Quantitative computed tomography texture analysis: can it improve diagnostic accuracy to differentiate malignant lymph nodes?

Diagnostic accuracy and reliability of CT-based Node-RADS for colon cancer

OBJECTIVE

The Node-RADS classification was recently published as a classification system to better characterize lymph nodes in oncological imaging. The present analysis investigated the diagnostic benefit of the Node-RADS classification of staging computed tomography (CT) images to categorize and stage lymph nodes in patients with colon cancer.

MATERIALS AND METHODS

All patients were surgically resected and the lymph nodes were histopathological analyzed. All investigated lymph nodes were scored in accordance to the Node-RADS classification by two experienced radiologists. Interreader variability was assessed with Cohen's kappa analysis, discrimination analysis was performed with Mann-Whitney-U test and diagnostic accuracy was assessed with receiver-operating characteristics (ROC) curve analysis.

RESULTS

Overall, 108 patients (n = 49 females, 45.3%) with a mean age of 70.08 ± 14.34 years were included. In discrimination analysis, the total Node-RADS score showed statistically significant differences between N- and N + stage (for reader 1: mean 1.89 ± 1.09 score for N- versus 2.93 ± 1.62 score for N+, for reader 2: 1.33 ± 0.48 score for N- versus 3.65 ± 0.94 score for N+, p = 0.001, respectively). ROC curve analysis for lymph node discrimination showed an area under the curve of 0.68. A threshold value of 2 resulted in a sensitivity of 0.62 and a specificity of 0.71.

CONCLUSION

Node-RADS score derived from staging CT shows only limited diagnostic accuracy to correctly predict nodal positivity in colon cancer. The interreader variability seems to be high and should question the clinical translation for this tumour entity.

Clinical Variables and Radiomics Features for Predicting Pneumothorax in Patients Undergoing CT-guided Transthoracic Core Needle Biopsy

Purpose To develop a prediction model combining both clinical and CT texture analysis radiomics features for predicting pneumothorax complications in patients undergoing CT-guided core needle biopsy. Materials and Methods A total of 424 patients (mean age, 65.6 years ± 12.7 [SD]; 232 male, 192 female) who underwent CT-guided core needle biopsy between January 2021 and October 2022 were retrospectively included as the training data set. Clinical and procedure-related characteristics were documented. Texture analysis radiomics features were extracted from the subpleural lung parenchyma traversed by needle. Moderate pneumothorax was defined as a postprocedure air rim of 2 cm or greater. The prediction model was developed using logistic regression with backward elimination, presented by linear fusion of the selected features weighted by their coefficients. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Validation was conducted in an external cohort (n = 45; mean age, 58.2 years ± 12.7; 19 male, 26 female) from a different hospital. Results Moderate pneumothorax occurred in 12.0% (51 of 424) of the training cohort and 8.9% (four of 45) of the external test cohort. Patients with emphysema (P < .001) or a longer needle path length (P = .01) exhibited a higher incidence of moderate pneumothorax in the training cohort. Texture analysis features, including gray-level co-occurrence matrix cluster shade (P < .001), gray-level run-length matrix low gray-level run emphasis (P = .049), gray-level run-length matrix run entropy (P = .003), gray-level size-zone matrix gray-level variance (P < .001), and neighboring gray-tone difference matrix complexity (P < .001), showed higher values in patients with moderate pneumothorax. The combined clinical-radiomics model demonstrated satisfactory performance in both the training (AUC 0.78, accuracy = 71.9%) and external test cohorts (AUC 0.86, accuracy 73.3%). Conclusion The model integrating both clinical and radiomics features offered practical diagnostic performance and accuracy for predicting moderate pneumothorax in patients undergoing CT-guided core needle biopsy. Keywords: Biopsy/Needle Aspiration, Thorax, CT, Pneumothorax, Core Needle Biopsy, Texture Analysis, Radiomics, CT Supplemental material is available for this article. © RSNA, 2024.

Transpedicular injection of rhBMP-2 with β-tricalcium phosphate to reduce the proximal junctional kyphosis after adult spinal deformity correction: preliminary study

The aim of this preliminary study was to assess the impact of injecting recombinant human bone morphogenetic protein-2 (rhBMP-2) with β-tricalcium phosphate (β-TCP) carrier into the uppermost instrumented vertebra (UIV) during surgery to prevent the development of proximal junctional kyphosis (PJK) and proximal junctional failure (PJF). The 25 patients from study group had received 0.5 mg rhBMP-2 mixed with 1.5 g β-TCP paste injection into the UIV during surgery. The control group consisted of 75 patients who underwent surgery immediately before the start of the study. The incidences of PJK and PJF were analyzed as primary outcomes. Spinopelvic parameters and patient-reported outcomes were analyzed as secondary outcomes. Hounsfield unit (HU) measurements were performed to confirm the effect of rhBMP-2 with β-TCP on bone formation at preoperative and postoperative at computed tomography. PJK and PJF was more occurred in control group than study group (p = 0.02, 0.29, respectively). The HU of the UIV significantly increased 6 months after surgery. And the increment at the UIV was also significantly greater than that at the UIV-1 6 months after surgery. Injection of rhBMP-2 with β-TCP into the UIV reduced PJK and PJF rates 6 months after surgery with new bone formation.

Computed Tomography-Based Quantitative Texture Analysis and Gut Microbial Community Signatures Predict Survival in Non-Small Cell Lung Cancer

This study aims to combine computed tomography (CT)-based texture analysis (QTA) and a microbiome-based biomarker signature to predict the overall survival (OS) of immune checkpoint inhibitor (ICI)-treated non-small cell lung cancer (NSCLC) patients by analyzing their CT scans (n = 129) and fecal microbiome (n = 58). One hundred and five continuous CT parameters were obtained, where principal component analysis (PCA) identified seven major components that explained 80% of the data variation. Shotgun metagenomics (MG) and ITS analysis were performed to reveal the abundance of bacterial and fungal species. The relative abundance of Bacteroides dorei and Parabacteroides distasonis was associated with long OS (>6 mo), whereas the bacteria Clostridium perfringens and Enterococcus faecium and the fungal taxa Cortinarius davemallochii, Helotiales, Chaetosphaeriales, and Tremellomycetes were associated with short OS (≤6 mo). Hymenoscyphus immutabilis and Clavulinopsis fusiformis were more abundant in patients with high (≥50%) PD-L1-expressing tumors, whereas Thelephoraceae and Lachnospiraceae bacterium were enriched in patients with ICI-related toxicities. An artificial intelligence (AI) approach based on extreme gradient boosting evaluated the associations between the outcomes and various clinicopathological parameters. AI identified MG signatures for patients with a favorable ICI response and high PD-L1 expression, with 84% and 79% accuracy, respectively. The combination of QTA parameters and MG had a positive predictive value of 90% for both therapeutic response and OS. According to our hypothesis, the QTA parameters and gut microbiome signatures can predict OS, the response to therapy, the PD-L1 expression, and toxicity in NSCLC patients treated with ICI, and a machine learning approach can combine these variables to create a reliable predictive model, as we suggest in this research.

Lymph node metastasis in cancer progression: molecular mechanisms, clinical significance and therapeutic interventions

Lymph nodes (LNs) are important hubs for metastatic cell arrest and growth, immune modulation, and secondary dissemination to distant sites through a series of mechanisms, and it has been proved that lymph node metastasis (LNM) is an essential prognostic indicator in many different types of cancer. Therefore, it is important for oncologists to understand the mechanisms of tumor cells to metastasize to LNs, as well as how LNM affects the prognosis and therapy of patients with cancer in order to provide patients with accurate disease assessment and effective treatment strategies. In recent years, with the updates in both basic and clinical studies on LNM and the application of advanced medical technologies, much progress has been made in the understanding of the mechanisms of LNM and the strategies for diagnosis and treatment of LNM. In this review, current knowledge of the anatomical and physiological characteristics of LNs, as well as the molecular mechanisms of LNM, are described. The clinical significance of LNM in different anatomical sites is summarized, including the roles of LNM playing in staging, prognostic prediction, and treatment selection for patients with various types of cancers. And the novel exploration and academic disputes of strategies for recognition, diagnosis, and therapeutic interventions of metastatic LNs are also discussed.

Impact of Noise Level on the Accuracy of Automated Measurement of CT Number Linearity on ACR CT and Computational Phantoms

Background

Methods for segmentation, i.e., Full-segmentation (FS) and Segmentation-rotation (SR), are proposed for maintaining Computed Tomography (CT) number linearity. However, their effectiveness has not yet been tested against noise.

Objective

This study aimed to evaluate the influence of noise on the accuracy of CT number linearity of the FS and SR methods on American College of Radiology (ACR) CT and computational phantoms.

Material and Methods

This experimental study utilized two phantoms, ACR CT and computational phantoms. An ACR CT phantom was scanned by a 128-slice CT scanner with various tube currents from 80 to 200 mA to acquire various noises, with other constant parameters. The computational phantom was added by different Gaussian noises between 20 and 120 Hounsfield Units (HU). The CT number linearity was measured by the FS and SR methods, and the accuracy of CT number linearity was computed on two phantoms.

Results

The two methods successfully segmented both phantoms at low noise, i.e., less than 60 HU. However, segmentation and measurement of CT number linearity are not accurate on a computational phantom using the FS method for more than 60-HU noise. The SR method is still accurate up to 120 HU of noise.

Conclusion

The SR method outperformed the FS method to measure the CT number linearity due to its endurance in extreme noise.

CT texture analysis and node-RADS CT score of mediastinal lymph nodes - diagnostic performance in lung cancer patients

BACKGROUND

Texture analysis derived from computed tomography (CT) can provide clinically relevant imaging biomarkers. Node-RADS is a recently proposed classification to categorize lymph nodes in radiological images. The present study sought to investigate the diagnostic abilities of CT texture analysis and Node-RADS to discriminate benign from malignant mediastinal lymph nodes in patients with lung cancer.

METHODS

Ninety-one patients (n = 32 females, 35%) with a mean age of 64.8 ± 10.8 years were included in this retrospective study. Texture analysis was performed using the free available Mazda software. All lymph nodes were scored accordingly to the Node-RADS classification. All primary tumors and all investigated mediastinal lymph nodes were histopathologically confirmed during clinical workup.

RESULTS

In discrimination analysis, Node-RADS score showed statistically significant differences between N0 and N1-3 (p < 0.001). Multiple texture features were different between benign and malignant lymph nodes: S(1,0)AngScMom, S(1,0)SumEntrp, S(1,0)Entropy, S(0,1)SumAverg. Correlation analysis revealed positive associations between the texture features with Node-RADS score: S(4,0)Entropy (r = 0.72, p < 0.001), S(3,0) Entropy (r = 0.72, p < 0.001), S(2,2)Entropy (r = 0.72, p < 0.001).

CONCLUSIONS

Several texture features and Node-RADS derived from CT were associated with the malignancy of mediastinal lymph nodes and might therefore be helpful for discrimination purposes. Both of the two quantitative assessments could be translated and used in clinical routine.

A CT-Based Radiomics Nomogram in Predicting the Postoperative Prognosis of Colorectal Cancer: A Two-center Study

RATIONALE AND OBJECTIVES

This retrospective study aimed to develop a practical model to determine overall survival after surgery in patients with colorectal cancer according to radiomics signatures based on computed tomography (CT) images and clinical predictors.

MATERIALS AND METHODS

A total of 121 colorectal cancer (CRC) patients were selected to construct the model, and 51 patients and 114 patients were selected for internal validation and external testing. The radiomics features were extracted from each patient's CT images. Univariable Cox regression and least absolute shrinkage and selection operator regression were used to select radiomics features. The performance of the nomogram was evaluated by calibration curves and the c-index. Kaplan-Meier analysis was used to compare the overall survival between these subgroups.

RESULTS

The radiomics features of the CRC patients were significantly correlated with survival time. The c-indexes of the nomogram in the training cohort, internal validation cohort and external test cohort were 0.782, 0.721, and 0.677. Our nomogram integrated the optimal radiomics signature with clinical predictors showed a significant improvement in the prediction of CRC patients' overall survival. The calibration curves showed that the predicted survival time was close to the actual survival time. According to Kaplan-Meier analysis, the 1-, 2-, and 3-year survival rates of the low-risk group were higher than those of the high-risk group.

CONCLUSION

The nomogram combining the optimal radiomics signature and clinical predictors further improved the predicted accuracy of survival prognosis for CRC patients. These findings might affect treatment strategies and enable a step forward for precise medicine.

Analysis of the value of enhanced CT combined with texture analysis in the differential diagnosis of pulmonary sclerosing pneumocytoma and atypical peripheral lung cancer: a feasibility study

BACKGROUND

As a rare benign lung tumour, pulmonary sclerosing pneumocytoma (PSP) is often misdiagnosed as atypical peripheral lung cancer (APLC) on routine imaging examinations. This study explored the value of enhanced CT combined with texture analysis to differentiate between PSP and APLC.

METHODS

Forty-eight patients with PSP and fifty patients with APLC were retrospectively enrolled. The CT image features of the two groups of lesions were analysed, and MaZda software was used to evaluate the texture of CT venous phase thin-layer images. Independent sample t-test, Mann-Whitney U tests or χ² tests were used to compare between groups. The intra-class correlation coefficient (ICC) was used to analyse the consistency of the selected texture parameters. Spearman correlation analysis was used to evaluate the differences in texture parameters between the two groups. Based on the statistically significant CT image features and CT texture parameters, the independent influencing factors between PSP and APLC were analysed by multivariate logistic regression. Extremely randomized trees (ERT) was used as the classifier to build models, and the models were evaluated by the five-fold cross-validation method.

RESULTS

Logistic regression analysis based on CT image features showed that calcification and arterial phase CT values were independent factors for distinguishing PSP from APLC. The results of logistic regression analysis based on CT texture parameters showed that WavEnHL_s-1 and Perc.01% were independent influencing factors to distinguish the two. Compared with the single-factor model (models A and B), the classification accuracy of the model based on image features combined with texture parameters was 0.84 ± 0.04, the AUC was 0.84 ± 0.03, and the sensitivity and specificity were 0.82 ± 0.13 and 0.87 ± 0.12, respectively.

CONCLUSION

Enhanced CT combined with texture analysis showed good diagnostic value for distinguishing PSP and APLC, which may contribute to clinical decision-making and prognosis evaluation.

Texture analysis of dual-phase contrast-enhanced CT in the diagnosis of cervical lymph node metastasis in patients with papillary thyroid cancer

BACKGROUND

Computed tomography texture analysis (CTTA) provides objective and quantitative information regarding tumor heterogeneity beyond visual inspection. However, no study has yet used CTTA to differentiate metastatic from non-metastatic cervical lymph node in patients with papillary thyroid cancer (PTC).

PURPOSE

To evaluate the value of texture analysis of dual-phase contrast-enhanced CT images in diagnosing cervical lymph node metastasis in patients with PTC.

MATERIAL AND METHODS

Metastatic (n = 27) and non-metastatic (n = 32) cervical lymph nodes were analyzed retrospectively. Texture analyses were performed on both arterial (A) and venous (V) phase CT images. Texture parameters, including mean gray-level intensity, skewness, kurtosis, entropy, and uniformity, were obtained and compared between groups. Receiver operating characteristic (ROC) curves analyses and multivariate logistic regression analysis were used in our study.

RESULTS

Metastatic lymph nodes showed significantly higher A-mean gray-level intensity, A-entropy, and lower A-kurtosis and V-kurtosis (all P < 0.001) than non-metastatic mimics. The ROC curve analyses indicated that A-kurtosis demonstrated an optimal diagnostic area under the curve (AUC; 0.884) and specificity (92.59%), while the A-mean gray-level intensity showed optimal diagnostic sensitivity (90.62%). Multivariate logistic regression analysis showed that A-mean gray-level intensity (P = 0.006, odds ratio [OR] = 24.297) and V-kurtosis (P = 0.014, OR = 19.651) were the independent predictor for metastatic cervical lymph node.

CONCLUSION

Dual-phase contrast-enhanced CCTA-especially A-mean gray-level intensity and V-kurtosis-may have the potential to diagnose metastatic cervical lymph node in patients with PTC.

Value of Quantitative CTTA in Differentiating Malignant From Benign Bosniak III Renal Lesions on CT Images

OBJECTIVE

The aim of this study was to investigate whether computed tomography texture analysis can differentiate malignant from benign Bosniak III renal lesions on computed tomography (CT) images.

METHODS

This retrospective case-control study included 45 patients/lesions (22 benign and 23 malignant lesions) with Bosniak III renal lesions who underwent CT examination. Axial image slices in the unenhanced phase, corticomedullary phase, and nephrographic phase were selected and delineated manually. Computed tomography texture analysis was performed on each lesion during these 3 phases. Histogram-based, gray-level co-occurrence matrix, and gray-level run-length matrix features were extracted using open-source software and analyzed. In addition, receiver operating characteristic curve was constructed, and the area under the receiver operating characteristic curve (AUC) of each feature was constructed.

RESULTS

Of the 33 extracted features, 16 features showed significant differences (P < 0.05). Eight features were significantly different between the 2 groups after Holm-Bonferroni correction, including 3 histogram-based, 4 gray-level co-occurrence matrix, and 1 gray-level run-length matrix features (P < 0.01). The texture features resulted in the highest AUC of 0.769 ± 0.074. Renal cell carcinomas were labeled with a higher degree of lesion gray-level disorder and lower lesion homogeneity, and a model incorporating the 3 most discriminative features resulted in an AUC of 0.846 ± 0.058.

CONCLUSIONS

The results of this study showed that CT texture features were related to malignancy in Bosniak III renal lesions. Computed tomography texture analysis might help in differentiating malignant from benign Bosniak III renal lesions on CT images.

Improving accuracy of 18F-fluorodeoxyglucose PET computed tomography to diagnose nodal involvement in non-small cell lung cancer: utility of using various predictive models

PURPOSE

To determine predictive models (PM) that could improve the accuracy for identifying metastatic regional nodes in non-small cell lung cancer based on both PET and CT findings seen on 18F-FDG PET CT.

METHODS

Three hundred thirty-nine biopsy-proven NSCLC patients who underwent surgical resection and had a staging 18F-FDG PET CT were enrolled. PET parameters obtained were (1) presence of visual PET positive nodes, (2) SUVmax of nodes (NSUV), (3) ratio of node to aorta SUVmax (N/A ratio) and (4) ratio of node to primary tumour SUVmax (N/T ratio). CT parameters obtained were (1) short-axis diameter and (2) Hounsfield units (HU) of PET-positive nodes. PET and CT parameters were correlated with nodal histopathology to find out the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and overall accuracy. Different PM combining these parameters were devised and the incremental improvement in accuracy was determined.

RESULTS

Visual PET positivity showed sensitivity, specificity, PPV, NPV and accuracy of 72.4, 76.1, 30.1, 95.1 and 75.6, respectively. PM2 which combined visual PET positivity, NSUV and HU appears more clinically relevant and showed sensitivity, specificity, PPV, NPV and accuracy of 53.5, 96.5, 68.9, 93.6 and 91.2, respectively. PM6 which combined visual PET positivity, NSUV, N/A ratio and HU showed the maximum PPV (80.0%), specificity (98.3%) and accuracy of (91.9%).

CONCLUSION

PM combining parameters like nodal SUVmax, N/A ratio, N/T ratio and HU values have shown to improve the PPV, specificity and overall accuracy of 18FDG PET CT in the preoperative diagnosis of nodal metastases.

Preoperatively Estimating the Malignant Potential of Mediastinal Lymph Nodes: A Pilot Study Toward Establishing a Robust Radiomics Model Based on Contrast-Enhanced CT Imaging

PURPOSE

To establish and validate a radiomics model to estimate the malignancy of mediastinal lymph nodes (LNs) based on contrast-enhanced CT imaging.

METHOD

In total, 201 pathologically confirmed mediastinal LNs from 129 patients were enrolled and assigned to training and test sets. Radiomics features were extracted from the region of interest (ROI) delineated on venous-phase CT imaging of LN. Feature selection was performed with least absolute shrinkage and selection operator (LASSO) binary logistic regression. Multivariate logistic regression was performed with the backward stepwise elimination. A model was fitted to associate mediastinal LN malignancy with selected features. The performance of the model was assessed and compared to that of five other machine learning algorithms (support vector machine, naive Bayes, random forest, decision tree, K-nearest neighbor) using receiver operating characteristic (ROC) curves. Calibration curves and Hosmer-Lemeshow tests were used to assess the calibration degree. Decision curve analysis (DCA) was used to assess the clinical usefulness of the logistic regression model in both the training and test sets. Stratified analysis was performed for different scanners and slice thicknesses.

RESULT

Among the six machine learning methods, the logistic regression model with the eight strongest features showed a significant association with mediastinal LN status and the satisfactory diagnostic performance for distinguishing malignant LNs from benign LNs. The accuracy, sensitivity, specificity and area under the ROC curve (AUC) were 0.850/0.803, 0.821/0.806, 0.893/0.800, and 0.922/0.850 in the training/test sets, respectively. The Hosmer-Lemeshow test showed that the P value was > 0.05, indicating good calibration, and the calibration curves showed good agreement between the classifications and actual observations. DCA showed that the model would obtain more benefit when the threshold probability was between 30% and 90% in the test set. Stratified analysis showed that the performance was not affected by different scanners or slice thicknesses. There was no significant difference (DeLong test, P > 0.05) between any two subgroups, which showed the generalization of the radiomics score across different factors.

CONCLUSION

The model we built could help assist the preoperative estimation of mediastinal LN malignancy based on contrast-enhanced CT imaging, with stability for different scanners and slice thicknesses.

Radiomics Texture Features in Advanced Colorectal Cancer: Correlation with BRAF Mutation and 5-year Overall Survival

PURPOSE

To explore the potential of radiomics texture features as potential biomarkers to enable detection of the presence of BRAF mutation and prediction of 5-year overall survival (OS) in stage IV colorectal cancer (CRC).

MATERIALS AND METHODS

In this retrospective study, a total of 145 patients (mean age, 61 years ± 14 [standard deviation {SD}]; 68 female patients and 77 male patients) with stage IV CRC who underwent molecular profiling and pretreatment contrast material-enhanced CT scans between 2004 and 2018 were included. Tumor radiomics texture features, including the mean, the SD, the mean value of positive pixels (MPP), skewness, kurtosis, and entropy, were extracted from regions of interest on CT images after applying three Laplacian-of-Gaussian filters known as spatial scaling factors (SSFs) (SSF = 2, fine; SSF = 4, medium; SSF = 6, coarse) by using specialized software; values of these parameters were also obtained without filtration (SSF = 0). The Wilcoxon rank sum test was used to assess differences between mutated versus wild-type BRAF tumors. Associations between radiomics texture features and 5-year OS were determined by using Kaplan-Meier estimators using the log-rank test and multivariate Cox proportional-hazards regression analysis.

RESULTS

The SDs and MPPs of radiomic texture features were significantly lower in BRAF mutant tumors than in wild-type BRAF tumors at SSFs of 0, 4, and 6 (P = .006, P = .007, and P = .005, respectively). Patients with skewness less than or equal to -0.75 at an SSF of 0 and a mean of greater than or equal to 17.76 at an SSF of 2 showed better 5-year OS (hazard ratio [HR], 0.53 [95% confidence interval {CI}: 0.29, 0.94]; HR, 0.40 [95% CI: 0.22, 0.71]; log-rank P = .025 and P = .002, respectively). Tumor location (right colon vs left colon vs rectum) had no significant impact on the clinical outcome (log-rank P = .53).

CONCLUSION

Radiomics texture features can serve as potential biomarkers for determining BRAF mutation status and as predictors of 5-year OS in patients with advanced-stage CRC.Keywords: Abdomen/GI, CT, Comparative Studies, Large BowelSupplemental material is available for this article.© RSNA, 2020.

2-[18F]FDG PET/CT radiomics in lung cancer: An overview of the technical aspect and its emerging role in management of the disease

Lung cancer is the most common cancer, worldwide, and a major health issue with a remarkable mortality rate. 2-[¹⁸F]fluoro-2-deoxy-D-glucose positron emission tomography/computed tomography (2-[¹⁸F]FDG PET/CT) plays an indispensable role in the management of lung cancer patients. Long-established quantitative parameters such as size, density, and metabolic activity have been and are being employed in the current practice to enhance interpretation and improve diagnostic and prognostic value. The introduction of radiomics analysis revolutionized the quantitative evaluation of medical imaging, revealing data within images beyond visual interpretation. The "big data" are extracted from high-quality images and are converted into information that correlates to relevant genetic, pathologic, clinical, or prognostic features. Technically advanced, diverse methods have been implemented in different studies. The standardization of image acquisition, segmentation and features analysis is still a debated issue. Importantly, a body of features has been extracted and employed for diagnosis, staging, risk stratification, prognostication, and therapeutic response. 2-[¹⁸F]FDG PET/CT-derived features show promising value in non-invasively diagnosing the malignant nature of pulmonary nodules, differentiating lung cancer subtypes, and predicting response to different therapies as well as survival. In this review article, we aimed to provide an overview of the technical aspects used in radiomics analysis in non-small cell lung cancer (NSCLC) and elucidate the role of 2-[¹⁸F]FDG PET/CT-derived radiomics in the diagnosis, prognostication, and therapeutic response.