of preoperative prediction of LVI using FDG PET/CT to help guide clinical decision making in NSCLC.