Association of Fluorodeoxyglucose Positron Emission Tomography Radiomics Features with Clinicopathological Factors and Prognosis in Lung Squamous Cell Cancer

[18F]FDG PET/CT is useful in discriminating invasive adenocarcinomas among pure ground-glass nodules: comparison with CT findings-a bicenter retrospective study

PURPOSE

Predicting the malignancy of pure ground-glass nodules (GGNs) using CT is challenging. The optimal role of [18F]FDG PET/CT in this context has not been clarified. We compared the performance of [18F]FDG PET/CT in evaluating GGNs for predicting invasive adenocarcinomas (IACs) with CT.

METHODS

From June 2012 to December 2020, we retrospectively enrolled patients with pure GGNs on CT who underwent [18F]FDG PET/CT within 90 days. Overall, 38 patients with 40 ≥ 1-cm GGNs were pathologically confirmed. CT images were analyzed for size, attenuation, uniformity, shape, margin, tumor-lung interface, and internal/surrounding characteristics. Visual [18F]FDG positivity, maximum standardized uptake value (SUVmax), and tissue fraction-corrected SUVmax (SUVmaxTF) were evaluated on PET/CT.

RESULTS

The histopathology of the 40 GGNs were: 25 IACs (62.5%), 9 minimally invasive adenocarcinomas (MIA, 22.5%), and 6 adenocarcinomas in situ (AIS, 15.0%). No significant differences were found in CT findings according to histopathology, whereas visual [18F]FDG positivity, SUVmax, and SUVmaxTF were significantly different (P=0.001, 0.033, and 0.018, respectively). The size, visual [18F]FDG positivity, SUVmax, and SUVmaxTF showed significant diagnostic performance to predict IACs (area under the curve=0.693, 0.773, 0.717, and 0.723, respectively; P=0.029, 0.001, 0.018, and 0.013, respectively). In the multivariate logistic regression analysis, visual [18F]FDG positivity discriminated IACs among GGNs among various CT and PET findings (P=0.008).

CONCLUSIONS

[18F]FDG PET/CT demonstrated superior diagnostic performance compared to CT in differentiating IAC from AIS/MIA among pure GGNs, thus it has the potential to guide the proper management of patients with pure GGNs.

18F-Fluorodeoxyglucose Positron Emission Tomography-Based Risk Score Model for Prediction of Five-Year Survival Outcome after Curative Resection of Non-Small-Cell Lung Cancer

The aim of our retrospective study is to develop and assess an imaging-based model utilizing 18F-FDG PET parameters for predicting the five-year survival in non-small-cell lung cancer (NSCLC) patients after curative surgery. A total of 361 NSCLC patients who underwent curative surgery were assigned to the training set (n = 253) and the test set (n = 108). The LASSO regression model was used to construct a PET-based risk score for predicting five-year survival. A hybrid model that combined the PET-based risk score and clinical variables was developed using multivariate logistic regression analysis. The predictive performance was determined by the area under the curve (AUC). The individual features with the best predictive performances were co-occurrence_contrast (AUC = 0.675) and SUL peak (AUC = 0.671). The PET-based risk score was identified as an independent predictor after adjusting for clinical variables (OR 5.231, 95% CI 1.987-6.932; p = 0.009). The hybrid model, which integrated clinical variables, significantly outperformed the PET-based risk score alone in predictive accuracy (AUC = 0.771 vs. 0.696, p = 0.022), a finding that was consistent in the test set. The PET-based risk score, especially when integrated with clinical variables, demonstrates good predictive ability for five-year survival in NSCLC patients following curative surgery.

A comparison between centralized and asynchronous federated learning approaches for survival outcome prediction using clinical and PET data from non-small cell lung cancer patients

BACKGROUND AND OBJECTIVE

Survival analysis plays an essential role in the medical field for optimal treatment decision-making. Recently, survival analysis based on the deep learning (DL) approach has been proposed and is demonstrating promising results. However, developing an ideal prediction model requires integrating large datasets across multiple institutions, which poses challenges concerning medical data privacy.

METHODS

In this paper, we propose FedSurv, an asynchronous federated learning (FL) framework designed to predict survival time using clinical information and positron emission tomography (PET)-based features. This study used two datasets: a public radiogenic dataset of non-small cell lung cancer (NSCLC) from the Cancer Imaging Archive (RNSCLC), and an in-house dataset from the Chonnam National University Hwasun Hospital (CNUHH) in South Korea, consisting of clinical risk factors and F-18 fluorodeoxyglucose (FDG) PET images in NSCLC patients. Initially, each dataset was divided into multiple clients according to histological attributes, and each client was trained using the proposed DL model to predict individual survival time. The FL framework collected weights and parameters from the clients, which were then incorporated into the global model. Finally, the global model aggregated all weights and parameters and redistributed the updated model weights to each client. We evaluated different frameworks including single-client-based approach, centralized learning and FL.

RESULTS

We evaluated our method on two independent datasets. First, on the RNSCLC dataset, the mean absolute error (MAE) was 490.80±22.95 d and the C-Index was 0.69±0.01. Second, on the CNUHH dataset, the MAE was 494.25±40.16 d and the C-Index was 0.71±0.01. The FL approach achieved centralized method performance in PET-based survival time prediction and outperformed single-client-based approaches.

CONCLUSIONS

Our results demonstrated the feasibility and effectiveness of employing FL for individual survival prediction in NSCLC patients, using clinical information and PET-based features.

Machine learning for differentiating lung squamous cell cancer from adenocarcinoma using Clinical-Metabolic characteristics and 18F-FDG PET/CT radiomics

Noninvasive differentiation between the squamous cell carcinoma (SCC) and adenocarcinoma (ADC) subtypes of non-small cell lung cancer (NSCLC) could benefit patients who are unsuitable for invasive diagnostic procedures. Therefore, this study evaluates the predictive performance of a PET/CT-based radiomics model. It aims to distinguish between the histological subtypes of lung adenocarcinoma and squamous cell carcinoma, employing four different machine learning techniques. A total of 255 Non-Small Cell Lung Cancer (NSCLC) patients were retrospectively analyzed and randomly divided into the training (n = 177) and validation (n = 78) sets, respectively. Radiomics features were extracted, and the Least Absolute Shrinkage and Selection Operator (LASSO) method was employed for feature selection. Subsequently, models were constructed using four distinct machine learning techniques, with the top-performing algorithm determined by evaluating metrics such as accuracy, sensitivity, specificity, and the area under the curve (AUC). The efficacy of the various models was appraised and compared using the DeLong test. A nomogram was developed based on the model with the best predictive efficiency and clinical utility, and it was validated using calibration curves. Results indicated that the logistic regression classifier had better predictive power in the validation cohort of the radiomic model. The combined model (AUC 0.870) exhibited superior predictive power compared to the clinical model (AUC 0.848) and the radiomics model (AUC 0.774). In this study, we discovered that the combined model, refined by the logistic regression classifier, exhibited the most effective performance in classifying the histological subtypes of NSCLC.

Prognostic Significance of Volumetric Parameters Based on FDG PET/CT in Patients with Lung Adenocarcinoma Undergoing Curative Surgery

INTRODUCTION

FDG PET/CT is a robust imaging modality to diagnose and stratify prognoses for non-small cell lung carcinoma. However, the role of FDG PET/CT in operable lung adenocarcinoma patients has not been previously investigated in a large cohort with varying pathological stages. The prognostic value of volumetric parameters based on FDG PET/CT was investigated in patients with stage I-III lung adenocarcinoma receiving curative surgery.

METHODS

This retrospective study included 432 patients with lung adenocarcinoma undergoing preoperative FDG PET/CT between January 2016 and December 2017. Clinicopathologic variables, conventional image parameters, such as the maximum standardized uptake value (SUVmax) and mean SUV (SUVmean) of the primary tumor, and volumetric parameters, such as metabolic tumor volume (MTV) and total lesion glycolysis (TLG), were included in Cox regression analysis. Subgroup analysis was conducted to compare hazard ratios (HRs) based on MTV in each pathological stage. A new staging system including volumetric parameters was suggested.

RESULTS

A total of 432 patients (median age: 62 years; interquartile range: 56-70 years; 225 males) were evaluated. Sex, age, presence of EGFR mutation, pathological stage, MTV, and TLG of the primary tumor were selected as statistically significant prognostic factors for overall survival irrespective of other variables (OS; p < 0.05 for all). Pathological stage, MTV, and TLG of the primary tumor were selected as statistically significant prognostic factors for disease-free survival irrespective of other variables (p < 0.05 for all). The suggested new staging system including MTV as an additional criterion showed better discrimination and prediction for OS than the conventional pathological staging system despite statistical insignificance (concordance index: 0.698 vs. 0.673).

CONCLUSIONS

The volumetric parameters of the primary tumor based on preoperative FDG PET/CT were independent prognostic factors in addition to pathological stage in patients with operable lung adenocarcinoma. The suggested new staging system considering MTV predicted the prognoses better than the conventional pathological staging system.