Metabolic radiogenomics in lung cancer: associations between FDG PET image features and oncogenic signaling pathway alterations

Prognostic value of combining clinical factors, 18F-FDG PET-based intensity, volumetric features, and deep learning predictor in patients with EGFR-mutated lung adenocarcinoma undergoing targeted therapies: a cross-scanner and temporal validation study

OBJECTIVE

To investigate the prognostic value of 18F-FDG PET-based intensity, volumetric features, and deep learning (DL) across different generations of PET scanners in patients with epidermal growth factor receptor (EGFR)-mutated lung adenocarcinoma receiving tyrosine kinase inhibitor (TKI) treatment.

METHODS

We retrospectively analyzed the pre-treatment 18F-FDG PET of 217 patients with advanced-stage lung adenocarcinoma and actionable EGFR mutations who received TKI as first-line treatment. Patients were separated into analog (n = 166) and digital (n = 51) PET cohorts. 18F-FDG PET-derived intensity, volumetric features, ResNet-50 DL of the primary tumor, and clinical variables were used to predict progression-free survival (PFS). Independent prognosticators were used to develop prediction model. Model was developed and validated in the analog and digital PET cohorts, respectively.

RESULTS

In the analog PET cohort, female sex, stage IVB status, exon 19 deletion, SUVmax, metabolic tumor volume, and positive DL prediction independently predicted PFS. The model devised from these six prognosticators significantly predicted PFS in the analog (HR = 1.319, p < 0.001) and digital PET cohorts (HR = 1.284, p = 0.001). Our model provided incremental prognostic value to staging status (c-indices = 0.738 vs. 0.558 and 0.662 vs. 0.598 in the analog and digital PET cohorts, respectively). Our model also demonstrated a significant prognostic value for overall survival (HR = 1.198, p < 0.001, c-index = 0.708 and HR = 1.256, p = 0.021, c-index = 0.664 in the analog and digital PET cohorts, respectively).

CONCLUSIONS

Combining 18F-FDG PET-based intensity, volumetric features, and DL with clinical variables may improve the survival stratification in patients with advanced EGFR-mutated lung adenocarcinoma receiving TKI treatment. Implementing the prediction model across different generations of PET scanners may be feasible and facilitate tailored therapeutic strategies for these patients.

Comparative analysis of batch correction methods for FDG PET/CT using metabolic radiogenomic data of lung cancer patients

In radiomics research, the issue of different instruments being used is significant. In this study, we compared three correction methods to reduce the batch effects in radiogenomic data from fluorodeoxyglucose (FDG) PET/CT images of lung cancer patients. Texture features of the FDG PET/CT images and genomic data were retrospectively obtained. The features were corrected with different methods: phantom correction, ComBat method, and Limma method. Batch effects were estimated using three analytic tools: principal component analysis (PCA), the k-nearest neighbor batch effect test (kBET), and the silhouette score. Finally, the associations of features and gene mutations were compared between each correction method. Although the kBET rejection rate and silhouette score were lower in the phantom-corrected data than in the uncorrected data, a PCA plot showed a similar variance. ComBat and Limma methods provided correction with low batch effects, and there was no significant difference in the results of the two methods. In ComBat- and Limma-corrected data, more texture features exhibited a significant association with the TP53 mutation than in those in the phantom-corrected data. This study suggests that correction with ComBat or Limma methods can be more effective or equally as effective as the phantom method in reducing batch effects.

Prediction of EGFR mutation status in lung adenocarcinoma based on 18F-FDG PET/CT radiomic features

The earlier identification of EGFR mutation status in lung adenocarcinoma patients is crucial for treatment decision-making. Radiomics, which involves high-throughput extraction of imaging features from medical images for quantitative analysis, can quantify tumor heterogeneity and assess tumor biology non-invasively. This field has gained attention from researchers in recent years. The aim of this study is to establish a model based on 18F-FDG PET/CT radiomic features to predict the epidermal growth factor receptor (EGFR) mutation status of lung adenocarcinoma and evaluate its performance. 155 patients with lung adenocarcinoma who underwent 18F-FDG PET/CT scans and EGFR gene detection before treatment were retrospectively analyzed. The LIFEx packages was used to perform 3D volume of interest (VOI) segmentation manually on DICOM images and extract 128 radiomic features. The Wilcoxon rank sum test and least absolute shrinkage and selection operator (LASSO) regression algorithm were applied to filter the radiomic features and establish models. The performance of the models was evaluated by the receiver operating characteristic (ROC) curve and the area under the curve (AUC). Among the models we have built, the radiomic model based on 18F-FDG PET/CT has the best prediction performance for EGFR gene mutation status, with an AUC of 0.90 (95% CI 0.84~0.96) in the training set and 0.79 (95% CI 0.64~0.94) in the test set. In conclusion, we have established a radiomics model based on 18F-FDG PET/CT, which has good predictive performance in identifying EGFR gene mutation status in lung adenocarcinoma patients.

Genomic and Glycolytic Entropy Are Reliable Radiogenomic Heterogeneity Biomarkers for Non-Small Cell Lung Cancer

Radiogenomic heterogeneity features in ¹⁸F-fluorodeoxyglucose positron emission tomography (¹⁸F-FDG PET) have become popular in non-small cell lung cancer (NSCLC) research. However, the reliabilities of genomic heterogeneity features and of PET-based glycolytic features in different image matrix sizes have yet to be thoroughly tested. We conducted a prospective study with 46 NSCLC patients to assess the intra-class correlation coefficient (ICC) of different genomic heterogeneity features. We also tested the ICC of PET-based heterogeneity features from different image matrix sizes. The association of radiogenomic features with clinical data was also examined. The entropy-based genomic heterogeneity feature (ICC = 0.736) is more reliable than the median-based feature (ICC = -0.416). The PET-based glycolytic entropy was insensitive to image matrix size change (ICC = 0.958) and remained reliable in tumors with a metabolic volume of <10 mL (ICC = 0.894). The glycolytic entropy is also significantly associated with advanced cancer stages (p = 0.011). We conclude that the entropy-based radiogenomic features are reliable and may serve as ideal biomarkers for research and further clinical use for NSCLC.

Synergies of Radiomics and Transcriptomics in Lung Cancer Diagnosis: A Pilot Study

Radiotranscriptomics is an emerging field that aims to investigate the relationships between the radiomic features extracted from medical images and gene expression profiles that contribute in the diagnosis, treatment planning, and prognosis of cancer. This study proposes a methodological framework for the investigation of these associations with application on non-small-cell lung cancer (NSCLC). Six publicly available NSCLC datasets with transcriptomics data were used to derive and validate a transcriptomic signature for its ability to differentiate between cancer and non-malignant lung tissue. A publicly available dataset of 24 NSCLC-diagnosed patients, with both transcriptomic and imaging data, was used for the joint radiotranscriptomic analysis. For each patient, 749 Computed Tomography (CT) radiomic features were extracted and the corresponding transcriptomics data were provided through DNA microarrays. The radiomic features were clustered using the iterative K-means algorithm resulting in 77 homogeneous clusters, represented by meta-radiomic features. The most significant differentially expressed genes (DEGs) were selected by performing Significance Analysis of Microarrays (SAM) and 2-fold change. The interactions among the CT imaging features and the selected DEGs were investigated using SAM and a Spearman rank correlation test with a False Discovery Rate (FDR) of 5%, leading to the extraction of 73 DEGs significantly correlated with radiomic features. These genes were used to produce predictive models of the meta-radiomics features, defined as p-metaomics features, by performing Lasso regression. Of the 77 meta-radiomic features, 51 can be modeled in terms of the transcriptomic signature. These significant radiotranscriptomics relationships form a reliable basis to biologically justify the radiomics features extracted from anatomic imaging modalities. Thus, the biological value of these radiomic features was justified via enrichment analysis on their transcriptomics-based regression models, revealing closely associated biological processes and pathways. Overall, the proposed methodological framework provides joint radiotranscriptomics markers and models to support the connection and complementarities between the transcriptome and the phenotype in cancer, as demonstrated in the case of NSCLC.

Glucose metabolic heterogeneity correlates with pathological features and improves survival stratification of resectable lung adenocarcinoma

OBJECTIVE

We investigated whether glycolytic heterogeneity correlated with histopathology, and further stratified the survival outcomes pertaining to resectable lung adenocarcinoma.

METHODS

We retrospectively analyzed the ¹⁸F-fluorodeoxyglucose positron emission tomography-derived entropy and histopathology from 128 patients who had undergone curative surgery for lung adenocarcinoma. Disease-free survival (DFS) and overall survival (OS) were analyzed using univariate and multivariate Cox regression models. Independent predictors were used to construct survival prediction models.

RESULTS

Entropy significantly correlated with histopathology, including tumor grades, lympho-vascular invasion, and visceral pleural invasion. Furthermore, entropy was an independent predictor of unfavorable DFS (p = 0.031) and OS (p = 0.004), while pathological nodal metastasis independently predicted DFS (p = 0.009). Our entropy-based models outperformed the traditional staging system (c-index = 0.694 versus 0.636, p = 0.010 for DFS; c-index = 0.704 versus 0.630, p = 0.233 for OS). The models provided further survival stratification in subgroups comprising different tumor grades (DFS: HR = 2.065, 1.315, and 1.408 for grade 1-3, p = 0.004, 0.001, and 0.039, respectively; OS: HR = 25.557, 6.484, and 2.570, for grade 1-3, p = 0.006, < 0.001, and = 0.224, respectively).

CONCLUSION

The glycolytic heterogeneity portrayed by entropy is associated with aggressive histopathological characteristics. The proposed entropy-based models may provide more sophisticated survival stratification in addition to histopathology and may enable personalized treatment strategies for resectable lung cancer.

A review of radiomics and genomics applications in cancers: the way towards precision medicine

The application of radiogenomics in oncology has great prospects in precision medicine. Radiogenomics combines large volumes of radiomic features from medical digital images, genetic data from high-throughput sequencing, and clinical-epidemiological data into mathematical modelling. The amalgamation of radiomics and genomics provides an approach to better study the molecular mechanism of tumour pathogenesis, as well as new evidence-supporting strategies to identify the characteristics of cancer patients, make clinical decisions by predicting prognosis, and improve the development of individualized treatment guidance. In this review, we summarized recent research on radiogenomics applications in solid cancers and presented the challenges impeding the adoption of radiomics in clinical practice. More standard guidelines are required to normalize radiomics into reproducible and convincible analyses and develop it as a mature field.

Radiomics-guided radiation therapy: opportunities and challenges

Radiomics is an advanced image-processing framework, which extracts image features and considers them as biomarkers towards personalized medicine. Applications include disease detection, diagnosis, prognosis, and therapy response assessment/prediction. As radiation therapy aims for further individualized treatments, radiomics could play a critical role in various steps before, during and after treatment. Elucidation of the concept of radiomics-guided radiation therapy (RGRT) is the aim of this review, attempting to highlight opportunities and challenges underlying the use of radiomics to guide clinicians and physicists towards more effective radiation treatments. This work identifies the value of RGRT in various steps of radiotherapy from patient selection to follow-up, and subsequently provides recommendations to improve future radiotherapy using quantitative imaging features.

[18F]FDG-PET/CT radiomics and artificial intelligence in lung cancer: Technical aspects and potential clinical applications

Lung cancer is the second most common cancer and the leading cause of cancer-related death worldwide. Molecular imaging using [¹⁸F]fluorodeoxyglucose Positron Emission Tomography and/or Computed Tomography ([¹⁸F]FDG-PET/CT) plays an essential role in the diagnosis, evaluation of response to treatment, and prediction of outcomes. The images are evaluated using qualitative and conventional quantitative indices. However, there is far more information embedded in the images, which can be extracted by sophisticated algorithms. Recently, the concept of uncovering and analyzing the invisible data extracted from medical images, called radiomics, is gaining more attention. Currently, [¹⁸F]FDG-PET/CT radiomics is growingly evaluated in lung cancer to discover if it enhances the diagnostic performance or implication of [¹⁸F]FDG-PET/CT in the management of lung cancer. In this review, we provide a short overview of the technical aspects, as they are discussed in different articles of this special issue. We mainly focus on the diagnostic performance of the [¹⁸F]FDG-PET/CT-based radiomics and the role of artificial intelligence in non-small cell lung cancer, impacting the early detection, staging, prediction of tumor subtypes, biomarkers, and patient's outcomes.

Tumor glycolytic heterogeneity improves detection of regional nodal metastasis in patients with lung adenocarcinoma

OBJECTIVE

The diagnostic performance of ¹⁸F-FDG PET for detecting regional lymph node metastasis in resectable lung cancer is variable, and its sensitivity for adenocarcinoma is even lower. We aimed to evaluate the value of ¹⁸F-FDG PET-derived features in predicting pathological lymph node metastasis in patients with lung adenocarcinoma.

METHODS

We retrospectively analyzed pretreatment ¹⁸F-FDG PET-derived features of 126 lung adenocarcinoma patients who underwent curative surgery. A logistic regression model was used to analyze the association between study variables and pathological regional lymph node status obtained from the curative surgery. Furthermore, Cox regression analysis was used to test the effect of the study variables on survival outcomes, including disease-free survival (DFS) and overall survival (OS).

RESULTS

The primary tumor entropy (OR = 1.7, p = 0.014) and visual interpretation of regional nodes via ¹⁸F-FDG PET (OR = 2.5, p = 0.026) independently predicted pathological regional lymph node metastasis. The areas under the receiver-operating-characteristic curves were 0.631, 0.671, and 0.711 for visual interpretation, primary tumor entropy, and their combination, respectively. Based on visual interpretation, a primary tumor entropy ≥ 3.0 improved the positive predictive value of positive visual interpretation from 51.2% to 63.0%, whereas an entropy < 3.0 improved the negative predictive value of negative visual interpretation from 75.3% to 82.6%. In cases with positive visual interpretation and low entropy, or negative visual interpretation and high entropy, the nodal metastasis rates were approximately 30%. In the survival analyses, the primary tumor entropy was also independently associated with DFS (HR = 2.7, p = 0.001) and OS (HR = 4.8, p = 0.001).

CONCLUSIONS

Our preliminary results show that the primary tumor entropy may improve ¹⁸F-FDG PET visual interpretation in predicting pathological nodal metastasis in lung adenocarcinoma, and may also show a survival prognostic value. This versatile biomarker may facilitate tailored therapeutic strategies for patients with resectable lung adenocarcinoma.