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

PET radiomics-based lymphovascular invasion prediction in lung cancer using multiple segmentation and multi-machine learning algorithms

The current study aimed to predict lymphovascular invasion (LVI) using multiple machine learning algorithms and multi-segmentation positron emission tomography (PET) radiomics in non-small cell lung cancer (NSCLC) patients, offering new avenues for personalized treatment strategies and improving patient outcomes. One hundred and twenty-six patients with NSCLC were enrolled in this study. Various automated and semi-automated PET image segmentation methods were applied, including Local Active Contour (LAC), Fuzzy-C-mean (FCM), K-means (KM), Watershed, Region Growing (RG), and Iterative thresholding (IT) with different percentages of the threshold. One hundred five radiomic features were extracted from each region of interest (ROI). Multiple feature selection methods, including Minimum Redundancy Maximum Relevance (MRMR), Recursive Feature Elimination (RFE), and Boruta, and multiple classifiers, including Multilayer Perceptron (MLP), Logistic Regression (LR), XGBoost (XGB), Naive Bayes (NB), and Random Forest (RF), were employed. Synthetic Minority Oversampling Technique (SMOTE) was also used to determine if it boosts the area under the ROC curve (AUC), accuracy (ACC), sensitivity (SEN), and specificity (SPE). Our results indicated that the combination of SMOTE, IT (with 45% threshold), RFE feature selection and LR classifier showed the best performance (AUC = 0.93, ACC = 0.84, SEN = 0.85, SPE = 0.84) followed by SMOTE, FCM segmentation, MRMR feature selection, and LR classifier (AUC = 0.92, ACC = 0.87, SEN = 1, SPE = 0.84). The highest ACC belonged to the IT segmentation (with 45 and 50% thresholds) alongside Boruta feature selection and the NB classifier without SMOTE (ACC = 0.9, AUC = 0.78 and 0.76, SEN = 0.7, and SPE = 0.94, respectively). Our results indicate that selection of appropriate segmentation method and machine learning algorithm may be helpful in successful prediction of LVI in patients with NSCLC with high accuracy using PET radiomics analysis.

The role of baseline 18F-FDG PET/CT for survival prognosis in NSCLC patients undergoing immunotherapy: a systematic review and meta-analysis

Background

The value of pretreatment baseline 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET)/computed tomography (CT) as a prognostic factor for survival of patients with non-small-cell lung cancer (NSCLC) receiving immunotherapy remained uncertain.

Objectives

To investigate the prognostic ability of baseline 18F-FDG PET/CT in patients with NSCLC receiving immunotherapy.

Design

A systematic review and meta-analysis.

Data sources and methods

We searched the PubMed, EMBASE, and Cochrane Central Register of Controlled Trials databases until May 7, 2024, and extracted data related to patient characteristics, semiquantitative parameters of 18F-FDG PET/CT, and survival. We pooled hazard ratios (HRs) to evaluate the prognostic value of the maximum standardized uptake value (SUVmax), mean standardized uptake value (SUVmean), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) for overall survival (OS) and progression-free survival (PFS).

Results

A total of 22 studies (1363 patients, average age range 30-88 years) were included. Baseline 18F-FDG PET/CT-derived MTV was significantly associated with both OS (HR: 1.124, 95% confidence interval (CI) 1.058-1.195, I 2 = 81.70%) and PFS (HR: 1.069, 95% CI: 1.016-1.124, I 2 = 71.80%). Other baseline 18F-FDG PET/CT-derived parameters, including SUVmax (OS: HR: 0.930, 95% CI: 0.718-1.230; PFS: HR: 0.979, 95% CI: 0.759-1.262), SUVmean (OS: HR: 0.801, 95% CI: 0.549-1.170; PFS: HR: 0.688, 95% CI: 0.464-1.020), and TLG (OS: HR: 0.999, 95% CI: 0.980-1.018; PFS: HR: 0.995, 95% CI: 0.980-1.010), were not associated with survival. Sensitivity analyses by removing one study at a time did not significantly alter the association between MTV and PFS or between MTV and OS. There was no evidence of publication bias.

Conclusion

Pretreatment baseline 18F-FDG PET/CT-derived MTV might be a prognostic biomarker in NSCLC patients receiving immunotherapy. Further studies are needed to support routine use.

Predicting lymphovascular invasion in N0 stage non-small cell lung cancer: A nomogram based on Dual-energy CT imaging and clinical findings

PURPOSE

To construct a nomogram for predicting lymphovascular invasion (LVI) in N0 stage non-small cell lung cancer (NSCLC) using dual-energy computed tomography (DECT) findings combined with clinical findings.

METHODS

We retrospectively recruited 135 patients with N0 stage NSCLC from two hospitals underwent DECT before surgery and were divided into development cohort (n = 107) and validation cohort (n = 28). The clinical findings (baseline characteristics, biochemical markers, serum tumor markers and Immunohistochemical markers), DECT-derived parameters (iodine concentration [IC], effective atomic number [Eff-Z] and normalized iodine concentration [NIC], iodine enhancement [IE] and NIC ratio [NICr]) and Fractal dimension (FD) were collected and measured. A nomogram was constructed using significant findings to predict LVI in N0 stage NSCLC and was externally validated.

RESULTS

Multivariable analysis revealed that lymphocyte count (LYMPH, odds ratio [OR]: 3.71, P=0.014), IC in arterial phase (ICa, OR: 1.25, P=0.021), NIC in venous phase (NICv, OR: 587.12, P=0.009) and FD (OR: 0.01, P=0.033) were independent significant factors for predicting LVI in N0 stage NSCLC, and were used to construct a nomogram. The nomogram exhibited robust predictive capabilities in both the development and validation cohort, with AUCs of 0.819 (95 % CI: 72.6-90.4) and 0.844 (95 % CI: 68.2-95.8), respectively. The calibration plots showed excellent agreement between the predicted probabilities and the actual rates of positive LVI, on external validation.

CONCLUSIONS

Combination of clinical and DECT imaging findings could aid in predicting LVI in N0 stage NSCLC using significant findings of LYMPH, ICa, NICv and FD.

2.5D peritumoural radiomics predicts postoperative recurrence in stage I lung adenocarcinoma

Objective

Radiomics can non-invasively predict the prognosis of a tumour by applying advanced imaging feature algorithms.The aim of this study was to predict the chance of postoperative recurrence by modelling tumour radiomics and peritumour radiomics and clinical features in patients with stage I lung adenocarcinoma (LUAD).

Materials and methods

Retrospective analysis of 190 patients with postoperative pathologically confirmed stage I LUAD from centre 1, who were divided into training cohort and internal validation cohort, with centre 2 added as external validation cohort. To develop a combined radiation-clinical omics model nomogram incorporating clinical features based on images from low-dose lung cancer screening CT plain for predicting postoperative recurrence and to evaluate the performance of the nomogram in the training cohort, internal validation cohort and external validation cohort.

Results

A total of 190 patients were included in the model in centre 1 and randomised into a training cohort of 133 and an internal validation cohort of 57 in a ratio of 7:3, and 39 were included in centre 2 as an external validation cohort. In the training cohort (AUC=0.865, 95% CI 0.824-0.906), internal validation cohort (AUC=0.902, 95% CI 0.851-0.953) and external validation cohort (AUC=0.830,95% CI 0.751-0.908), the combined radiation-clinical omics model had a good predictive ability. The combined model performed significantly better than the conventional single-modality models (clinical model, radiomic model), and the calibration curve and decision curve analysis (DCA) showed high accuracy and clinical utility of the nomogram.

Conclusion

The combined preoperative radiation-clinical omics model provides good predictive value for postoperative recurrence in stage ILUAD and combines the model's superiority in both internal and external validation cohorts, demonstrating its potential to aid in postoperative treatment strategies.

18F-fluorodeoxyglucose positron emission tomography/computed tomography parameters are associated with histological outcomes in superficial esophageal squamous cell carcinoma

Endoscopic submucosal dissection is a standard treatment for early esophageal squamous cell carcinoma. However, submucosal or lymphovascular invasion increases the risk of lymph node metastasis. Although 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) parameters are associated with prognosis in patients with advanced esophageal squamous cell carcinoma, the utility of FDG PET/CT in diagnosing superficial esophageal carcinoma remains unclear. This study aimed to investigate the association between FDG PET/CT parameters and histopathological findings in superficial esophageal carcinoma. Fifty-three patients with superficial esophageal cancer who underwent FDG PET/CT scans before undergoing interventions were retrospectively analyzed. The maximal standardized uptake value (SUVmax), metabolic tumor volume, and total lesion glycolysis were significantly higher in the cases with submucosal invasion (T1b) compared with those confined to the muscularis mucosa (T1a). In contrast, classification of intrapapillary capillary loops patterns with magnifying endoscopy did not yield statistical differences between T1a and T1b. Multivariable analysis revealed that SUVmax was the only independent predictor of submucosal and lymphovascular invasion. This study demonstrated that SUVmax may be useful in predicting submucosal and lymphovascular invasion. Thus, the value of SUVmax may guide clinical decision-making in superficial esophageal squamous cell carcinoma.

68Ga-FAPI-04 PET/CT in Non-Small Cell Lung Cancer: Accurate Evaluation of Lymph Node Metastasis and Correlation with Fibroblast Activation Protein Expression

Fibroblast activation protein (FAP) is a promising diagnostic and therapeutic target in various solid tumors. This study aimed to assess the diagnostic efficiency of 68Ga-labeled FAP inhibitor (FAPI)-04 PET/CT for detecting lymph node metastasis in non-small cell lung cancer (NSCLC) and to investigate the correlation between tumor 68Ga-FAPI-04 uptake and FAP expression. Methods: We retrospectively enrolled 136 participants with suspected or biopsy-confirmed NSCLC who underwent 68Ga-FAPI-04 PET/CT for initial staging. The diagnostic performance of 68Ga-FAPI-04 for the detection of NSCLC was evaluated. The final histopathology or typical imaging features were used as the reference standard. The SUVmax and SUVmean, 68Ga-FAPI-avid tumor volume (FTV), and total lesion FAP expression (TLF) were measured and calculated. FAP immunostaining of tissue specimens was performed. The correlation between 68Ga-FAPI-04 uptake and FAP expression was assessed using the Spearman correlation coefficient. Results: Ninety-one participants (median age, 65 y [interquartile range, 58-70 y]; 69 men) with NSCLC were finally analyzed. In lesion-based analysis, the diagnostic sensitivity and positive predictive value of 68Ga-FAPI-04 PET/CT for detection of the primary tumor were 96.70% (88/91) and 100% (88/88), respectively. In station-based analysis, the diagnostic sensitivity, specificity, and accuracy for the detection of lymph node metastasis were 72.00% (18/25), 93.10% (108/116), and 89.36% (126/141), respectively. Tumor 68Ga-FAPI-04 uptake (SUVmax, SUVmean, FTV, and TLF) correlated positively with FAP expression (r = 0.470, 0.477, 0.582, and 0.608, respectively; all P ≤ 0.001). The volume parameters FTV and TLF correlated strongly with FAP expression in 31 surgical specimens (r = 0.700 and 0.770, respectively; both P < 0.001). Conclusion: 68Ga-FAPI-04 PET/CT had excellent diagnostic efficiency for detecting lymph node metastasis, and 68Ga-FAPI-04 uptake showed a close association with FAP expression in participants with NSCLC.

18F-FDG PET/CT radiomics for prediction of lymphovascular invasion in patients with early stage non-small cell lung cancer

Objective

To explore a prediction model for lymphovascular invasion (LVI) on cT1-2N0M0 radiologic solid non-small cell lung cancer (NSCLC) based on a 2-deoxy-2[18F]fluoro-D-glucose ([18F]F-FDG) positron emission tomography-computed tomography (PET-CT) radiomics analysis.

Methods

The present work retrospectively included 148 patients receiving surgical resection and verified pathologically with cT1-2N0M0 radiologic solid NSCLC. The cases were randomized into training or validation sets in the ratio of 7:3. PET and CT images were used to select optimal radiomics features. Three radiomics predictive models incorporating CT, PET, as well as PET/CT images radiomics features (CT-RS, PET-RS, PET/CT-RS) were developed using logistic analyses. Furthermore, model performance was evaluated by ROC analysis for predicting LVI status. Model performance was evaluated in terms of discrimination, calibration along with clinical utility. Kaplan-Meier curves were employed to analyze the outcome of LVI.

Results

The ROC analysis demonstrated that PET/CT-RS (AUCs were 0.773 and 0.774 for training and validation sets) outperformed both CT-RS(AUCs, 0.727 and 0.752) and PET-RS(AUCs, 0.715 and 0.733). A PET/CT radiology nomogram (PET/CT-model) was developed to estimate LVI; the model demonstrated conspicuous prediction performance for training (C-index, 0.766; 95%CI, 0.728-0.805) and validation sets (C-index, 0.774; 95%CI, 0.702-0.846). Besides, decision curve analysis and calibration curve showed that PET/CT-model provided clinically beneficial effects. Disease-free survival and overall survival varied significantly between LVI and non-LVI cases (P<0.001).

Conclusions

The PET/CT radiomics models could effectively predict LVI on early stage radiologic solid lung cancer and provide support for clinical treatment decisions.

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.

Predicting pathological highly invasive lung cancer from preoperative [18F]FDG PET/CT with multiple machine learning models

PURPOSE

The efficacy of sublobar resection of primary lung cancer have been proven in recent years. However, sublobar resection for highly invasive lung cancer increases local recurrence. We developed and validated multiple machine learning models predicting pathological invasiveness of lung cancer based on preoperative [¹⁸F]fluorodeoxyglucose (FDG) positron emission tomography (PET) and computed tomography (CT) radiomic features.

METHODS

Overall, 873 patients who underwent lobectomy or segmentectomy for primary lung cancer were enrolled. Radiomics features were extracted from preoperative PET/CT images with the PyRadiomics package. Seven machine learning models and an ensemble of all models (ENS) were evaluated after 100 iterations. In addition, the probability of highly invasive lung cancer was calculated in a nested cross-validation to assess the calibration plot and clinical usefulness and to compare to consolidation tumour ratio (CTR) on CT images, one of the generally used diagnostic criteria.

RESULTS

In the training set, when PET and CT features were combined, all models achieved an area under the curve (AUC) of ≥ 0.880. In the test set, ENS showed the highest mean AUC of 0.880 and smallest standard deviation of 0.0165, and when the cutoff was 0.5, accuracy of 0.804, F1 of 0.851, precision of 0.821, and recall of 0.885. In the nested cross-validation, the AUC of 0.882 (95% CI: 0.860-0.905) showed a high discriminative ability, and the calibration plot indicated consistency with a Brier score of 0.131. A decision curve analysis showed that the ENS was valid with a threshold probability ranging from 3 to 98%. Accuracy showed an improvement of more than 8% over the CTR.

CONCLUSION

The machine learning model based on preoperative [¹⁸F]FDG PET/CT images was able to predict pathological highly invasive lung cancer with high discriminative ability and stability. The calibration plot showed good consistency, suggesting its usefulness in quantitative risk assessment.