Non-small Cell Lung Cancer Status Research Articles

Prediction of oncogene mutation status in non-small cell lung cancer leveraging radiomics from CT scans: A systematic review and meta-analysis with a special focus on artificial-intelligence-based methods.

e20603 Background: In non-small cell lung cancer (NSCLC), alternative strategies to determine patient oncogene mutation status are essential to overcome some of the drawbacks associated with current methods. We aimed to review the use of radiomics alone or in combination with clinical data and to evaluate the performance of artificial intelligence (AI)-based models on the prediction of oncogene mutation status. Methods: A PRISMA-compliant literature review was conducted. The Medline (via Pubmed), Embase, and Cochrane Library databases were searched for studies published through June 30, 2023, predicting oncogene mutation status in patients with NSCLC using radiomics. Independent meta-analyses evaluating the performance of AI-based models developed with radiomics features or with a combination of radiomics features plus clinical data for the prediction of different oncogenic driver mutations were performed. A meta-regression to analyze the influence of methodological/clinical factors was also conducted. Results: Out of the 615 studies identified, 89 evaluating models for the prediction of epidermal growth factor-1 (EGFR), anaplastic lymphoma kinase (ALK), and Kirsten rat sarcoma virus (KRAS) mutations were included in the systematic review, including a total of 32,084 patients. A total of 38 met the inclusion criteria for the meta-analyses (encompassing 17,066 patients). The AI algorithms' sensitivity/false positive rate (FPR) in predicting EGFR, ALK, and KRAS mutations using radiomics-based models was 0.753 (95% CI 0.721–0.783)/0.346 (95% CI 0.305–0.390), 0.754 (95% CI 0.639–0.841)/ 0.225 (95% CI 0.163–0.302), and 0.744 (95% CI 0.605–0.846)/0.376 (95% CI 0.274–0.491), respectively. A meta-analysis of combined models was only possible for EGFR mutation, revealing a sensitivity/FPR of 0.800 (95% CI 0.767–0.830)/0.335 (95% CI 0.279–0.396). No statistically significant results were obtained in the meta-regression. Conclusions: Radiomics with a specific focus on CT-based models may represent valuable non-invasive tools for the determination of oncogene mutation status in NSCLC. Further investigation is required to analyze whether clinical data might boost their performance.

Predicting epidermal growth factor receptor mutations in non-small cell lung cancer through dual-layer spectral CT: a prospective study

ObjectiveTo determine whether quantitative parameters of detector-derived dual-layer spectral computed tomography (DLCT) can reliably identify epidermal growth factor receptor (EGFR) mutation status in patients with non-small cell lung cancer (NSCLC).MethodsPatients with NSCLC who underwent arterial phase (AP) and venous phase (VP) DLCT between December 2021 and November 2022 were subdivided into the mutated and wild-type EGFR groups following EGFR mutation testing. Their baseline clinical data, conventional CT images, and spectral images were obtained. Iodine concentration (IC), iodine no water (INW), effective atomic number (Zeff), virtual monoenergetic images, the slope of the spectral attenuation curve (λHU), enhancement degree (ED), arterial enhancement fraction (AEF), and normalized AEF (NAEF) were measured for each lesion.ResultsNinety-two patients (median age, 61 years, interquartile range [51, 67]; 33 men) were evaluated. The univariate analysis indicated that IC, normalized IC (NIC), INW and ED for the AP and VP, as well as Zeff and λHU for the VP were significantly associated with EGFR mutation status (all p < 0.05). INW(VP) showed the best diagnostic performance (AUC, 0.892 [95% confidence interval {CI}: 0.823, 0.960]). However, neither AEF (p = 0.156) nor NAEF (p = 0.567) showed significant differences between the two groups. The multivariate analysis showed that INW(AP) and NIC(VP) were significant predictors of EGFR mutation status, with the latter showing better performance (p = 0.029; AUC, 0.897 [95% CI: 0.816, 0.951] vs. 0.774 [95% CI: 0.675, 0.855]).ConclusionQuantitative parameters of DLCT can help predict EGFR mutation status in patients with NSCLC.Critical relevance statementQuantitative parameters of DLCT, especially NIC(VP), can help predict EGFR mutation status in patients with NSCLC, facilitating appropriate and individualized treatment for them.Key PointsDetermining EGFR mutation status in patients with NSCLC before starting therapy is essential.Quantitative parameters of DLCT can predict EGFR mutation status in NSCLC patients.NIC in venous phase is an important parameter to guide individualized treatment selection for NSCLC patients.Graphical

Integrating image and gene-data with a semi-supervised attention model for prediction of KRAS gene mutation status in non-small cell lung cancer.

KRAS is a pathogenic gene frequently implicated in non-small cell lung cancer (NSCLC). However, biopsy as a diagnostic method has practical limitations. Therefore, it is important to accurately determine the mutation status of the KRAS gene non-invasively by combining NSCLC CT images and genetic data for early diagnosis and subsequent targeted therapy of patients. This paper proposes a Semi-supervised Multimodal Multiscale Attention Model (S2MMAM). S2MMAM comprises a Supervised Multilevel Fusion Segmentation Network (SMF-SN) and a Semi-supervised Multimodal Fusion Classification Network (S2MF-CN). S2MMAM facilitates the execution of the classification task by transferring the useful information captured in SMF-SN to the S2MF-CN to improve the model prediction accuracy. In SMF-SN, we propose a Triple Attention-guided Feature Aggregation module for obtaining segmentation features that incorporate high-level semantic abstract features and low-level semantic detail features. Segmentation features provide pre-guidance and key information expansion for S2MF-CN. S2MF-CN shares the encoder and decoder parameters of SMF-SN, which enables S2MF-CN to obtain rich classification features. S2MF-CN uses the proposed Intra and Inter Mutual Guidance Attention Fusion (I2MGAF) module to first guide segmentation and classification feature fusion to extract hidden multi-scale contextual information. I2MGAF then guides the multidimensional fusion of genetic data and CT image data to compensate for the lack of information in single modality data. S2MMAM achieved 83.27% AUC and 81.67% accuracy in predicting KRAS gene mutation status in NSCLC. This method uses medical image CT and genetic data to effectively improve the accuracy of predicting KRAS gene mutation status in NSCLC.

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.

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 (all P < 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.

PP401 Toxicity and efficiency of EGFR-TKI for poor performance status non-small cell lung cancer with EGFR driver mutation: A retrospective analysis in a single institution

PP401 Toxicity and efficiency of EGFR-TKI for poor performance status non-small cell lung cancer with EGFR driver mutation: A retrospective analysis in a single institution

First-in-Humans PET Imaging of KRASG12C Mutation Status in Non-Small Cell Lung and Colorectal Cancer Patients Using [18F]PFPMD.

Kirsten rat sarcoma (KRAS) mutations are an important marker for tumor-targeted therapy. In this study, we sought to develop a KRASG12C oncoprotein-targeted PET tracer and to evaluate its translational potential for noninvasive imaging of the KRASG12C mutation in non-small cell lung cancer (NSCLC) and colorectal cancer (CRC) patients. Methods: [18F]PFPMD was synthesized on the basis of AMG510 (sotorasib) by attaching a polyethylene glycol chain to the quinazolinone structure. The binding selectivity and imaging potential of [18F]PFPMD were verified by cellular uptake, internalization, and blocking (H358: KRASG12C mutation; A549: non-KRASG12C mutation) studies, as well as by a small-animal PET/CT imaging study on tumor-bearing mice. Five healthy volunteers were enrolled to assess the safety, biodistribution, and dosimetry of [18F]PFPMD. Subsequently, 14 NSCLC or CRC patients with or without the KRASG12C mutation underwent [18F]PFPMD and [18F]FDG PET/CT imaging. The SUVmax of tumor uptake of [18F]PFPMD was measured and compared between patients with and without the KRASG12C mutation. Results: [18F]PFPMD was obtained with a high radiochemical yield, radiochemical purity, and stability. The protein-binding assay showed that [18F]PFPMD selectively binds to the KRASG12C protein. [18F]PFPMD uptake was significantly higher in H358 than in A549 and was decreased by pretreatment with AMG510 (H358 vs. A549: 3.22% ± 0.28% vs. 2.50% ± 0.25%, P < 0.05; block: 2.06% ± 0.13%, P < 0.01). Similar results were observed in tumor-bearing mice on PET imaging (H358 vs. A549: 3.93% ± 0.24% vs. 2.47% ± 0.26% injected dose/g, P < 0.01; block: 2.89% ± 0.29% injected dose/g; P < 0.05). [18F]PFPMD was safe in humans and was excreted primarily by the gallbladder and intestines. The whole-body effective dose was comparable to that of [18F]FDG. The accumulation of [18F]PFPMD in KRASG12C mutation tumors was significantly higher than that in non-KRASG12C mutation tumors (SUVmax: 3.73 ± 0.58 vs. 2.39 ± 0.22, P < 0.01) in NSCLC and CRC patients. Conclusion: [18F]PFPMD is a safe and promising PET tracer for noninvasive screening of the KRASG12C mutation status in NSCLC and CRC patients.

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.

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). 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-WhitneyUtest, 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). 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. 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. 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. • 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.

Dietary factors and the risk of lung cancer by epidermal growth factor receptor mutation status and histological subtypes.

Previous studies have reported differential associations of certain dietary factors such as soy consumption by epidermal growth factor receptor mutant (EGFR +) subtype of non-small cell lung cancer (NSCLC). However, whether the other dietary factors including meat, fruits, and vegetables have differential risks on different histological and molecular subtypes of lung cancer remains unclear. Therefore, we conducted a case-control study to evaluate these associations. A total of 3,170 cases and 4,238 controls from three different studies (Genes and Environment in Lung Cancer Study, Lung Cancer Consortium Singapore Study, and Multi-ethnic Cohort Study) were included. Information on demographics, lifestyle, and dietary consumption was obtained using questionnaires. Diet was assessed by using the number of standard servings of each item consumed per week. Multivariable logistic regression was used to estimate odds ratios (ORs) and 95% confidence intervals (CIs) for the association between meat, vegetables, and fruits consumption with lung cancer risk after adjusting for potential confounders. We identified a significant inverse association between higher consumption of fruits and the risk of lung cancer (2nd tertile: OR = 0.54, 95%CI = 0.46-0.65; 3rd tertile: OR = 0.77, 95%CI = 0.65-0.91), compared with the lower (1st tertile) consumption of fruits. Higher vegetable consumption was significantly associated with a lower risk of EGFR + lung cancer (OR = 0.69, 95% CI = 0.54-0.88), however, this association was not significant among EGFR wild-type (-) lung cancer. Conversely, higher consumption of total meat (OR = 2.10, 95%CI = 1.58-2.79) was significantly associated with higher lung cancer risk, as compared with the lower consumption group. Differential associations between vegetable consumption with EGFR mutation status in NSCLC were found. Further prospective studies are warranted to assess this association and elucidate the biological mechanisms.

Recent and current advances in PET/CT imaging in the field of predicting epidermal growth factor receptor mutations in non-small cell lung cancer.

Tyrosine kinase inhibitors (TKIs) are a significant treatment strategy for the management of non-small cell lung cancer (NSCLC) with epidermal growth factor receptor (EGFR) mutation status. Currently, EGFR mutation status is established based on tumor tissue acquired by biopsy or resection, so there is a compelling need to develop non-invasive, rapid, and accurate gene mutation detection methods. Non-invasive molecular imaging, such as positron emission tomography/computed tomography (PET/CT), has been widely applied to obtain the tumor molecular and genomic features for NSCLC treatment. Recent studies have shown that PET/CT can precisely quantify EGFR mutation status in NSCLC patients for precision therapy. This review article discusses PET/CT advances in predicting EGFR mutation status in NSCLC and their clinical usefulness.

Intratumoral and peritumoral radiomics nomograms for the preoperative prediction of lymphovascular invasion and overall survival in non-small cell lung cancer.

To evaluate the predictive value of intratumoral and peritumoral radiomics and radiomics nomogram for preoperative lymphovascular invasion (LVI) status and overall survival (OS) in patients with non-small cell lung cancer (NSCLC). In total, 240 NSCLC patients from our institution were randomly divided into the training cohort (n = 145) and internal validation cohort (n = 95) with a ratio of 6:4, and 65 patients from the Cancer Imaging Archive were enrolled as the external validation cohort. We extracted 1217 CT-based radiomics features from the gross tumor volume (GTV) and gross tumor volume incorporating peritumoral 3, 6, and 9 mm regions (GPTV3, GPTV6, GPTV9). A radiomics nomogram based on clinical independent predictors and radiomics score (Radscore) of the best radiomics model was constructed. The correlation between factors and OS was evaluated with the Kaplan-Meier survival analysis and Cox proportional hazards regression analysis. Compared with GTV, GPTV3, and GPTV6 radiomics models, GPTV9 radiomics model exhibited better prediction performance with the AUCs of 0.82, 0.75, and 0.67 in the training, internal validation, and external validation cohorts, respectively. In the clinical model, smoking and clinical stage were independent predictors. The nomogram incorporating independent predictors and GPTV9-Radscore was clinically useful, with the AUCs of 0.89, 0.83, and 0.66 in three cohorts. Pathological LVI, GPTV9-Radscore-predicted, and Nomoscore-predicted LVI were associated with poor OS (p < 0.05). CT-based radiomics nomogram can predict LVI and OS in patients with NSCLC and may help in making personalized treatment strategies before surgery. • Compared with GTV, GPTV3, and GPTV6 radiomics models, GPTV9 radiomics model showed better prediction performance for LVI status in NSCLC. • The radiomics nomogram based on GPTV9 radiomics features and clinical independent predictors could effectively predict LVI status and OS in NSCLC and outperformed the clinical model. • The radiomics nomogram had a wider scope of clinical application.

IMPORTANCE of PRETREATMENT 18F-FDG PET/CT TEXTURE ANALYSIS in PREDICTING EGFR and ALK MUTATION in PATIENTS with NON-SMALL CELL LUNG CANCER.

Identification of anaplastic lymphoma kinase (ALK) and epidermal growth factor receptor (EGFR) mutation types is of great importance before treatment with tyrosine kinase inhibitors (TKIs). Radiomics is a new strategy for noninvasively predicting the genetic status of cancer. We aimed to evaluate the predictive power of 18F-FDG PET/CT-based radiomic features for mutational status before treatment in non-small cell lung cancer (NSCLC) and to develop a predictive model based on radiomic features. Images of patients who underwent 18F-FDG PET/CT for initial staging with the diagnosis of NSCLC between January 2015 and July 2020 were evaluated using LIFEx software. The region of interest (ROI) of the primary tumor was established and volumetric and textural features were obtained. Clinical data and radiomic data were evaluated with machine learning (ML) algorithms to create a model. For EGFR mutation prediction, the most successful machine learning algorithm obtained with GLZLM_GLNU and clinical data was Naive Bayes (AUC: 0.751, MCC: 0.347, acc: 71.4%). For ALK rearrangement prediction, the most successful machine learning algorithm obtained with GLCM_correlation, GLZLM_LZHGE and clinical data was evaluated as Naive Bayes (AUC: 0.682, MCC: 0.221, acc: 77.4%). In our study, we created prediction models based on radiomic analysis of 18F-FDG PET/CT images. Tissue analysis with ML algorithms are non-invasive methods for predicting ALK rearrangement and EGFR mutation status in NSCLC, which may be useful for targeted therapy selection in a clinical setting.

Development and validation of a computed tomography-based immune ecosystem diversity index as an imaging biomarker in non-small cell lung cancer.

To date, there are no data on the noninvasive surrogate of intratumoural immune status that could be prognostic of survival outcomes in non-small cell lung cancer (NSCLC). We aimed to develop and validate the immune ecosystem diversity index (iEDI), an imaging biomarker, to indicate the intratumoural immune status in NSCLC. We further investigated the clinical relevance of the biomarker for survival prediction. In this retrospective study, two independent NSCLC cohorts (Resec1, n = 149; Resec2, n = 97) were included to develop and validate the iEDI to classify the intratumoural immune status. Paraffin-embedded resected specimens in Resec1 and Resec2 were stained by immunohistochemistry, and the density percentiles of CD3+, CD4+, and CD8+ T cells to all cells were quantified to estimate intratumoural immune status. Then, EDI features were extracted using preoperative computed tomography to develop an imaging biomarker, called iEDI, to determine the immune status. The prognostic value of iEDI was investigated on NSCLC patients receiving surgical resection (Resec1; Resec2; internal cohort Resec3, n = 419; external cohort Resec4, n = 96; and TCIA cohort Resec5, n = 55). iEDI successfully classified immune status in Resec1 (AUC 0.771, 95% confidence interval [CI] 0.759-0.783; and 0.770 through internal validation) and Resec2 (0.669, 0.647-0.691). Patients with higher iEDI-score had longer overall survival (OS) in Resec3 (unadjusted hazard ratio 0.335, 95%CI 0.206-0.546, p < 0.001), Resec4 (0.199, 0.040-1.000, p < 0.001), and TCIA (0.303, 0.098-0.944, p = 0.001). iEDI is a non-invasive surrogate of intratumoural immune status and prognostic of OS for NSCLC patients receiving surgical resection. • Decoding tumour immune microenvironment enables advanced biomarkers identification. • Immune ecosystem diversity index characterises intratumoural immune status noninvasively. • Immune ecosystem diversity index is prognostic for NSCLC patients.

A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts Tumor Immune Profiles in Non-Small Cell Lung Cancer: A Retrospective Multicohort Study.

BackgroundThe tumor immune microenvironment (TIME) phenotypes have been reported to mainly impact the efficacy of immunotherapy. Given the increasing use of immunotherapy in cancers, knowing an individual’s TIME phenotypes could be helpful in screening patients who are more likely to respond to immunotherapy. Our study intended to establish, validate, and apply a machine learning model to predict TIME profiles in non-small cell lung cancer (NSCLC) by using 18F-FDG PET/CT radiomics and clinical characteristics.MethodsThe RNA-seq data of 1145 NSCLC patients from The Cancer Genome Atlas (TCGA) cohort were analyzed. Then, 221 NSCLC patients from Daping Hospital (DPH) cohort received18F-FDG PET/CT scans before treatment and CD8 expression of the tumor samples were tested. The Artificial Intelligence Kit software was used to extract radiomic features of PET/CT images and develop a radiomics signature. The models were established by radiomics, clinical features, and radiomics-clinical combination, respectively, the performance of which was calculated by receiver operating curves (ROCs) and compared by DeLong test. Moreover, based on radiomics score (Rad-score) and clinical features, a nomogram was established. Finally, we applied the combined model to evaluate TIME phenotypes of NSCLC patients in The Cancer Imaging Archive (TCIA) cohort (n = 39).ResultsTCGA data showed CD8 expression could represent the TIME profiles in NSCLC. In DPH cohort, PET/CT radiomics model outperformed CT model (AUC: 0.907 vs. 0.861, P = 0.0314) to predict CD8 expression. Further, PET/CT radiomics-clinical combined model (AUC = 0.932) outperformed PET/CT radiomics model (AUC = 0.907, P = 0.0326) or clinical model (AUC = 0.868, P = 0.0036) to predict CD8 expression. In the TCIA cohort, the predicted CD8-high group had significantly higher immune scores and more activated immune pathways than the predicted CD8-low group (P = 0.0421).ConclusionOur study indicates that 18F-FDG PET/CT radiomics-clinical combined model could be a clinically practical method to non-invasively detect the tumor immune status in NSCLCs.

Predicting EGFR mutation status by a deep learning approach in patients with non-small cell lung cancer brain metastases.

Non-small cell lung cancer (NSCLC) tends to metastasize to the brain. Between 10 and 60% of NSCLCs harbor an activating mutation in the epidermal growth-factor receptor (EGFR), which may be targeted with selective EGFR inhibitors. However, due to a high discordance rate between the molecular profile of the primary tumor and the brain metastases (BMs), identifying an individual patient's EGFR status of the BMs necessitates tissue diagnosis via an invasive surgical procedure. We employed a deep learning (DL) method with the aim of noninvasive detection of the EGFR mutation status in NSCLC BM. We retrospectively collected clinical, radiological, and pathological-molecular data of all the NSCLC patients who had been diagnosed with BMs and underwent resection of their BM during 2009-2019. The study population was then divided into two groups based upon EGFR mutational status. We further employed a DL technique to classify the two groups according to their preoperative magnetic resonance imaging features. Augmentation techniques, transfer learning approach, and post-processing of the predicted results were applied to overcome the relatively small cohort. Finally, we established the accuracy of our model in predicting EGFR mutation status of BM of NSCLC. Fifty-nine patients were included in the study, 16 patients harbored EGFR mutations. Our model predicted mutational status with mean accuracy of 89.8%, sensitivity of 68.7%, specificity of 97.7%, and a receiver operating characteristic curve value of 0.91 across the 5 validation datasets. DL-based noninvasive molecular characterization is feasible, has high accuracy and should be further validated in large prospective cohorts.

Efficacy of early interdisciplinary palliative care based on WARM model in non-small-cell lung cancer

Objective: To assess the therapeutic effect of the early interdisciplinary palliative care based on WARM model (whole, assessment, revaluation, management) on the quality of life, psychological state, pain and nutritional status in patients with non-small-cell lung cancer (NSCLC). Methods: A total of 60 patients from Chongqing University Cancer Hospital with newly diagnosed advanced NSCLC from Oct 15, 2019 to Jun 12, 2020 were enrolled. According to the method of random number table, the patients were divided into two groups: standard oncologic care group (SC, n=30) and early palliative care group (EPC, n=30). SC group only received standard oncological care, while EPC group received standard oncological care and additional comprehensive treatment from a MDT consisted of medical oncologists, palliative care nurses, dietitians and psychologists. The quality of life [functional assessment of cancer therapy-lung (FACT-L) scale], psychological state [hospital anxiety and depression scale (HADS) and patient health questionnaire-9 (PHQ-9)], nutritional status [patient-generated subjective global assessment (PG-SGA)], and cancer pain status [numerical rating scale (NRS)] were observed and compared between the two groups before and after the 6 months treatment, respectively. Results: A total of 45 patients completed 6 months treatment, including 24 males and 21 females, aged 38-82 (60.5±1.7), with 23 patients in the EPC group and 22 patients in the SC group. Patients assigned to EPC group had a better quality of life than those assigned to SC group [FACT-L scale: (122.3±1.6) vs (111.8±2.1), P<0.001]. Fewer patients had anxiety and depressive symptoms in the EPC group than those in the SC group [HADS anxiety subscale: (1.1±0.3) vs (2.9±0.4), P<0.001; HADS depression subscale: (0.7±0.3) vs (3.6±0.4), P<0.001]. The PHQ-9 results showed that 100.0% (23/23) patients were free of depression in the EPC group, while 45.5% (10/22) patients were free of depression in SC group (P<0.001). Furthermore, patients in the EPC group had a better nutritional status [moderate malnutrition: 60.9% (14/23); no malnutrition: 39.1% (9/23)] than those in the SC group [severe malnutrition: 40.9% (9/22); moderate malnutrition: 50.0% (11/22); no malnutrition: 9.1% (2/22)] (P<0.001). There was no significant difference in NRS score between EPC group and SC group (P=0.140). Conclusion: Early interdisciplinary palliative care based on WARM model can improve the quality of life, psychological state and nutritional status in NSCLC patients.

1312P Prognostic impact of KRAS status in patients with non-small cell lung cancer (NSCLC) treated with immune checkpoint inhibitor monotherapy

KRAS gene mutations are found in 20-30% of NSCLC. The prognostic value of KRAS status in NSCLC is still controversial, and may be affected by mutation subtypes. Moreover, KRAS mutations have been associated with increased programmed death-ligand 1 (PD-L1) expression, high tumor mutation burden and might be associated with greater benefit from ICI. Therefore, we explored the prognostic impact of KRAS mutations in patients with advanced NSCLC treated with ICI monotherapy.

Effect of Radiation in Patients with HeartMate 3 LVAD Therapy

Introduction Radiation therapy in patients with axial flow left ventricular assist devices (LVAD) has not been associated with significant device malfunction. However, the effects of radiation on the fully magnetically levitated HeartMate 3 (Abbott, Abbott Park, IL) LVAD are not well known. We report two cases of stereotactic bone radiation therapy (SBRT) in patients with a HeartMate 3 LVAD implantation. Case Report Patient 1 71-year-old woman with history of chronic systolic heart failure status post HeartMate 3 LVAD and history of left upper lobe non-small cell lung cancer status post lobectomy was found to have an incidental left lateral thorax wall mass on CT imaging with subsequent biopsy consistent for recurrent oligometastatic lung adenocarcinoma. She consequently underwent 5 fractions of 600 cGy SBRT to her left lateral chest wall over a period of 10 days. Mild fatigue was reported following radiation, however LVAD log files sent subsequent to each fraction were unremarkable. On follow up, no cardiac symptoms were reported and LVAD parameters were normal with flow 4.6 L/min, speed 5600 rpm, pulse index 2.8 and power 4.4 watts. Device malfunction has not been witnessed during 1 year follow up. Patient 2 70-year-old man with history of advanced systolic heart failure status post HeartMate 3 LVAD implantation was found to have a right upper lobe nodule and mediastinal lymphadenopathy on CT imaging. Ensuing biopsy diagnosed squamous cell lung cancer without metastatic disease. SBRT was initiated and 5 treatments of 1000 cGy were delivered to the right upper lobe lesion within 10 days. No LVAD complications or symptoms of heart failure were witnessed during treatment. On follow up, patient denied any symptoms and LVAD function remained normal with observed with flow 4.3 L/min, speed 5200 rpm, pulse index 4.8 and power 3.8 watts. Device malfunction has not been witnessed during 1 year follow up. Summary Our 2 cases suggests that SBRT in patients with HeartMate 3 LVAD implantation may be safe and likely not associated with device malfunction. Larger studies are required to better evaluate this relationship and to determine long term safety profile.

A PET/CT nomogram incorporating SUVmax and CT radiomics for preoperative nodal staging in non-small cell lung cancer

ObjectivesTo develop and validate a PET/CT nomogram for preoperative estimation of lymph node (LN) staging in patients with non-small cell lung cancer (NSCLC).MethodsA total of 263 pathologically confirmed LNs from 124 patients with NCSLC were retrospectively analyzed. Positron-emission tomography/computed tomography (PET/CT) examination was performed before treatment according to the clinical schedule. In the training cohort (N = 185), malignancy-related features, such as SUVmax, short-axis diameter (SAD), and CT radiomics features, were extracted from the regions of LN based on the PET/CT scan. The Minimum-Redundancy Maximum-Relevance (mRMR) algorithm and the Least Absolute Shrinkage and Selection Operator (LASSO) regression model were used for feature selection and radiomics score building. The radiomics score (Rad-Score) and SUVmax were incorporated in a PET/CT nomogram using the multivariable logistic regression analysis. The performance of the proposed model was evaluated with discrimination, calibration, and clinical application in an independent testing cohort (N = 78).ResultsThe radiomics scores consisting of 14 selected features were significantly associated with LN status for both training cohort with AUC of 0.849 (95% confidence interval (CI), 0.796–0.903) and testing cohort with AUC of 0.828 (95% CI, 0.782–0.919). The PET/CT nomogram incorporating radiomics score and SUVmax showed moderate improvement of the efficiency with AUC of 0.881 (95% CI, 0.834–0.928) in the training cohort and AUC of 0.872 (95% CI, 0.797–0.946) in the testing cohort. The decision curve analysis indicated that the PET/CT nomogram was clinically useful.ConclusionThe PET/CT nomogram, which incorporates Rad-Score and SUVmax, can improve the diagnostic performance of LN metastasis.Key Points• The PET/CT nomogram (Int-Score) based on lymph node (LN) PET/CT images can reliably predict LN status in NSCLC.• Int-Score is a relatively objective diagnostic method, which can play an auxiliary role in the process of clinicians making treatment decisions.

Abstract 16294: A Case of Paradoxical Coronary Embolism in a Patient With Undiagnosed Malignancy

Introduction: Coronary embolism is a rare cause of acute myocardial infarction (AMI) in comparison with atherosclerotic plaque rupture. We present a case of an inferior ST elevation myocardial infarction caused by coronary embolism. The source was thought to be from the combination of deep vein thrombosis (DVT) and patent foramen ovale (PFO), accounting for a unique presentation and pathophysiology. Case: An 86-year-old female with a history of hypertension, non-small cell lung cancer status post resection with no residual disease, presented with a three-day history of epigastric discomfort, dyspnea on exertion and confusion. On presentation, she was afebrile with normal vital signs. Physical exam revealed epigastric pain on palpation. Initial labs were significant for high sensitivity troponin elevation to 9591 ng/L. ECG showed ST elevations in leads II, III, aVF. Coronary angiogram showed distal left anterior descending artery 71% stenosis and left posterior descending artery 99% stenosis. Given multiple distal locations concerning for coronary emboli, coronary angioplasty was done without stenting given no evidence of plaque rupture. After the angiogram, patient was found to have slurred speech and left sided facial droop. CT head showed multiple embolic infarcts. A transesophageal echocardiogram revealed a small PFO but no valvular vegetation/calcification or left atrial appendage thrombus. Lower extremity dopplers demonstrated lower extremity DVT. CT abdomen showed a pancreatic mass with hepatic metastasis, concerning for metastatic pancreatic adenocarcinoma. Patient was started on atorvastatin and aspirin only as AMI was due to a suspected embolic event. She received an IVC filter due to contraindication of anticoagulation in acute stroke and discharged to follow up with Oncology outpatient. Conclusions: In comparison to atherosclerotic plaque rupture, AMI as a result of an embolic coronary phenomena is rare. In fact, less than 1% of AMIs are caused by paradoxical embolism due to a PFO. There are many case reports about embolic AMI due to valvular vegetation or calcification. However, paradoxical coronary embolism due to PFO should be considered in patients with risk factors for a hypercoagulable state such as malignancy or DVT.