Radiomics signature: A potential and incremental predictor for EGFR mutation status in NSCLC patients, comparison with CT morphology

External Validation of a CT-Based Radiogenomics Model for the Detection of EGFR Mutation in NSCLC and the Impact of Prevalence in Model Building by Using Synthetic Minority Over Sampling (SMOTE): Lessons Learned

RATIONALE AND OBJECTIVES

Radiogenomics holds promise in identifying molecular alterations in nonsmall cell lung cancer (NSCLC) using imaging features. Previously, we developed a radiogenomics model to predict epidermal growth factor receptor (EGFR) mutations based on contrast-enhanced computed tomography (CECT) in NSCLC patients. The current study aimed to externally validate this model using a publicly available National Institutes of Health (NIH)-based NSCLC dataset and assess the effect of EGFR mutation prevalence on model performance through synthetic minority oversampling technique (SMOTE).

MATERIALS AND METHODS

The original radiogenomics model was validated on an independent NIH cohort (n=140). For assessing the influence of disease prevalence, six SMOTE-augmented datasets were created, simulating EGFR mutation prevalence from 25% to 50%. Seven models were developed (one from original data, six SMOTE-augmented), each undergoing rigorous cross-validation, feature selection, and logistic regression modeling. Models were tested against the NIH cohort. Performance was compared using area under the receiver operating characteristic curve (Area Under the Curve [AUC]), and differences between radiomic-only, clinical-only, and combined models were statistically assessed.

RESULTS

External validation revealed poor diagnostic performance for both our model and a previously published EGFR radiomics model (AUC ∼0.5). The clinical model alone achieved higher diagnostic accuracy (AUC 0.74). SMOTE-augmented models showed increased sensitivity but did not improve overall AUC compared to the clinical-only model. Changing EGFR mutation prevalence had minimal impact on AUC, challenging previous assumptions about the influence of sample imbalance on model performance.

CONCLUSION

External validation failed to reproduce prior radiogenomics model performance, while clinical variables alone retained strong predictive value. SMOTE-based oversampling did not improve diagnostic accuracy, suggesting that, in EGFR prediction, radiomics may offer limited value beyond clinical data. Emphasis on robust external validation and data-sharing is essential for future clinical implementation of radiogenomic models.

CT-based radiomics predictive model for spread through air space of IA stage lung adenocarcinoma

BackgroundSpread through air spaces (STAS) in lung adenocarcinoma means different treatment and worse prognosis.PurposeTo construct a radiomics model based on CT scans to predict the presence of STAS in stage IA lung adenocarcinoma, compared with the traditional clinical model.Material and MethodsThe study included 317 patients (median age = 57.21 years; age range = 45.84-68.61 years) with pathologically confirmed stage IA lung adenocarcinoma. In total, 122 (38.5%) patients were diagnosed with STAS by pathology after the operation. Two experienced radiologists independently segmented the lesions using MITK software and extracted 1791 radiomics features using Python. Single-factor t-test or Mann-Whitney U-test and LASSO were used to screen for radiomics signatures related to STAS. This study constructed a radiomics model, a clinical model, and a combined model, combining radiomics and clinical features. Model performance was evaluated using the area under the curve (AUC).ResultsBy single-factor analysis, four clinical features and 13 radiomics features were significantly associated with STAS. The three models (the clinical, radiomics, and combine models) achieved predictive efficacy, with an AUC of 0.849, 0.867, and 0.939, respectively, in the training set and 0.808, 0.848, and 0.876, respectively, in the testing set.ConclusionThe combined model based on the radiomics and clinical features of preoperative chest CT could be used to preoperatively diagnose the presence of STAS in stage IA lung adenocarcinoma and has an excellent diagnostic performance.

Interpretable CT Radiomics-based Machine Learning Model for Preoperative Prediction of Ki-67 Expression in Clear Cell Renal Cell Carcinoma

RATIONALE AND OBJECTIVES

To develop and externally validate interpretable CT radiomics-based machine learning (ML) models for preoperative Ki-67 expression prediction in clear cell renal cell carcinoma (ccRCC).

METHODS

506 patients were retrospectively enrolled from three independent institutes and divided into the training (n=357) and external test (n=149) sets. Ki67 expression was determined by immunohistochemistry (IHC) and categorized into low (<15%) and high (≥15%) expression groups. Radiomics features were extracted from segmented tumor regions in the corticomedullary phase (CMP) CT images using the "PyRadiomics" package. The least absolute shrinkage and selection operator (LASSO) regression was applied to select the most relevant radiomics features for Ki-67 expression, which were then used to train five ML models. Models' performances were evaluated via the receiving operator curve analysis and compared using Delong test. Calibration and decision curve analyses assessed the models' clinical utility. Kaplan-Meier analysis and Log-rank tests were conducted to determine the prognostic value of radiomics-predicted Ki-67 expression status. The optimal model was interpreted using SHapley Additive exPlanations (SHAP).

RESULTS

Eight radiomics feature were selected to build models using Random forest (RF), eXtreme Gradient Boosting (XGBoost), Logistic regression (LR), Support vector machine (SVM), and K-nearest neighbor (KNN). The RF model exhibited the best performance, achieving the highest area under the curve (AUC) in both the training (0.910, 95% confidence interval [CI]: 0.881-0.936) and external test (0.885, 95% CI: 0.826-0.934) sets, as confirmed by Delong test (all P values＜0.05). Calibration and decision curves further demonstrated the superior clinical utility of the RF model. Both IHC-based and RF-predicted high Ki-67 expression groups were significantly associated with a higher risk of tumor recurrence in the training and external test sets (all P values＜0.05). The prediction process of the RF model was uncovered in the globe and individualized terms using the SHAP.

CONCLUSION

The interpretable CT radiomics-based RF classifier exhibited robust predictive performance in assessing Ki-67 expression levels preoperatively, offering valuable prognostic insights and aiding clinical decision-making in ccRCC patients.

Radiomics based on dual-layer spectral detector CT for predicting EGFR mutation status in non-small cell lung cancer

OBJECTIVE

To explore the value of dual-layer spectral computed tomography (DLCT)-based radiomics for predicting epidermal growth factor receptor (EGFR) mutation status in patients with non-small cell lung cancer (NSCLC).

METHODS

DLCT images and clinical information from 115 patients with NSCLC were collected retrospectively and randomly assigned to a training group (n = 81) and a validation group (n = 34). A radiomics model was constructed based on the DLCT radiomic features by least absolute shrinkage and selection operator (LASSO) dimensionality reduction. A clinical model based on clinical and CT features was established. A nomogram was built combining the radiomic scores (Radscores) and clinical factors. Receiver operating characteristic (ROC) analysis and decision curve analysis (DCA) were used for the efficacy and clinical value of the models assessment.

RESULTS

A total of six radiomic features and two clinical features were screened for modeling. The AUCs of the radiomic model, clinical model, and nomogram were 0.909, 0.797, and 0.922, respectively, in the training group and 0.874, 0.691, and 0.881, respectively, in the validation group. The AUCs of the nomogram and the radiomics model were significantly higher than that of the clinical model, but no significant difference was found between them. DCA revealed that nomogram had the greatest clinical benefit at most threshold intervals.

CONCLUSION

Nomogram integrating clinical factors and pretreatment DLCT radiomic features can help evaluate the EGFR mutation status of patients with NSCLC in a noninvasive way.

Comprehensive Potential of Artificial Intelligence for Predicting PD-L1 Expression and EGFR Mutations in Lung Cancer: A Systematic Review and Meta-Analysis

OBJECTIVE

To evaluate the methodological quality and the predictive performance of artificial intelligence (AI) for predicting programmed death ligand 1 (PD-L1) expression and epidermal growth factor receptors (EGFR) mutations in lung cancer (LC) based on systematic review and meta-analysis.

METHODS

AI studies based on PET/CT, CT, PET, and immunohistochemistry (IHC)-whole-slide image (WSI) were included to predict PD-L1 expression or EGFR mutations in LC. The modified Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool was used to evaluate the methodological quality. A comprehensive meta-analysis was conducted to analyze the overall area under the curve (AUC). The Cochrane diagnostic test and I2 statistics were used to assess the heterogeneity of the meta-analysis.

RESULTS

A total of 45 AI studies were included, of which 10 were used to predict PD-L1 expression and 35 were used to predict EGFR mutations. Based on the analysis using the QUADAS-2 tool, 37 studies achieved a high-quality score of 7. In the meta-analysis of PD-L1 expression levels, the overall AUCs for PET/CT, CT, and IHC-WSI were 0.80 (95% confidence interval [CI], 0.77-0.84), 0.74 (95% CI, 0.69-0.77), and 0.95 (95% CI, 0.93-0.97), respectively. For EGFR mutation status, the overall AUCs for PET/CT, CT, and PET were 0.85 (95% CI, 0.81-0.88), 0.83 (95% CI, 0.80-0.86), and 0.75 (95% CI, 0.71-0.79), respectively. The Cochrane Diagnostic Test revealed an I2 value exceeding 50%, indicating substantial heterogeneity in the PD-L1 and EGFR meta-analyses. When AI was combined with clinicopathological features, the enhancement in predicting PD-L1 expression was not substantial, whereas the prediction of EGFR mutations showed improvement compared to the CT and PET models, albeit not significantly so compared to the PET/CT models.

CONCLUSIONS

The overall performance of AI in predicting PD-L1 expression and EGFR mutations in LC has promising clinical implications.

From Images to Genes: Radiogenomics Based on Artificial Intelligence to Achieve Non-Invasive Precision Medicine in Cancer Patients

With the increasing demand for precision medicine in cancer patients, radiogenomics emerges as a promising frontier. Radiogenomics is originally defined as a methodology for associating gene expression information from high-throughput technologies with imaging phenotypes. However, with advancements in medical imaging, high-throughput omics technologies, and artificial intelligence, both the concept and application of radiogenomics have significantly broadened. In this review, the history of radiogenomics is enumerated, related omics technologies, the five basic workflows and their applications across tumors, the role of AI in radiogenomics, the opportunities and challenges from tumor heterogeneity, and the applications of radiogenomics in tumor immune microenvironment. The application of radiogenomics in positron emission tomography and the role of radiogenomics in multi-omics studies is also discussed. Finally, the challenges faced by clinical transformation, along with future trends in this field is discussed.

Non-invasive, fast, and high-performance EGFR gene mutation prediction method based on deep transfer learning and model stacking for patients with Non-Small Cell Lung Cancer

Purpose

To propose an intelligent, non-invasive, highly precise, and rapid method to predict the mutation status of the Epidermal Growth Factor Receptor (EGFR) to accelerate treatment with Tyrosine Kinase Inhibitor (TKI) for patients with untreated adenocarcinoma Non-Small Cell Lung Cancer.

Materials and methods

Real-world data from 521 patients with adenocarcinoma NSCLC who performed a CT scan and underwent surgery or pathological biopsy to determine EGFR gene mutation between January 2021 and July 2022, is collected. Solutions to the problems that prevent the model from achieving very high precision, namely: human errors made during the annotation of the database and the low precision of the output decision of the model, are proposed. Thus, among the 521 analyzed cases, only 40 were selected as patients with EGFR gene mutation and 98 cases with wild-type EGFR.

Results

The proposed model is trained, validated, and tested on 12,040 2D images extracted from the 138 CT scans images where patients were randomly partitioned into training (80 %) and test (20 %) sets. The performance obtained for EGFR gene mutation prediction was 95.22 % for accuracy, 960.2 for F1_score, 95.89 % for precision, 96.92 % for sensitivity, 94.01 % for Cohen kappa, and 98 % for AUC.

Conclusion

An EGFR gene mutation status prediction method, with high-performance thanks to an intelligent prediction model entrained by highly accurate annotated data is proposed. The outcome of this project will facilitate rapid decision-making when applying a TKI as an initial treatment.

Analysis of postoperative recurrence-free survival in non-small cell lung cancer patients based on consensus clustering

AIMS

This study aims to assess whether consensus clustering, based on computed tomography (CT) radiomics from both intratumoral and peritumoral regions, can effectively stratify the risk of non-small cell lung cancer (NSCLC) patients and predict their postoperative recurrence-free survival (RFS).

MATERIALS AND METHODS

A retrospective analysis was conducted on the data of surgical patients diagnosed with NSCLC between December 2014 and April 2020. After preprocessing CT images, radiomic features were extracted from a 9-mm region encompassing both the tumor and its peritumoral area. Consensus clustering was utilized to analyze the radiomics features and categorize patients into distinct clusters. A comparison of the differences in clinical pathological characteristics was conducted among the clusters. Kaplan-Meier survival analysis was employed to investigate differences in survival among the clusters.

RESULTS

A total of 266 patients were included in this study, and consensus clustering identified three clusters (Cluster 1: n=111, Cluster 2: n=61, Cluster 3: n=94). Multiple clinical risk factors, including pathological TNM staging, programmed cell death ligand 1 (PD-L1), and epidermal growth factor receptor (EGFR) expression status exhibit significant differences among the three clusters. Kaplan-Meier survival analysis demonstrated significant variations in RFS across the clusters (P<0.001). The 3-year cumulative recurrence-free survival rates were 76.5% (95% CI: 68.6-84.4) for Cluster 1, 45.9% (95% CI: 33.4-58.4) for Cluster 2, and 41.5% (95% CI: 31.6-51.5) for Cluster 3.

CONCLUSIONS

Consensus clustering of CT radiomics based on intratumoral and peritumoral regions can stratify the risk of postoperative recurrence in patients with NSCLC.

CT-based whole lung radiomics nomogram for identification of PRISm from non-COPD subjects

BACKGROUND

Preserved Ratio Impaired Spirometry (PRISm) is considered to be a precursor of chronic obstructive pulmonary disease. Radiomics nomogram can effectively identify the PRISm subjects from non-COPD subjects, especially when during large-scale CT lung cancer screening.

METHODS

Totally 1481 participants (864, 370 and 247 in training, internal validation, and external validation cohorts, respectively) were included. Whole lung on thin-section computed tomography (CT) was segmented with a fully automated segmentation algorithm. PyRadiomics was adopted for extracting radiomics features. Clinical features were also obtained. Moreover, Spearman correlation analysis, minimum redundancy maximum relevance (mRMR) feature ranking and least absolute shrinkage and selection operator (LASSO) classifier were adopted to analyze whether radiomics features could be used to build radiomics signatures. A nomogram that incorporated clinical features and radiomics signature was constructed through multivariable logistic regression. Last, calibration, discrimination and clinical usefulness were analyzed using validation cohorts.

RESULTS

The radiomics signature, which included 14 stable features, was related to PRISm of training and validation cohorts (p < 0.001). The radiomics nomogram incorporating independent predicting factors (radiomics signature, age, BMI, and gender) well discriminated PRISm from non-COPD subjects compared with clinical model or radiomics signature alone for training cohort (AUC 0.787 vs. 0.675 vs. 0.778), internal (AUC 0.773 vs. 0.682 vs. 0.767) and external validation cohorts (AUC 0.702 vs. 0.610 vs. 0.699). Decision curve analysis suggested that our constructed radiomics nomogram outperformed clinical model.

CONCLUSIONS

The CT-based whole lung radiomics nomogram could identify PRISm to help decision-making in clinic.

Multiple primary lung cancer: Updates and perspectives

Management of multiple primary lung cancer (MPLC) remains challenging, partly due to its increasing incidence, especially with the significant rise in cases of multiple lung nodules caused by low-dose computed tomography screening. Moreover, the indefinite pathogenesis, diagnostic criteria, and treatment selection add to the complexity. In recent years, there have been continuous efforts to dissect the molecular characteristics of MPLC and explore new diagnostic approaches as well as treatment modalities, which will be reviewed here, with a focus on newly emerging evidence and future perspectives, hope to provide new insights into the management of MPLC and serve as inspiration for future research related to MPLC.

Improved Prediction of Epidermal Growth Factor Receptor Status by Combined Radiomics of Primary Nonsmall-Cell Lung Cancer and Distant Metastasis

OBJECTIVES

This study aimed to investigate radiomics based on primary nonsmall-cell lung cancer (NSCLC) and distant metastases to predict epidermal growth factor receptor (EGFR) mutation status.

METHODS

A total of 290 patients (mean age, 58.21 ± 9.28) diagnosed with brain (BM, n = 150) or spinal bone metastasis (SM, n = 140) from primary NSCLC were enrolled as a primary cohort. An external validation cohort, consisting of 69 patients (mean age, 59.87 ± 7.23; BM, n = 36; SM, n = 33), was enrolled from another center. Thoracic computed tomography-based features were extracted from the primary tumor and peritumoral area and selected using the least absolute shrinkage and selection operator regression to build a radiomic signature (RS-primary). Contrast-enhanced magnetic resonance imaging-based features were calculated and selected from the BM and SM to build RS-BM and RS-SM, respectively. The RS-BM-Com and RS-SM-Com were developed by integrating the most important features from the primary tumor, BM, and SM.

RESULTS

Six computed tomography-based features showed high association with EGFR mutation status: 3 from intratumoral and 3 from peritumoral areas. By combination of features from primary tumor and metastases, the developed RS-BM-Com and RS-SM-Com performed well with areas under curve in the training (RS-BM-Com vs RS-BM, 0.936 vs 0.885, P = 0.177; RS-SM-Com vs RS-SM, 0.929 vs 0.843, P = 0.003), internal validation (RS-BM-Com vs RS-BM, 0.920 vs 0.858, P = 0.492; RS-SM-Com vs RS-SM, 0.896 vs 0.859, P = 0.379), and external validation (RS-BM-Com vs RS-BM, 0.882 vs 0.805, P = 0.263; RS-SM-Com vs RS-SM, 0.865 vs 0.816, P = 0.312) cohorts.

CONCLUSIONS

This study indicates that the accuracy of detecting EGFR mutations significantly enhanced in the presence of metastases in primary NSCLC. The established radiomic signatures from this approach may be useful as new predictors for patients with distant metastases.

Habitat-Based Radiomics for Predicting EGFR Mutations in Exon 19 and 21 From Brain Metastasis

RATIONALE AND OBJECTIVES

To explore and externally validate habitat-based radiomics for preoperative prediction of epidermal growth factor receptor (EGFR) mutations in exon 19 and 21 from MRI imaging of non-small cell lung cancer (NSCLC)-originated brain metastasis (BM).

METHODS

A total of 170, 62 and 61 patients from center 1, center 2 and center 3, respectively were included. All patients underwent contrast-enhanced T1-weighted (T1CE) and T2-weighted (T2W) MRI scans. Radiomics features were extracted from the tumor active (TA) and peritumoral edema (PE) regions in each MRI slice. The most important features were selected by the least absolute shrinkage and selection operator regression to develop radiomics signatures based on TA (RS-TA), PE (RS-PE) and their combination (RS-Com). Receiver operating characteristic (ROC) curve analysis was performed to access performance of radiomics models for both internal and external validation cohorts.

RESULTS

10, four and six most predictive features were identified to be strongly associated with the EGFR mutation status, exon 19 and exon 21, respectively. The RSs derived from the PE region outperformed those from the TA region for predicting the EGFR mutation, exon 19 and exon 21. The RS-Coms generated the highest performance in the primary training (AUCs, RS-EGFR-Com vs. RS-exon 19-Com vs. RS-exon 21-Com, 0.955 vs. 0.946 vs. 0.928), internal validation (AUCs, RS-EGFR-Com vs. RS-exon 19-Com vs. RS-exon 21-Com, 0.879 vs. 0.819 vs. 0.882), external validation 1 (AUCs, RS-EGFR-Com vs. RS-exon 19-Com vs. RS-exon 21-Com, 0.830 vs. 0.825 vs. 0.822), and external validation 2 (AUCs, RS-EGFR-Com vs. RS-exon 19-Com vs. RS-exon 21-Com, 0.812 vs. 0.818 vs. 0.800) cohort.

CONCLUSION

The developed habitat-based radiomics model can be used to accurately predict the EGFR mutation subtypes, which may potentially guide personalized treatments for NSCLC patients with BM.

Habitat radiomics and deep learning fusion nomogram to predict EGFR mutation status in stage I non-small cell lung cancer: a multicenter study

Develop a radiomics nomogram that integrates deep learning, radiomics, and clinical variables to predict epidermal growth factor receptor (EGFR) mutation status in patients with stage I non-small cell lung cancer (NSCLC). We retrospectively included 438 patients who underwent curative surgery and completed driver-gene mutation tests for stage I NSCLC from four academic medical centers. Predictive models were established by extracting and analyzing radiomic features in intratumoral, peritumoral, and habitat regions of CT images to identify EGFR mutation status in stage I NSCLC. Additionally, three deep learning models based on the intratumoral region were constructed. A nomogram was developed by integrating representative radiomic signatures, deep learning, and clinical features. Model performance was assessed by calculating the area under the receiver operating characteristic (ROC) curve. The established habitat radiomics features demonstrated encouraging performance in discriminating between EGFR mutant and wild-type, with predictive ability superior to other single models (AUC 0.886, 0.812, and 0.790 for the training, validation, and external test sets, respectively). The radiomics-based nomogram exhibited excellent performance, achieving the highest AUC values of 0.917, 0.837, and 0.809 in the training, validation, and external test sets, respectively. Decision curve analysis (DCA) indicated that the nomogram provided a higher net benefit than other radiomics models, offering valuable information for treatment.

Value of multi-center 18F-FDG PET/CT radiomics in predicting EGFR mutation status in lung adenocarcinoma

BACKGROUND

Accurate, noninvasive, and reliable assessment of epidermal growth factor receptor (EGFR) mutation status and EGFR molecular subtypes is essential for treatment plan selection and individualized therapy in lung adenocarcinoma (LUAD). Radiomics models based on 18F-FDG PET/CT have great potential in identifying EGFR mutation status and EGFR subtypes in patients with LUAD. The validation of multi-center data, model visualization, and interpretation are significantly important for the management, application and trust of machine learning predictive models. However, few EGFR-related research involved model visualization and interpretation, and multi-center trial.

PURPOSE

To develop explainable optimal predictive models based on handcrafted radiomics features (HRFs) extracted from multi-center 18F-FDG PET/CT to predict EGFR mutation status and molecular subtypes in LUAD.

METHODS

Baseline 18F-FDG PET/CT images of 383 LUAD patients from three hospitals and one public data set were collected. Further, 1808 HRFs were extracted from the primary tumor regions using Pyradiomics. Predictive models were built based on cross-combination of seven feature selection methods and seven machine learning algorithms. Yellowbrick and explainable artificial intelligence technology were used for model visualization and interpretation. Receiver operating characteristic curve, classification report and confusion matrix were used for model performance evaluation. Clinical applicability of the optimal models was assessed by decision curve analysis.

RESULTS

STACK feature selection method combined with light gradient boosting machine (LGBM) reached optimal performance in identifying EGFR mutation status ([area under the curve] AUC = 0.81 in the internal test cohort; AUC = 0.62 in the external test cohort). Random forest feature selection method combined with LGBM reached optimal performance in predicting EGFR mutation molecular subtypes (AUC = 0.89 in the internal test cohort; AUC = 0.61 in the external test cohort).

CONCLUSIONS

Explainable machine learning models combined with radiomics features extracted from multi-center/scanner 18F-FDG PET/CT have certain potential to identify EGFR mutation status and subtypes in LUAD, which might be helpful to the treatment of LUAD.

Contrast Enhanced CT Radiogenomics in a Retrospective NSCLC Cohort: Models, Attempted Validation of a Published Model and the Relevance of the Clinical Context

RATIONALE AND OBJECTIVE

To develop a radiogenomic predictive model for non-small cell lung cancer (NSCLC) patients studied through contrast enhanced chest computed tomography (CE-CT) targeting the most frequent gene alterations. M&M: A retrospective study of patients with NSCLC imaged with CE-CT before treatment and had their tumor genomics sequenced at our institution was performed. Data was gathered from their imaging studies, their electronic medical records and a web-based database search (cBioPortal.ca). All of the patient data was tabulated for analysis. Two predictive models (M1 & M2) were created using different approaches and a third model was extracted from the literature to also be tested in our population.

RESULTS

Out of 157 patients, eighty were male (51%) and 124 (79%) had a history of smoking. The three most prevalent genes were KRAS, TP53 and EGFR. The M1 radiomics-only model median AUC were 0.61 (TP53), 0.53 (KRAS) and 0.64 (EGFR) and for M1 radiomics + clinical were 0.61 (TP53), 0.61 (KRAS) and 0.80 (EGFR). The M2 radiomics-only model median AUC were 0.63 (TP53), 0.60 (KRAS) and 0.65 (EGFR) and for M2 radiomics + clinical were 0.64 (TP53), 0.62 (KRAS) and 0.81 (EGFR). The external EGFR radiomic model showed an AUC of 0.69 and 0.86 for the radiomics-only and combined radiomics + clinical respectively.

CONCLUSION

Our study was able to provide robust predictive radiomics model evaluation for the detection of TP53, KRAS and EGFR. We also compared our performance with an already published model and observed how impactful clinical variables can be on models' performance.

CLINICAL RELEVANCE STATEMENT

Identifying tumor mutations in patients that can't undergo biopsy is critical for their outcomes.

KEYPOINTS

• Tumor genomic profiling is critical for treatment selection • CE-CT radiomics produce robust predictive models comparable to those already published • Clinical variables should be considered/included in predictive models.

Using Multi-phase CT Radiomics Features to Predict EGFR Mutation Status in Lung Adenocarcinoma Patients

RATIONALE AND OBJECTIVES

This study aimed to non-invasively predict epidermal growth factor receptor (EGFR) mutation status in patients with lung adenocarcinoma using multi-phase computed tomography (CT) radiomics features.

MATERIALS AND METHODS

A total of 424 patients with lung adenocarcinoma were recruited from two hospitals who underwent preoperative non-enhanced CT (NE-CT) and enhanced CT (including arterial phase CT [AP-CT], and venous phase CT [VP-CT]). Patients were divided into training (n = 297) and external validation (n = 127) cohorts according to hospital. Radiomics features were extracted from the NE-CT, AP-CT, and VP-CT images, respectively. The Wilcoxon test, correlation analysis, and simulated annealing were used for feature screening. A clinical model and eight radiomics models were established. Furthermore, a clinical-radiomics model was constructed by incorporating multi-phase CT features and clinical risk factors. Receiver operating characteristic curves were used to evaluate the predictive performance of the models.

RESULTS

The predictive performance of multi-phase CT radiomics model (AUC of 0.925 [95% CI, 0.879-0.971] in the validation cohort) was higher than that of NE-CT, AP-CT, VP-CT, and clinical models (AUCs of 0.860 [95% CI,0.794-0.927], 0.792 [95% CI, 0.713-0.871], 0.753 [95% CI, 0.669-0.838], and 0.706 [95% CI, 0.620-0.791] in the validation cohort, respectively) (all P < 0.05). The predictive performance of the clinical-radiomics model (AUC of 0.927 [95% CI, 0.882-0.971] in the validation cohort) was comparable to that of multi-phase CT radiomics model (P > 0.05).

CONCLUSION

Our multi-phase CT radiomics model showed good performance in identifying the EGFR mutation status in patients with lung adenocarcinoma, which may assist personalized treatment decisions.

Multisequence MRI-based radiomics signature as potential biomarkers for differentiating KRAS mutations in non-small cell lung cancer with brain metastases

Background

Kirsten rat sarcoma virus (KRAS) has evolved from a genotype with predictive value to a therapeutic target recently. The study aimed to establish non-invasive radiomics models based on MRI to discriminate KRAS from epidermal growth factor receptor (EGFR) or anaplastic lymphoma kinase (ALK) mutations in lung cancer patients with brain metastases (BM), then further explore the optimal sequence for prediction.

Methods

This retrospective study involved 317 patients (218 patients in training cohort and 99 patients in testing cohort) who had confirmed of KRAS, EGFR or ALK mutations. Radiomics features were separately extracted from T2WI, T2 fluid-attenuated inversion recovery (T2-FLAIR), diffusion weighted imaging (DWI) and contrast-enhanced T1-weighted imaging (T1-CE) sequences. The maximal information coefficient and recursive feature elimination method were used to select informative features. Then we built four radiomics models for differentiating KRAS from EGFR or ALK using random forest classifier. ROC curves were used to validate the capability of the models.

Results

The four radiomics models for discriminating KRAS from EGFR all worked well, especially DWI and T2WI models (AUCs: 0.942, 0.942 in training cohort, 0.949, 0.954 in testing cohort). When KRAS compared to ALK, DWI and T2-FLAIR models showed excellent performance in two cohorts (AUCs: 0.947, 0.917 in training cohort, 0.850, 0.824 in testing cohort).

Conclusions

Radiomics classifiers integrating MRI have potential to discriminate KRAS from EGFR or ALK, which are helpful to guide treatment and facilitate the discovery of new approaches capable of achieving this long-sought goal of cure in lung cancer patients with KRAS.

Nomogram using intratumoral and peritumoral radiomics for the preoperative prediction of visceral pleural invasion in clinical stage IA lung adenocarcinoma

BACKGROUND

Accurate prediction of visceral pleural invasion (VPI) in lung adenocarcinoma before operation can provide guidance and help for surgical operation and postoperative treatment. We investigate the value of intratumoral and peritumoral radiomics nomograms for preoperatively predicting the status of VPI in patients diagnosed with clinical stage IA lung adenocarcinoma.

METHODS

A total of 404 patients from our hospital were randomly assigned to a training set (n = 283) and an internal validation set (n = 121) using a 7:3 ratio, while 81 patients from two other hospitals constituted the external validation set. We extracted 1218 CT-based radiomics features from the gross tumor volume (GTV) as well as the gross peritumoral tumor volume (GPTV5, 10, 15), respectively, and constructed radiomic models. Additionally, we developed a nomogram based on relevant CT features and the radscore derived from the optimal radiomics model.

RESULTS

The GPTV10 radiomics model exhibited superior predictive performance compared to GTV, GPTV5, and GPTV15, with area under the curve (AUC) values of 0.855, 0.842, and 0.842 in the three respective sets. In the clinical model, the solid component size, pleural indentation, solid attachment, and vascular convergence sign were identified as independent risk factors among the CT features. The predictive performance of the nomogram, which incorporated relevant CT features and the GPTV10-radscore, outperformed both the radiomics model and clinical model alone, with AUC values of 0.894, 0.828, and 0.876 in the three respective sets.

CONCLUSIONS

The nomogram, integrating radiomics features and CT morphological features, exhibits good performance in predicting VPI status in lung adenocarcinoma.

MR-based radiomics predictive modelling of EGFR mutation and HER2 overexpression in metastatic brain adenocarcinoma: a two-centre study

OBJECTIVES

Magnetic resonance (MR)-based radiomics features of brain metastases are utilised to predict epidermal growth factor receptor (EGFR) mutation and human epidermal growth factor receptor 2 (HER2) overexpression in adenocarcinoma, with the aim to identify the most predictive MR sequence.

METHODS

A retrospective inclusion of 268 individuals with brain metastases from adenocarcinoma across two institutions was conducted. Utilising T1-weighted imaging (T1 contrast-enhanced [T1-CE]) and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequences, 1,409 radiomics features were extracted. These sequences were randomly divided into training and test sets at a 7:3 ratio. The selection of relevant features was done using the least absolute shrinkage selection operator, and the training cohort's support vector classifier model was employed to generate the predictive model. The performance of the radiomics features was evaluated using a separate test set.

RESULTS

For contrast-enhanced T1-CE cohorts, the radiomics features based on 19 selected characteristics exhibited excellent discrimination. No significant differences in age, sex, and time to metastasis were observed between the groups with EGFR mutations or HER2 + and those with wild-type EGFR or HER2 (p > 0.05). Radiomics feature analysis for T1-CE revealed an area under the curve (AUC) of 0.98, classification accuracy of 0.93, sensitivity of 0.92, and specificity of 0.93 in the training cohort. In the test set, the AUC was 0.82. The 19 radiomics features for the T2-FLAIR sequence showed AUCs of 0.86 in the training set and 0.70 in the test set.

CONCLUSIONS

This study developed a T1-CE signature that could serve as a non-invasive adjunctive tool to determine the presence of EGFR mutations and HER2 + status in adenocarcinoma, aiding in the direction of treatment plans.

CLINICAL RELEVANCE STATEMENT

We propose radiomics features based on T1-CE brain MR sequences that are both evidence-based and non-invasive. These can be employed to guide clinical treatment planning in patients with brain metastases from adenocarcinoma.

Distinguishing EGFR mutation molecular subtypes based on MRI radiomics features of lung adenocarcinoma brain metastases

OBJECTIVE

To explore the feasibility of identifying epidermal growth factor receptor (EGFR) mutation molecular subtypes in primary lesions based on the radiomics features of lung adenocarcinoma brain metastases using magnetic resonance imaging (MRI).

METHODS

We retrospectively analyzed clinical, imaging, and genetic testing data of patients with lung adenocarcinoma with EGFR gene mutations who had brain metastases. Three-dimensional radiomics features were extracted from contrast-enhanced T1-weighted images. The volume of interest was delineated and normalized using Z-score, dimensionality reduction was performed using principal component analysis, feature selection using Relief, and radiomics model construction using adaptive boosting as a classifier. Data were randomly divided into training and testing datasets at an 8:2 ratio. Five-fold cross-validation was conducted in the training set to select the optimal radiomics features and establish a predictive model for distinguishing between exon 19 deletion (19Del) and exon 21 L858R point mutation (21L858R), the two most common EGFR gene mutations. The testing set was used for external validation of the models. Model performance was evaluated using receiver operating characteristic curve and decision curve analyses.

RESULTS

Overall, 86 patients with 228 brain metastases were included. Patient age was identified as an independent predictor for distinguishing between 19Del and 21L858R. The area under the curve (AUC) values of the radiomics model in the training and testing datasets were 0.895 (95% confidence interval [CI]: 0.850-0.939) and 0.759 (95% CI: 0.0.614-0.903), respectively. The AUC for diagnosis of all cases using a combined model of age and radiomics was 0.888 (95% CI: 0.846-0.930), slightly higher than that of the radiomics model alone (0.866, 95% CI: 0.820-0.913), but without statistical significance (p=0.1626). In the decision curve analysis, both models demonstrated clinical net benefits.

CONCLUSIONS

The radiomics model based on MRI of lung adenocarcinoma brain metastases could distinguish between EGFR 19Del and 21L858R mutations in the primary lesion.

CT-Based Intratumoral and Peritumoral Radiomics Nomograms for the Preoperative Prediction of Spread Through Air Spaces in Clinical Stage IA Non-small Cell Lung Cancer

The study aims to investigate the value of intratumoral and peritumoral radiomics and clinical-radiological features for predicting spread through air spaces (STAS) in patients with clinical stage IA non-small cell lung cancer (NSCLC). A total of 336 NSCLC patients from our hospital were randomly divided into the training cohort (n = 236) and the internal validation cohort (n = 100) at a ratio of 7:3, and 69 patients from the other two external hospitals were collected as the external validation cohort. Univariate and multivariate analyses were used to select clinical-radiological features and construct a clinical model. The GTV, PTV5, PTV10, PTV15, PTV20, GPTV5, GPTV10, GPTV15, and GPTV20 models were constructed based on intratumoral and peritumoral (5 mm, 10 mm, 15 mm, 20 mm) radiomics features. Additionally, the radscore of the optimal radiomics model and clinical-radiological predictors were used to construct a combined model and plot a nomogram. Lastly, the ROC curve and AUC value were used to evaluate the diagnostic performance of the model. Tumor density type (OR = 6.738) and distal ribbon sign (OR = 5.141) were independent risk factors for the occurrence of STAS. The GPTV10 model outperformed the other radiomics models, and its AUC values were 0.887, 0.876, and 0.868 in the three cohorts. The AUC values of the combined model constructed based on GPTV10 radscore and clinical-radiological predictors were 0.901, 0.875, and 0.878. DeLong test results revealed that the combined model was superior to the clinical model in the three cohorts. The nomogram based on GPTV10 radscore and clinical-radiological features exhibited high predictive efficiency for STAS status in NSCLC.

Tumor-liver interface in MRI of liver metastasis enables prediction of EGFR mutation in patients with lung cancer: A proof-of-concept study

BACKGROUND

Preoperative prediction of the epidermal growth factor receptor (EGFR) status in non-small-cell lung cancer (NSCLC) patients with liver metastasis (LM) may have potential clinical values for assisting in treatment decision-making.

PURPOSE

To explore the value of tumor-liver interface (TLI)-based magnetic resonance imaging (MRI) radiomics for detecting the EGFR mutation in NSCLC patients with LM.

METHODS

This retrospective study included 123 and 44 patients from hospital 1 (between Feb. 2018 and Dec. 2021) and hospital 2 (between Nov. 2015 and Aug. 2022), respectively. The patients received contrast-enhanced T1-weighted (CET1) and T2-weighted (T2W) liver MRI scans before treatment. Radiomics features were extracted from MRI images of TLI and the whole tumor region, separately. The least absolute shrinkage and selection operator (LASSO) regression was used to screen the features and establish radiomics signatures (RSs) based on TLI (RS-TLI) and the whole tumor (RS-W). The RSs were evaluated by the receiver operating characteristic (ROC) curve analysis.

RESULTS

A total of 5 and 6 features were identified highly correlated with the EGFR mutation status from TLI and the whole tumor, respectively. The RS-TLI showed better prediction performance than RS-W in the training (AUCs, RS-TLI vs. RS-W, 0.842 vs. 0.797), internal validation (AUCs, RS-TLI vs. RS-W, 0.771 vs. 0.676) and external validation (AUCs, RS-TLI vs. RS-W, 0.733 vs. 0.679) cohort.

CONCLUSION

Our study demonstrated that TLI-based radiomics can improve prediction performance of the EGFR mutation in lung cancer patients with LM. The established multi-parametric MRI radiomics models may be used as new markers that can potentially assist in personalized treatment planning.

Predicting EGFR Mutation Status in Non-Small Cell Lung Cancer Using Artificial Intelligence: A Systematic Review and Meta-Analysis

RATIONALE AND OBJECTIVES

Recent advancements in artificial intelligence (AI) render a substantial promise for epidermal growth factor receptor (EGFR) mutation status prediction in non-small cell lung cancer (NSCLC). We aimed to evaluate the performance and quality of AI algorithms that use radiomics features in predicting EGFR mutation status in patient with NSCLC.

MATERIALS AND METHODS

We searched PubMed (Medline), EMBASE, Web of Science, and IEEExplore for studies published up to February 28, 2022. Studies utilizing an AI algorithm (either conventional machine learning [cML] and deep learning [DL]) for predicting EGFR mutations in patients with NSLCL were included. We extracted binary diagnostic accuracy data and constructed a bivariate random-effects model to obtain pooled sensitivity, specificity, and 95% confidence interval. This study is registered with PROSPERO, CRD42021278738.

RESULTS

Our search identified 460 studies, of which 42 were included. Thirty-five studies were included in the meta-analysis. The AI algorithms exhibited an overall area under the curve (AUC) value of 0.789 and pooled sensitivity and specificity levels of 72.2% and 73.3%, respectively. The DL algorithms outperformed cML in terms of AUC (0.822 vs. 0.775) and sensitivity (80.1% vs. 71.1%), but had lower specificity (70.0% vs. 73.8%, p-value < 0.001) compared to cML. Subgroup analysis revealed that the use of positron-emission tomography/computed tomography, additional clinical information, deep feature extraction, and manual segmentation can improve diagnostic performance.

CONCLUSION

DL algorithms can serve as a novel method for increasing predictive accuracy and thus have considerable potential for use in predicting EGFR mutation status in patient with NSCLC. We also suggest that guidelines on using AI algorithms in medical image analysis should be developed with a focus on oncologic radiomics.

A deep learning model integrating multisequence MRI to predict EGFR mutation subtype in brain metastases from non-small cell lung cancer

BACKGROUND

To establish a predictive model based on multisequence magnetic resonance imaging (MRI) using deep learning to identify wild-type (WT) epidermal growth factor receptor (EGFR), EGFR exon 19 deletion (19Del), and EGFR exon 21-point mutation (21L858R) simultaneously.

METHODS

A total of 399 patients with proven brain metastases of non-small cell lung cancer (NSCLC) were retrospectively enrolled and divided into training (n = 306) and testing (n = 93) cohorts separately based on two timepoints. All patients underwent 3.0-T brain MRI including T2-weighted, T2-weighted fluid-attenuated inversion recovery, diffusion-weighted imaging, and contrast-enhanced T1-weighted sequences. Radiomics features were extracted from each lesion based on four sequences. An algorithm combining radiomics approach with graph convolutional networks architecture (Radio-GCN) was designed for the prediction of EGFR mutation status and subtype. The area under the curve (AUC) at receiver operating characteristic analysis was used to evaluate the predication capabilities of each model.

RESULTS

We extracted 1,290 radiomics features from each MRI sequence. The AUCs of the Radio-GCN model for identifying EGFR 19Del, 21L858R, and WT for the lesion-wise analysis were 0.996 ± 0.004, 0.971 ± 0.013, and 1.000 ± 0.000 on the independent testing cohort separately. It also yielded AUCs of 1.000 ± 0.000, 0.991 ± 0.009, and 1.000 ± 0.000 for predicting EGFR mutations respectively for the patient-wise analysis. The κ coefficients were 0.735 and 0.812, respectively.

CONCLUSIONS

The constructed Radio-GCN model is a new potential tool to predict the EGFR mutation status and subtype in NSCLC patients with brain metastases.

RELEVANCE STATEMENT

The study demonstrated that a deep learning approach based on multisequence MRI can help to predict the EGFR mutation status in NSCLC patients with brain metastases, which is beneficial to guide a personalized treatment.

KEY POINTS

• This is the first study to predict the EGFR mutation subtype simultaneously. • The Radio-GCN model holds the potential to be used as a diagnostic tool. • This study provides an imaging surrogate for identifying the EGFR mutation subtype.

An [18F]FDG PET/3D-ultrashort echo time MRI-based radiomics model established by machine learning facilitates preoperative assessment of lymph node status in non-small cell lung cancer

OBJECTIVES

To develop an [18F]FDG PET/3D-UTE model based on clinical factors, three-dimensional ultrashort echo time (3D-UTE), and PET radiomics features via machine learning for the assessment of lymph node (LN) status in non-small cell lung cancer (NSCLC).

METHODS

A total of 145 NSCLC patients (training, 101 cases; test, 44 cases) underwent whole-body [18F]FDG PET/CT and chest [18F]FDG PET/MRI were enrolled. Preoperative clinical factors and 3D-UTE, CT, and PET radiomics features were analyzed. The Mann-Whitney U test, LASSO regression, and SelectKBest were used for feature extraction. Five machine learning algorithms were used to establish prediction models, which were evaluated by the area under receiver-operator characteristic (ROC), DeLong test, calibration curves, and decision curve analysis (DCA).

RESULTS

A prediction model based on random forest, consisting of four clinical factors, six 3D-UTE, and six PET radiomics features, was used as the final model for PET/3D-UTE. The AUCs of this model were 0.912 and 0.791 in the training and test sets, respectively, which not only showed different degrees of improvement over individual models such as clinical, 3D-UTE, and PET (AUC-training = 0.838, 0.834, and 0.828, AUC-test = 0.756, 0.745, and 0.768, respectively) but also achieved the similar diagnostic efficacy as the optimal PET/CT model (AUC-training = 0.890, AUC-test = 0.793). The calibration curves and DCA indicated good consistency (C-index, 0.912) and clinical utility of this model, respectively.

CONCLUSION

The [18F]FDG PET/3D-UTE model based on clinical factors, 3D-UTE, and PET radiomics features using machine learning methods could noninvasively assess the LN status of NSCLC.

CLINICAL RELEVANCE STATEMENT

A machine learning model of 18F-fluorodeoxyglucose positron emission tomography/ three-dimensional ultrashort echo time could noninvasively assess the lymph node status of non-small cell lung cancer, which provides a novel method with less radiation burden for clinical practice.

KEY POINTS

• The 3D-UTE radiomics model using the PLS-DA classifier was significantly associated with LN status in NSCLC and has similar diagnostic performance as the clinical, CT, and PET models. • The [18F]FDG PET/3D-UTE model based on clinical factors, 3D-UTE, and PET radiomics features using the RF classifier could noninvasively assess the LN status of NSCLC and showed improved diagnostic performance compared to the clinical, 3D-UTE, and PET models. • In the assessment of LN status in NSCLC, the [18F]FDG PET/3D-UTE model has similar diagnostic efficacy as the [18F]FDG PET/CT model that incorporates clinical factors and CT and PET radiomics features.

Hybrid deep multi-task learning radiomics approach for predicting EGFR mutation status of non-small cell lung cancer in CT images

Objective.Epidermal growth factor receptor (EGFR) mutation genotyping plays a pivotal role in targeted therapy for non-small cell lung cancer (NSCLC). We aimed to develop a computed tomography (CT) image-based hybrid deep radiomics model to predict EGFR mutation status in NSCLC and investigate the correlations between deep image and quantitative radiomics features.Approach.First, we retrospectively enrolled 818 patients from our centre and 131 patients from The Cancer Imaging Archive database to establish a training cohort (N= 654), an independent internal validation cohort (N= 164) and an external validation cohort (N= 131). Second, to predict EGFR mutation status, we developed three CT image-based models, namely, a multi-task deep neural network (DNN), a radiomics model and a feature fusion model. Third, we proposed a hybrid loss function to train the DNN model. Finally, to evaluate the model performance, we computed the areas under the receiver operating characteristic curves (AUCs) and decision curve analysis curves of the models.Main results.For the two validation cohorts, the feature fusion model achieved AUC values of 0.86 ± 0.03 and 0.80 ± 0.05, which were significantly higher than those of the single-task DNN and radiomics models (allP< 0.05). There was no significant difference between the feature fusion and the multi-task DNN models (P> 0.8). The binary prediction scores showed excellent prognostic value in predicting disease-free survival (P= 0.02) and overall survival (P< 0.005) for validation cohort 2.Significance.The results demonstrate that (1) the feature fusion and multi-task DNN models achieve significantly higher performance than that of the conventional radiomics and single-task DNN models, (2) the feature fusion model can decode the imaging phenotypes representing NSCLC heterogeneity related to both EGFR mutation and patient NSCLC prognosis, and (3) high correlations exist between some deep image and radiomics features.

Combined radiomics of primary tumour and bone metastasis improve the prediction of EGFR mutation status and response to EGFR-TKI therapy for NSCLC

PURPOSE

To develop radiomics models of primary tumour and spinal metastases to predict epidermal growth factor receptor (EGFR) mutations and therapeutic response to EGFR-tyrosine kinase inhibitor (TKI) in patients with metastatic non-small-cell lung cancer (NSCLC).

METHODS

We enrolled 203 patients with spinal metastases between December 2017 and September 2021, classified as patients with the EGFR mutation or EGFR wild-type. All patients underwent thoracic CT and spinal MRI scans before any treatment. Radiomics analysis was performed to extract features from primary tumour and metastases images and identify predictive features with the least absolute shrinkage and selection operator. Radiomics signatures (RS) were constructed based on primary tumour (RS-Pri), metastases (RS-Met), and in combination (RS-Com) to predict EGFR mutation status and response to EGFR-TKI. Receiver operating characteristic (ROC) curve analysis with 10-fold cross-validation was applied to assess the performance of the models.

RESULTS

To predict the EGFR mutation status, the RS based on the combination of primary tumour and metastases improved the prediction AUCs compared to those based on the primary tumour or metastasis alone in the training (RS-Com-EGFR: 0.927) and validation (RS-Com-EGFR: 0.812) cohorts. To predict response to EGFR-TKI, the developed RS based on combined primary tumour and metastasis generated the highest AUCs in the training (RS-Com-TKI: 0.880) and validation (RS-Com-TKI: 0.798) cohort.

CONCLUSIONS

Primary NSCLC and spinal metastases can provide complementary information to predict the EGFR mutation status and response to EGFR-TKI. The developed models that integrate primary lesions and metastases may be potential imaging markers to guide individual treatment decisions.

CT Radiomics Predict EGFR-T790M Resistance Mutation in Advanced Non-Small Cell Lung Cancer Patients After Progression on First-line EGFR-TKI

RATIONALE AND OBJECTIVES

We aim to explore the value of chest CT radiomics in predicting the epidermal growth factor receptor (EGFR)-T790M resistance mutation of advanced non-small cell lung cancer (NSCLC) patients after the failure of first-line EGFR-tyrosine kinase inhibitor (EGFR-TKI).

MATERIALS AND METHODS

A total of 211 and 135 advanced NSCLC patients with tumor tissue-based (Cohort-1) or circulating tumor DNA (ctDNA)-based (Cohort-2) EGFR-T790M testing were included, respectively. Cohort-1 was used for modeling and Cohort-2 was for models' validation. Radiomic features were extracted from tumor lesions on chest nonenhanced CT (NECT) and/or contrast-enhanced CT (CECT). We used eight feature selectors and eight classifier algorithms to establish radiomic models. Models were evaluated by area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA).

RESULTS

CT morphological manifestations of peripheral location and pleural indentation sign were associated with EGFR-T790M. For NECT, CECT, and NECT+CECT radiomic features, the feature selector and classifier algorithms of LASSO and Stepwise logistic regression, Boruta and SVM, and LASSO and SVM were chosen to develop the optimal model, respectively (AUC: 0.844, 0.811, and 0.897). All models performed well in calibration curves and DCA. Independent validation of models in Cohort-2 revealed that both NECT and CECT models individually had limited power for predicting EGFR-T790M mutation detected by ctDNA (AUC: 0.649, 0.675), while the NECT+CECT radiomic model had a satisfactory AUC (0.760).

CONCLUSION

This study proved the feasibility of using CT radiomic features to predict the EGFR-T790M resistance mutation, which could be helpful in guiding personalized therapeutic strategies.

Application of radiomics in diagnosis and treatment of lung cancer

Radiomics has become a research field that involves the process of converting standard nursing images into quantitative image data, which can be combined with other data sources and subsequently analyzed using traditional biostatistics or artificial intelligence (Al) methods. Due to the capture of biological and pathophysiological information by radiomics features, these quantitative radiomics features have been proven to provide fast and accurate non-invasive biomarkers for lung cancer risk prediction, diagnosis, prognosis, treatment response monitoring, and tumor biology. In this review, radiomics has been emphasized and discussed in lung cancer research, including advantages, challenges, and drawbacks.

Association between Contrast-Enhanced Computed Tomography Radiomic Features, Genomic Alterations and Prognosis in Advanced Lung Adenocarcinoma Patients

Non-invasive methods to assess mutational status, as well as novel prognostic biomarkers, are warranted to foster therapy personalization of patients with advanced non-small cell lung cancer (NSCLC). This study investigated the association of contrast-enhanced Computed Tomography (CT) radiomic features of lung adenocarcinoma lesions, alone or integrated with clinical parameters, with tumor mutational status (EGFR, KRAS, ALK alterations) and Overall Survival (OS). In total, 261 retrospective and 48 prospective patients were enrolled. A Radiomic Score (RS) was created with LASSO-Logistic regression models to predict mutational status. Radiomic, clinical and clinical-radiomic models were trained on retrospective data and tested (Area Under the Curve, AUC) on prospective data. OS prediction models were trained and tested on retrospective data with internal cross-validation (C-index). RS significantly predicted each alteration at training (radiomic and clinical-radiomic AUC 0.95-0.98); validation performance was good for EGFR (AUC 0.86), moderate for KRAS and ALK (AUC 0.61-0.65). RS was also associated with OS at univariate and multivariable analysis, in the latter with stage and type of treatment. The validation C-index was 0.63, 0.79, and 0.80 for clinical, radiomic, and clinical-radiomic models. The study supports the potential role of CT radiomics for non-invasive identification of gene alterations and prognosis prediction in patients with advanced lung adenocarcinoma, to be confirmed with independent studies.

Detection of the gene mutation of epidermal growth factor receptor in lung adenocarcinoma by radiomic features from a small amount of PET data

OBJECTIVE

The purpose of this work was to identify the potential mutation of epidermal growth factor receptor in nonsmall cell adenocarcinoma by noninvasive method, and to explore whether the same or better effect can be achieved using a small amount of single-mode PET image data.

METHOD

A total of 115 patients were recruited and the results of their 18F-FDG PET images and gene detection after resection were obtained; 117 original radiation features and 744 wavelet transform features were extracted from PET images. Several methods were used to reduce the dimension of the data, and four classifier models were established to classify it. The above process was repeated to reduce the total amount of data and the area under the receiver operating characteristic curve (AUC) value that changed with the reduction of the data and the stability of the results was recorded.

RESULTS

The classifier with the best comprehensive performance under this dataset was logistic regression, whose AUC value is 0.843. And similar results can be obtained from only 30 cases of data.

CONCLUSION

A similar or better result could be achieved using a small number of single-mode PET images. In addition, significant results could be obtained using only the PET images of 30 patients.

Integrative radiomics and transcriptomics analyses reveal subtype characterization of non-small cell lung cancer

OBJECTIVES

To assess whether integrative radiomics and transcriptomics analyses could provide novel insights for radiomic features' molecular annotation and effective risk stratification in non-small cell lung cancer (NSCLC).

METHODS

A total of 627 NSCLC patients from three datasets were included. Radiomics features were extracted from segmented 3-dimensional tumour volumes and were z-score normalized for further analysis. In transcriptomics level, 186 pathways and 28 types of immune cells were assessed by using the Gene Set Variation Analysis (GSVA) algorithm. NSCLC patients were categorized into subgroups based on their radiomic features and pathways enrichment scores using consensus clustering. Subgroup-specific radiomics features were used to validate clustering performance and prognostic value. Kaplan-Meier survival analysis with the log-rank test and univariable and multivariable Cox analyses were conducted to explore survival differences among the subgroups.

RESULTS

Three radiotranscriptomics subtypes (RTSs) were identified based on the radiomics and pathways enrichment profiles. The three RTSs were characterized as having specific molecular hallmarks: RTS1 (proliferation subtype), RTS2 (metabolism subtype), and RTS3 (immune activation subtype). RTS3 showed increased infiltration of most immune cells. The RTS stratification strategy was validated in a validation cohort and showed significant prognostic value. Survival analysis demonstrated that the RTS strategy could stratify NSCLC patients according to prognosis (p = 0.009), and the RTS strategy remained an independent prognostic indicator after adjusting for other clinical parameters.

CONCLUSIONS

This radiotranscriptomics study provides a stratification strategy for NSCLC that could provide information for radiomics feature molecular annotation and prognostic prediction.

KEY POINTS

• Radiotranscriptomics subtypes (RTSs) could be used to stratify molecularly heterogeneous patients. • RTSs showed relationships between molecular phenotypes and radiomics features. • The RTS algorithm could be used to identify patients with poor prognosis.

Radiomics and artificial intelligence for precision medicine in lung cancer treatment

Lung cancer is the leading cause of cancer-related deaths worldwide. It exhibits, at the mesoscopic scale, phenotypic characteristics that are generally indiscernible to the human eye but can be captured non-invasively on medical imaging as radiomic features, which can form a high dimensional data space amenable to machine learning. Radiomic features can be harnessed and used in an artificial intelligence paradigm to risk stratify patients, and predict for histological and molecular findings, and clinical outcome measures, thereby facilitating precision medicine for improving patient care. Compared to tissue sampling-driven approaches, radiomics-based methods are superior for being non-invasive, reproducible, cheaper, and less susceptible to intra-tumoral heterogeneity. This review focuses on the application of radiomics, combined with artificial intelligence, for delivering precision medicine in lung cancer treatment, with discussion centered on pioneering and groundbreaking works, and future research directions in the area.

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.

Systematic Review, Meta-Analysis and Radiomics Quality Score Assessment of CT Radiomics-Based Models Predicting Tumor EGFR Mutation Status in Patients with Non-Small-Cell Lung Cancer

Assessment of the quality and current performance of computed tomography (CT) radiomics-based models in predicting epidermal growth factor receptor (EGFR) mutation status in patients with non-small-cell lung carcinoma (NSCLC). Two medical literature databases were systematically searched, and articles presenting original studies on CT radiomics-based models for predicting EGFR mutation status were retrieved. Forest plots and related statistical tests were performed to summarize the model performance and inter-study heterogeneity. The methodological quality of the selected studies was assessed via the Radiomics Quality Score (RQS). The performance of the models was evaluated using the area under the curve (ROC AUC). The range of the Risk RQS across the selected articles varied from 11 to 24, indicating a notable heterogeneity in the quality and methodology of the included studies. The average score was 15.25, which accounted for 42.34% of the maximum possible score. The pooled Area Under the Curve (AUC) value was 0.801, indicating the accuracy of CT radiomics-based models in predicting the EGFR mutation status. CT radiomics-based models show promising results as non-invasive alternatives for predicting EGFR mutation status in NSCLC patients. However, the quality of the studies using CT radiomics-based models varies widely, and further harmonization and prospective validation are needed before the generalization of these models.

Nomograms Using CT Morphological Features and Clinical Characteristics to Identify COPD in Patients with Lung Cancer: A Multicenter Study

Purpose

This study aimed to screen out computed tomography (CT) morphological features and clinical characteristics of patients with lung cancer to identify chronic obstructive pulmonary disease (COPD). Further, we aimed to develop and validate different diagnostic nomograms for predicting whether lung cancer is comorbid with COPD.

Patients and Methods

This retrospective study examined data from 498 patients with lung cancer (280 with COPD, 218 without COPD; 349 in training cohort, 149 in validation cohort) from two centers. Five clinical characteristics and 20 CT morphological features were evaluated. Differences in all variables were assessed between COPD and non-COPD groups. Models were developed using multivariable logistic regression to identify COPD, including clinical, imaging, and combined nomograms. Receiver operating characteristic curves were used to evaluate and compare the performance of nomograms.

Results

Age, sex, interface, bronchus cutoff sign, spine-like process, and spiculation sign were independent predictors of COPD in patients with lung cancer. In the training and validation cohorts, the clinical nomogram showed good performance to predict COPD in lung cancer patients (areas under the curves [AUCs] of 0.807 [95% CI, 0.761-0.854] and 0.753 [95% CI, 0.674-0.832]); while the imaging nomogram showed slightly better performance (AUCs of 0.814 [95% CI, 0.770-0.858] and 0.780 [95% CI, 0.705-0.856]). For the combined nomogram generated with clinical and imaging features, the performance was further improved (AUC=0.863 [95% CI, 0.824-0.903], 0.811 [95% CI, 0.742-0.880] in the training and validation cohort). At 60% risk threshold, there were more true negative predictions (48 vs 44) and higher accuracy (73.15% vs 71.14%) for the combined nomogram compared with the clinical nomogram in the validation cohort.

Conclusion

The combined nomogram developed with clinical and imaging features outperformed clinical and imaging nomograms; this provides a convenient method to detect COPD in patients with lung cancer using one-stop CT scanning.

CT-based radiomics nomogram may predict who can benefit from adaptive radiotherapy in patients with local advanced-NSCLC patients

BACKGROUND

Although adaptive radiotherapy (ART) has many advantages, ART is not universal in the clinical appliance due to the consumption of a lot of labor, and economic burden. It is necessary to explore a CT stimulation-based radiomics model for screening who can get more benefits from ART in locally advanced non-small cell lung cancer (NSCLC) patients.

METHOD

183 cases of NSCLC patients receiving concurrent chemoradiotherapy with an adaptive approach were enrolled as a primary cohort, while 28 cases from another hospital served as an independent external validation cohort. Tumor regression assessment was conducted based on GTV reduction (Criteria A) or according to RECIST Version 1.1(Criteria B). The radiomics features were extracted by the "PyRadiomics" package and further screened by the LASSO method. Then, logistic regression was used to establish the model. Bootstrap and external validation were applied to verify the stability of the model. The receiver operating characteristic (ROC) curve was delineated to assess the predictive efficacy of the radiomics model. Dose-volume histograms were quantitatively compared between the initial and composite ART plans. Clinical endpoints included overall survival (OS) and progression-free survival (PFS).

RESULT

There were no significant differences in clinical features between tumor regression-resistant (RR) and tumor regression-sensitivity (RS) groups. The AUC values of the Criteria A model and Criteria B model were 0.767 and 0.771, respectively. Bootstrapping validation and external validation confirmed the stability of models. In all patients, there was a significant benefit of ART in the lung, heart, cord, and esophagus compared to non-ART, particularly in RS patients. Furthermore, PFS and OS from ART were significantly longer in RS as defined by Criterion B than in RR patients with the same ART application.

CONCLUSION

CT-based radiomics can screen out the patients who can gain more benefits from ART, which contribute to guiding and popularizing the application of ART strategy in the clinic within economic benefits and feasibility.

Machine learning-based CT radiomics model to discriminate the primary and secondary intracranial hemorrhage

It is challenging to distinguish between primary and secondary intracranial hemorrhage (ICH) purely by imaging data, and the two forms of ICHs are treated differently. This study aims to evaluate the potential of CT-based machine learning to identify the etiology of ICHs and compare the effectiveness of two regions of interest (ROI) sketching methods. A total of 1702 radiomic features were extracted from the CT brain images of 238 patients with acute ICH. We used the Select K Best method, least absolute shrinkage, and selection operator logistic regression to select the most discriminable features with a support vector machine to build a classifier model. Then, a ten-fold cross-validation strategy was employed to evaluate the performance of the classifier. From all quantitative CT-based imaging features obtained by two sketch methods, eighteen features were selected respectively. The radiomics model outperformed radiologists in distinguishing between primary and secondary ICH in both the volume of interest and the three-layer ROI sketches. As a result, a machine learning-based CT radiomics model can improve the accuracy of identifying primary and secondary ICH. A three-layer ROI sketch can identify primary versus secondary ICH based on the CT radiomics method.

Computed tomography-based texture assessment for the differentiation of benign, borderline, and early-stage malignant ovarian neoplasms

OBJECTIVE

This study was performed to examine the value of computed tomography-based texture assessment for characterizing different types of ovarian neoplasms.

METHODS

This retrospective study involved 225 patients with histopathologically confirmed ovarian tumors after surgical resection. Two different data sets of thick (5-mm) slices (during regular and portal venous phases) were analyzed. Raw data analysis, principal component analysis, linear discriminant analysis, and nonlinear discriminant analysis were performed to classify ovarian tumors. The radiologist's misclassification rate was compared with the MaZda (texture analysis software) findings. The results were validated with the neural network classifier. Receiver operating characteristic curves were analyzed to determine the performances of different parameters.

RESULTS

Nonlinear discriminant analysis had a lower misclassification rate than the other analyses. Thirty texture parameters significantly differed between the two groups. In the training set, WavEnLH_s-3 and WavEnHL_s-3 were the optimal texture features during the regular phase, while WavEnHH_s-4 and Kurtosis seemed to be the most discriminative features during the portal venous phase. In the validation test, benign versus malignant tumors and benign versus borderline lesions were well-distinguished.

CONCLUSIONS

Computed tomography-based texture features provide a useful imaging signature that may assist in differentiating benign, borderline, and early-stage ovarian cancer.

Deep learning for predicting the risk of immune checkpoint inhibitor-related pneumonitis in lung cancer

AIM

To develop and validate a nomogram model that combines computed tomography (CT)-based radiological factors extracted from deep-learning and clinical factors for the early predictions of immune checkpoint inhibitor-related pneumonitis (ICI-P).

MATERIALS AND METHODS

Forty ICI-P patients and 101 patients without ICI-P were divided randomly into the training (n=113) and test (n=28) sets. The convolution neural network (CNN) algorithm was used to extract the CT-based radiological features of predictable ICI-P and calculated the CT score of each patient. A nomogram model to predict the risk of ICI-P was developed by logistic regression.

RESULTS

CT score was calculated from five radiological features extracted by the residual neural network-50-V2 with feature pyramid networks. Four predictors of ICI-P in the nomogram model included a clinical feature (pre-existing lung diseases), two serum markers (absolute lymphocyte count and lactate dehydrogenase), and a CT score. The area under curve of the nomogram model in the training (0.910 versus 0.871 versus 0.778) and test (0.900 versus 0.856 versus 0.869) sets was better than the radiological and clinical models. The nomogram model showed good consistency and better clinical practicability.

CONCLUSION

The nomogram model that combined CT-based radiological factors and clinical factors can be used as a new non-invasive tool for the early prediction of ICI-P in lung cancer patients after immunotherapy with low cost and low manual input.

Application of radiomics based on chest CT-enhanced dual-phase imaging in the immunotherapy of non-small cell lung cancer

OBJECTIVE

To explore the value of applying computed tomography (CT) radiomics based on different CT-enhanced phases to determine the immunotherapeutic efficacy of non-small cell lung cancer (NSCLC).

METHODS

106 patients with NSCLC who underwent immunotherapy are randomly divided into training (74) and validation (32) groups. CT-enhanced arterial and venous phase images of patients before treatment are collected. Region-of-interest (ROI) is segmented on the CT-enhanced images, and the radiomic features are extracted. One-way analysis of variance and least absolute shrinkage and selection operator (LASSO) are used to screen the optimal radiomics features and analyze the association between radiomics features and immunotherapy efficacy. The area under receiver-operated characteristic curves (AUC) along with the sensitivity and specificity are computed to evaluate diagnostic effectiveness.

RESULTS

LASSO regression analysis screens and selects 6 and 8 optimal features in the arterial and venous phases images, respectively. Applying to the training group, AUCs based on CT-enhanced arterial and venous phase images are 0.867 (95% CI:0.82-0.94) and 0.880 (95% CI:0.86-0.91) with the sensitivities of 73.91% and 76.19%, and specificities of 66.67% and 72.19%, respectively, while in validation group, AUCs of the arterial and venous phase images are 0.732 (95% CI:0.71-0.78) and 0.832 (95% CI:0.78-0.91) with sensitivities of 75.00% and 76.00%, and specificities of 73.07% and 75.00%, respectively. There are no significant differences between AUC values computed from arterial phases and venous phases images in both training and validation groups (P < 0.05).

CONCLUSION

The optimally selected radiomics features computed from CT-enhanced different-phase images can provide new imaging marks to evaluate efficacy of the targeted therapy in NSCLC with a high diagnostic value.

Predicting Tumor Mutation Burden and EGFR Mutation Using Clinical and Radiomic Features in Patients with Malignant Pulmonary Nodules

Pulmonary nodules (PNs) shown as persistent or growing ground-glass opacities (GGOs) are usually lung adenocarcinomas or their preinvasive lesions. Tumor mutation burden (TMB) and somatic mutations are important determinants for the choice of strategy in patients with lung cancer during therapy. A total of 93 post-operative patients with 108 malignant PNs were enrolled for analysis (75 cases in the training cohort and 33 cases in the validation cohort). Radiomics features were extracted from preoperative non-contrast computed tomography (CT) images of the entire tumor. Using commercial next generation sequencing, we detected TMB status and somatic mutations of all FFPE samples. Here, 870 quantitative radiomics features were extracted from the segmentations of PNs, and pathological and clinical characteristics were collected from medical records. The LASSO (least absolute shrinkage and selection operator) regression and stepwise logistic regressions were performed to establish the predictive model. For the epidermal growth factor receptor (EGFR) mutation, the AUCs of the clinical model and the integrative model validated by the validation set were 0.6726 (0.4755-0.8697) and 0.7421 (0.5698-0.9144). For the TMB status, the ROCs showed that AUCs of the clinical model and the integrative model validated by the validation set were 0.7808 (0.6231-0.9384) and 0.8462 (0.7132-0.9791). The quantitative radiomics signatures showed potential value in predicting the EGFR mutant and TMB status in GGOs. Moreover, the integrative model provided sufficient information for the selection of therapy and deserves further analysis.

Radiomics for prediction of response to EGFR-TKI based on metastasis/brain parenchyma (M/BP)-interface

PURPOSE

To evaluate the potential of subregional radiomics as a novel tumor marker in predicting epidermal growth factor receptor (EGFR) mutation status and response to EGFR-tyrosine kinase inhibitor (TKI) therapy in NSCLC patients with brain metastasis (BM).

MATERIALS AND METHODS

We included 230 patients from center 1, and 80 patients were included from center 2 to form a primary and external validation cohort, respectively. Patients underwent contrast-enhanced T1-weighted and T2-weighted MRI scans before treatment. The individual- and population-level clustering was used to partition the peritumoral edema area (POA) into phenotypically consistent subregions. Radiomics features were calculated and selected from the tumor active area (TAA), POA and subregions, and used to develop models. Prediction values of each region were investigated and compared with receiver operating characteristic curves and Delong test.

RESULTS

For predicting EGFR mutations, a multi-region combined model (EGFR-Fusion) was developed based on joint of the partitioned metastasis/brain parenchyma (M/BP)-interface and TAA, and generated the highest prediction performance in the training (AUC = 0.945, SEN = 0.878, SPE = 0.937), internal validation (AUC = 0.880, SEN = 0.733, SPE = 0.969), and external validation (AUC = 0.895, SEN = 0.875, SPE = 0.800) cohorts. For predicting response to EGFR-TKI, the developed multi-region combined model (TKI-Fusion) yielded predictive AUCs of 0.869 (SEN = 0.717, SPE = 0.884), 0.786 (SEN = 0.708, SPE = 0.818), and 0.802 (SEN = 0.750, SPE = 0.800) in the training, internal validation and external validation cohort, respectively.

CONCLUSION

Our study revealed that complementary information regarding the EGFR status and response to EGFR-TKI can be provided by subregional radiomics. The proposed radiomics models may be new markers to guide treatment plans for NSCLC patients with BM.

Non-Invasive Biomarkers for Early Lung Cancer Detection

Worldwide, lung cancer (LC) is the most common cause of cancer death, and any delay in the detection of new and relapsed disease serves as a major factor for a significant proportion of LC morbidity and mortality. Though invasive methods such as tissue biopsy are considered the gold standard for diagnosis and disease monitoring, they have several limitations. Therefore, there is an urgent need to identify and validate non-invasive biomarkers for the early diagnosis, prognosis, and treatment of lung cancer for improved patient management. Despite recent progress in the identification of non-invasive biomarkers, currently, there is a shortage of reliable and accessible biomarkers demonstrating high sensitivity and specificity for LC detection. In this review, we aim to cover the latest developments in the field, including the utility of biomarkers that are currently used in LC screening and diagnosis. We comment on their limitations and summarise the findings and developmental stages of potential molecular contenders such as microRNAs, circulating tumour DNA, and methylation markers. Furthermore, we summarise research challenges in the development of biomarkers used for screening purposes and the potential clinical applications of newly discovered biomarkers.

Predicting anaplastic lymphoma kinase rearrangement status in patients with non-small cell lung cancer using a machine learning algorithm that combines clinical features and CT images

PURPOSE

To develop an appropriate machine learning model for predicting anaplastic lymphoma kinase (ALK) rearrangement status in non-small cell lung cancer (NSCLC) patients using computed tomography (CT) images and clinical features.

METHOD AND MATERIALS

This study included 193 patients with NSCLC (154 in the training cohort, 39 in the validation cohort), 68 of whom tested positive for ALK rearrangements and 125 of whom tested negative. From the nonenhanced CT scans, 157 radiomic characteristics were extracted, and 8 clinical features were collected. Five machine learning (ML) models were assessed to find the best classification model for predicting ALK rearrangement status. A radiomic signature was developed using the least absolute shrinkage and selection operator (LASSO) algorithm. The predictive performance of the models based on radiomic features, clinical features, and their combination was assessed by receiver operating characteristic (ROC) curves.

RESULTS

The support vector machine (SVM) model had the highest AUC of 0.914 for classification. The clinical features model had an AUC=0.805 (95% CI 0.731-0.877) and an AUC=0.735 (95% CI 0.566-0.863) in the training and validation cohorts, respectively. The CT image-based ML model had an AUC=0.953 (95% CI 0.913-1.0) in the training cohort and an AUC=0.890 (95% CI 0.778-0.971) in the validation cohort. For predicting ALK rearrangement status, the ML model based on CT images and clinical features performed better than the model based on only clinical information or CT images, with an AUC of 0.965 (95% CI 0.826-0.882) in the primary cohort and an AUC of 0.914 (95% CI 0.804-0.893) in the validation cohort.

CONCLUSION

Our findings revealed that ALK rearrangement status could be accurately predicted using an ML-based classification model based on CT images and clinical data.

Deep learning analysis to predict EGFR mutation status in lung adenocarcinoma manifesting as pure ground-glass opacity nodules on CT

BACKGROUND

Epidermal growth factor receptor-tyrosine kinase inhibitors (EGFR-TKIs) showed potency as a non-invasive therapeutic approach in pure ground-glass opacity nodule (pGGN) lung adenocarcinoma. However, optimal methods of extracting information about EGFR mutation from pGGN lung adenocarcinoma images remain uncertain. We aimed to develop, validate, and evaluate the clinical utility of a deep learning model for predicting EGFR mutation status in lung adenocarcinoma manifesting as pGGN on computed tomography (CT).

METHODS

We included 185 resected pGGN lung adenocarcinomas in the primary cohort. The patients were divided into training (n = 125), validation (n = 23), and test sets (n = 37). A preoperative CT-based deep learning model with clinical factors as well as clinical and radiomics models was constructed and applied to the test set. We evaluated the clinical utility of the deep learning model by applying it to 83 GGNs that received EGFR-TKI from an independent cohort (clinical validation set), and treatment response was regarded as the reference standard.

RESULTS

The prediction efficiencies of each model were compared in terms of area under the curve (AUC). Among the 185 pGGN lung adenocarcinomas, 122 (65.9%) were EGFR-mutant and 63 (34.1%) were EGFR-wild type. The AUC of the clinical, radiomics, and deep learning with clinical models to predict EGFR mutations were 0.50, 0.64, and 0.85, respectively, for the test set. The AUC of deep learning with the clinical model in the validation set was 0.72.

CONCLUSIONS

Deep learning approach of CT images combined with clinical factors can predict EGFR mutations in patients with lung adenocarcinomas manifesting as pGGN, and its clinical utility was demonstrated in a real-world sample.

Combination of 18F-Fluorodeoxyglucose PET/CT Radiomics and Clinical Features for Predicting Epidermal Growth Factor Receptor Mutations in Lung Adenocarcinoma

OBJECTIVE

To identify epidermal growth factor receptor (EGFR) mutations in lung adenocarcinoma based on ¹⁸F-fluorodeoxyglucose (FDG) PET/CT radiomics and clinical features and to distinguish EGFR exon 19 deletion (19 del) and exon 21 L858R missense (21 L858R) mutations using FDG PET/CT radiomics.

MATERIALS AND METHODS

We retrospectively analyzed 179 patients with lung adenocarcinoma. They were randomly assigned to training (n = 125) and testing (n = 54) cohorts in a 7:3 ratio. A total of 2632 radiomics features were extracted from the tumor region of interest from the PET (1316) and CT (1316) images. Six PET/CT radiomics features that remained after the feature selection step were used to calculate the radiomics model score (rad-score). Subsequently, a combined clinical and radiomics model was constructed based on sex, smoking history, tumor diameter, and rad-score. The performance of the combined model in identifying EGFR mutations was assessed using a receiver operating characteristic (ROC) curve. Furthermore, in a subsample of 99 patients, a PET/CT radiomics model for distinguishing 19 del and 21 L858R EGFR mutational subtypes was established, and its performance was evaluated.

RESULTS

The area under the ROC curve (AUROC) and accuracy of the combined clinical and PET/CT radiomics models were 0.882 and 81.6%, respectively, in the training cohort and 0.837 and 74.1%, respectively, in the testing cohort. The AUROC and accuracy of the radiomics model for distinguishing between 19 del and 21 L858R EGFR mutational subtypes were 0.708 and 66.7%, respectively, in the training cohort and 0.652 and 56.7%, respectively, in the testing cohort.

CONCLUSION

The combined clinical and PET/CT radiomics model could identify the EGFR mutational status in lung adenocarcinoma with moderate accuracy. However, distinguishing between EGFR 19 del and 21 L858R mutational subtypes was more challenging using PET/CT radiomics.

Differentiating EGFR from ALK mutation status using radiomics signature based on MR sequences of brain metastasis

PURPOSE

More and more small brain metastases (BMs) in asymptomatic patients can be detected even prior to their primary lung cancer with the development of MRI. The aim of this study was to develop a predictive radiomics model to identify epidermal growth factor receptor (EGFR) and anaplastic lymphoma kinase (ALK) mutation status in BM and explore the optimal MR sequence for predication.

METHODS

This retrospective study included 186 patients with proven BM of lung cancer (training cohort: 70 patients with EGFR mutations and 65 patients with ALK rearrangements; testing cohort: 26 patients with EGFR mutations and 25 patients with ALK rearrangements). Radiomics features were separately extracted from contrast-enhanced T1-weighted imaging (T1-CE), T2 fluid-attenuated inversion recovery (T2-FLAIR) and T2WI sequences. The model for three MR sequences were constructed using a random forest classifier. ROC curves were used to validate the capability of the models in the training and testing cohorts.

RESULTS

The AUCs of the T2-FLAIR model were significantly higher than those of the T1-CE model in training cohort (0.991 versus 0.954) and testing cohort (0.950 versus 0.867) and much higher than those of the T2WI model in training cohort (0.991 versus 0.880) and testing cohort (0.950 versus 0.731). Besides, the F1 scores of the T1-CE model were slightly higher than the T2-FLAIR model and much higher than the T2WI model in two cohorts.

CONCLUSION

T2-FLAIR and T1-CE radiomics models that can be used as noninvasive tools for identifying EGFR and ALK mutation status are helpful to guide therapeutic strategies.

Development and validation of MRI-based radiomics signatures as new markers for preoperative assessment of EGFR mutation and subtypes from bone metastases

Background

This study aimed to develop and externally validate contrast-enhanced (CE) T1-weighted MRI-based radiomics for the identification of epidermal growth factor receptor (EGFR) mutation, exon-19 deletion and exon-21 L858R mutation from MR imaging of spinal bone metastasis from primary lung adenocarcinoma.

Methods

A total of 159 patients from our hospital between January 2017 and September 2021 formed a primary set, and 24 patients from another center between January 2017 and October 2021 formed an independent validation set. Radiomics features were extracted from the CET1 MRI using the Pyradiomics method. The least absolute shrinkage and selection operator (LASSO) regression was applied for selecting the most predictive features. Radiomics signatures (RSs) were developed based on the primary training set to predict EGFR mutations and differentiate between exon-19 deletion and exon-21 L858R. The RSs were validated on the internal and external validation sets using the Receiver Operating Characteristic (ROC) curve analysis.

Results

Eight, three, and five most predictive features were selected to build RS-EGFR, RS-19, and RS-21 for predicting EGFR mutation, exon-19 deletion and exon-21 L858R, respectively. The RSs generated favorable prediction efficacies for the primary (AUCs, RS-EGFR vs. RS-19 vs. RS-21, 0.851 vs. 0.816 vs. 0.814) and external validation (AUCs, RS-EGFR vs. RS-19 vs. RS-21, 0.807 vs. 0.742 vs. 0.792) sets.

Conclusions

Radiomics features from the CE MRI could be used to detect the EGFR mutation, increasing the certainty of identifying exon-19 deletion and exon-21 L858R mutations based on spinal metastasis MR imaging.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-09985-4.