Associations Between Somatic Mutations and Metabolic Imaging Phenotypes in Non-Small Cell Lung Cancer

Peritumoral radiomics features predict distant metastasis in locally advanced NSCLC

Purpose

Radiomics provides quantitative tissue heterogeneity profiling and is an exciting approach to developing imaging biomarkers in the context of precision medicine. Normal-appearing parenchymal tissues surrounding primary tumors can harbor microscopic disease that leads to increased risk of distant metastasis (DM). This study assesses whether computed-tomography (CT) imaging features of such peritumoral tissues can predict DM in locally advanced non-small cell lung cancer (NSCLC).

Material and methods

200 NSCLC patients of histological adenocarcinoma were included in this study. The investigated lung tissues were tumor rim, defined to be 3mm of tumor and parenchymal tissue on either side of the tumor border and the exterior region extended from 3 to 9mm outside of the tumor. Fifteen stable radiomic features were extracted and evaluated from each of these regions on pre-treatment CT images. For comparison, features from expert-delineated tumor contours were similarly prepared. The patient cohort was separated into training and validation datasets for prognostic power evaluation. Both univariable and multivariable analyses were performed for each region using concordance index (CI).

Results

Univariable analysis reveals that six out of fifteen tumor rim features were significantly prognostic of DM (p-value < 0.05), as were ten features from the visible tumor, and only one of the exterior features was. Multivariablely, a rim radiomic signature achieved the highest prognostic performance in the independent validation sub-cohort (CI = 0.64, p-value = 2.4×10⁻⁵) significantly over a multivariable clinical model (CI = 0.53), a visible tumor radiomics model (CI = 0.59), or an exterior tissue model (CI = 0.55). Furthermore, patient stratification by the combined rim signature and clinical predictor led to a significant improvement on the clinical predictor alone and also outperformed stratification using the combined tumor signature and clinical predictor.

Conclusions

We identified peritumoral rim radiomic features significantly associated with DM. This study demonstrated that peritumoral imaging characteristics may provide additional valuable information over the visible tumor features for patient risk stratification due to cancer metastasis.

MR-Based Radiomics Nomogram of Cervical Cancer in Prediction of the Lymph-Vascular Space Invasion preoperatively

Background

Lymph‐vascular space invasion (LVSI) is an unfavorable prognostic factor in cervical cancer. Unfortunately, there are no current clinical tools for the preoperative prediction of LVSI.

Purpose

To develop and validate an axial T₁ contrast‐enhanced (CE) MR‐based radiomics nomogram that incorporated a radiomics signature and some clinical parameters for predicting LVSI of cervical cancer preoperatively.

Study Type

Retrospective.

Population

In all, 105 patients were randomly divided into two cohorts at a 2:1 ratio.

Field Strength/Sequence

T₁ CE MRI sequences at 1.5T.

Assessment

Univariate analysis was performed on the radiomics features and clinical parameters. Multivariate analysis was performed to determine the optimal feature subset. The receiver operating characteristic (ROC) analysis was performed to evaluate the performance of prediction model and radiomics nomogram.

Statistical Tests

The Mann–Whitney U‐test and the chi‐square test were used to evaluate the performance of clinical characteristics and LVSI status by pathology. The minimum‐redundancy/maximum‐relevance and recursive feature elimination methods were applied to select the features. The radiomics model was constructed using logistic regression.

Results

Three radiomics features and one clinical characteristic were selected. The radiomics nomogram showed favorable discrimination between LVSI and non‐LVSI groups. The AUC was 0.754 (95% confidence interval [CI], 0.6326–0.8745) in the training cohort and 0.727 (95% CI, 0.5449–0.9097) in the validation cohort. The specificity and sensitivity were 0.756 and 0.828 in the training cohort and 0.773 and 0.692 in the validation cohort.

Data Conclusion

T₁ CE MR‐based radiomics nomogram serves as a noninvasive biomarker in the prediction of LVSI in patients with cervical cancer preoperatively.

Level of Evidence: 4

Technical Efficacy: Stage 2

J. Magn. Reson. Imaging 2019;49:1420–1426.

The developing role of FDG PET imaging for prognostication and radiotherapy target volume delineation in non-small cell lung cancer

Advancements in functional imaging technology have allowed new possibilities in contouring of target volumes, monitoring therapy, and predicting treatment outcome in non-small cell lung cancer (NSCLC). Consequently, the role of ¹⁸F-fluorodeoxyglucose positron emission tomography (FDG PET) has expanded in the last decades from a stand-alone diagnostic tool to a versatile instrument integrated with computed tomography (CT), with a prominent role in lung cancer radiotherapy. This review outlines the most recent literature on developments in FDG PET imaging for prognostication and radiotherapy target volume delineation (TVD) in NSCLC. We also describe the challenges facing the clinical implementation of these developments and present new ideas for future research.

Radiomics in Oncological PET/CT: Clinical Applications

18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) is widely used for staging, evaluating treatment response, and predicting prognosis in malignant diseases. FDG uptake and volumetric PET parameters such as metabolic tumor volume have been used and are still used as conventional PET parameters to assess biological characteristics of tumors. However, in recent years, additional features derived from PET images by computational processing have been found to reflect intratumoral heterogeneity, which is related to biological tumor features, and to provide additional predictive and prognostic information, which leads to the concept of radiomics. In this review, we focus on recent clinical studies of malignant diseases that investigated intratumoral heterogeneity on PET/CT, and we discuss its clinical role in various cancers.

Value of 18F-FDG PET/CT for predicting EGFR mutations and positive ALK expression in patients with non-small cell lung cancer: a retrospective analysis of 849 Chinese patients

PURPOSE

Epidermal growth factor receptor (EGFR) mutations and the anaplastic lymphoma kinase (ALK) rearrangement are the two most common druggable targets in non-small cell lung cancer (NSCLC). However, genetic testing is sometimes unavailable. Previous studies regarding the predictive role of 18F-FDG PET/CT for EGFR mutations in NSCLC patients are conflicting. We investigated whether or not 18F-FDG PET could be a valuable noninvasive method to predict EGFR mutations and ALK positivity in NSCLC using the largest patient cohort to date.

METHODS

We retrospectively reviewed and included 849 NSCLC patients who were tested for EGFR mutations or ALK status and subjected to 18F-FDG PET/CT prior to treatment. The differences in several clinical characteristics and three parameters based on 18F-FDG PET/CT, including the maximal standard uptake value (SUVmax) of the primary tumor (pSUVmax), lymph node (nSUVmax) and distant metastasis (mSUVmax), between the different subgroups were analyzed. Multivariate logistic regression analysis was performed to identify predictors of EGFR mutations and ALK positivity.

RESULTS

EGFR mutations were identified in 371 patients (45.9%). EGFR mutations were found more frequently in females, non-smokers, adenocarcinomas and stage I disease. Low pSUVmax, nSUVmax and mSUVmax were significantly associated with EGFR mutations. Multivariate analysis demonstrated that pSUVmax < 7.0, female sex, non-smoker status and adenocarcinoma were predictors of EGFR mutations. The receiver operating characteristic (ROC) curve yielded area under the curve (AUC) values of 0.557 and 0.697 for low pSUVmax alone and the combination of the four factors, respectively. ALK-positive patients tended to have a high nSUVmax. Younger age and distant metastasis were the only two independent predictors of ALK positivity.

CONCLUSION

We demonstrated that low pSUVmax is associated with mutant EGFR status and could be integrated with other clinical factors to enhance the discriminability on the EGFR mutation status in some NSCLC patients whose EGFR testing is unavailable.

Repeatability of FDG PET/CT metrics assessed in free breathing and deep inspiration breath hold in lung cancer patients

We measured the repeatability of FDG PET/CT uptake metrics when acquiring scans in free breathing (FB) conditions compared with deep inspiration breath hold (DIBH) for locally advanced lung cancer. Twenty patients were enrolled in this prospective study. Two FDG PET/CT scans per patient were conducted few days apart and in two breathing conditions (FB and DIBH). This resulted in four scans per patient. Up to four FDG PET avid lesions per patient were contoured. The following FDG metrics were measured in all lesions and in all four scans: Standardized uptake value (SUV)_peak, SUV_max, SUV_mean, metabolic tumor volume (MTV) and total lesion glycolysis (TLG), based on an isocontur of 50% of SUV_max. FDG PET avid volumes were delineated by a nuclear medicine physician. The gross tumor volumes (GTV) were contoured on the corresponding CT scans. Nineteen patients were available for analysis. Test-retest standard deviations of FDG uptake metrics in FB and DIBH were: SUV_peak FB/DIBH: 16.2%/16.5%; SUV_max: 18.2%/22.1%; SUV_mean: 18.3%/22.1%; TLG: 32.4%/40.5%. DIBH compared to FB resulted in higher values with mean differences in SUV_max of 12.6%, SUV_peak 4.4% and SUV_mean 11.9%. MTV, TLG and GTV were all significantly smaller on day 1 in DIBH compared to FB. However, the differences between metrics under FB and DIBH were in all cases smaller than 1 SD of the day to day repeatability. FDG acquisition in DIBH does not have a clinically relevant impact on the uptake metrics and does not improve the test-retest repeatability of FDG uptake metrics in lung cancer patients.

The role of metabolic tumor volume (MTV) measured by [18F] FDG PET/CT in predicting EGFR gene mutation status in non-small cell lung cancer

Many noninvasive methods have been explored to determine the mutation status of the epidermal growth factor receptor (EGFR) gene, which is important for individualized treatment of non-small cell lung cancer (NSCLC). We evaluated whether metabolic tumor volume (MTV), a parameter measured by [18F] fluorodeoxyglucose positron emission tomography/computed tomography (PET/CT) might help predict EGFR mutation status in NSCLC. Overall, 87 patients who underwent EGFR genotyping and pretreatment PET/CT between January 2013 and September 2016 were reviewed. Clinicopathologic characteristics and metabolic parameters including MTV were evaluated. Univariate and multivariate analyses were used to assess the independent variables that predict mutation status to create prediction models. Forty-one patients (41/87) were identified as having EGFR mutations. The multivariate analysis showed that patients with lower MTV (MTV≤11.0 cm3, p=0.001) who were non-smokers (p=0.037) and had a peripheral tumor location (p=0.033) were more likely to have EGFR mutations. Prediction models using these criteria for EGFR mutation yielded a high AUC (0.805, 95% CI 0.712–0.899), which suggests that the analysis had good discrimination. In conclusion, NSCLC patients with EGFR mutations showed significantly lower MTV than patients with wild-type EGFR. Prediction models based on MTV and clinicopathologic characteristics could provide more information for the identification of EGFR mutations.

Development of an Immune-Pathology Informed Radiomics Model for Non-Small Cell Lung Cancer

With increasing use of immunotherapy agents, pretreatment strategies for identifying responders and non-responders is useful for appropriate treatment assignment. We hypothesize that the local immune micro-environment of NSCLC is associated with patient outcomes and that these local immune features exhibit distinct radiologic characteristics discernible by quantitative imaging metrics. We assembled two cohorts of NSCLC patients treated with definitive surgical resection and extracted quantitative parameters from pretreatment CT imaging. The excised primary tumors were then quantified for percent tumor PDL1 expression and density of tumor-infiltrating lymphocyte (via CD3 count) utilizing immunohistochemistry and automated cell counting. Associating these pretreatment radiomics parameters with tumor immune parameters, we developed an immune pathology-informed model (IPIM) that separated patients into 4 clusters (designated A-D) utilizing 4 radiomics features. The IPIM designation was significantly associated with overall survival in both training (5 year OS: 61%, 41%, 50%, and 91%, for clusters A-D, respectively, P = 0.04) and validation (5 year OS: 55%, 72%, 75%, and 86%, for clusters A-D, respectively, P = 0.002) cohorts and immune pathology (all P < 0.05). Specifically, we identified a favorable outcome group characterized by low CT intensity and high heterogeneity that exhibited low PDL1 and high CD3 infiltration, suggestive of a favorable immune activated state. We have developed a NSCLC radiomics signature based on the immune micro-environment and patient outcomes. This manuscript demonstrates model creation and validation in independent cohorts.

A Postreconstruction Harmonization Method for Multicenter Radiomic Studies in PET

Several reports have shown that radiomic features are affected by acquisition and reconstruction parameters, thus hampering multicenter studies. We propose a method that, by removing the center effect while preserving patient-specific effects, standardizes features measured from PET images obtained using different imaging protocols. Methods: Pretreatment ¹⁸F-FDG PET images of patients with breast cancer were included. In one nuclear medicine department (department A), 63 patients were scanned on a time-of-flight PET/CT scanner, and 16 lesions were triple-negative (TN). In another nuclear medicine department (department B), 74 patients underwent PET/CT on a different brand of scanner and a different reconstruction protocol, and 15 lesions were TN. The images from department A were smoothed using a gaussian filter to mimic data from a third department (department A-S). The primary lesion was segmented to obtain a lesion volume of interest (VOI), and a spheric VOI was set in healthy liver tissue. Three SUVs and 6 textural features were computed in all VOIs. A harmonization method initially described for genomic data was used to estimate the department effect based on the observed feature values. Feature distributions in each department were compared before and after harmonization. Results: In healthy liver tissue, the distributions significantly differed for 4 of 9 features between departments A and B and for 6 of 9 between departments A and A-S (P < 0.05, Wilcoxon test). After harmonization, none of the 9 feature distributions significantly differed between 2 departments (P > 0.1). The same trend was observed in lesions, with a realignment of feature distributions between the departments after harmonization. Identification of TN lesions was largely enhanced after harmonization when the cutoffs were determined on data from one department and applied to data from the other department. Conclusion: The proposed harmonization method is efficient at removing the multicenter effect for textural features and SUVs. The method is easy to use, retains biologic variations not related to a center effect, and does not require any feature recalculation. Such harmonization allows for multicenter studies and for external validation of radiomic models or cutoffs and should facilitate the use of radiomic models in clinical practice.

Computer-Aided Nodule Assessment and Risk Yield (CANARY) may facilitate non-invasive prediction of EGFR mutation status in lung adenocarcinomas

Computer-Aided Nodule Assessment and Risk Yield (CANARY) is quantitative imaging analysis software that predicts the histopathological classification and post-treatment disease-free survival of patients with adenocarcinoma of the lung. CANARY characterizes nodules by the distribution of nine color-coded texture-based exemplars. We hypothesize that quantitative computed tomography (CT) analysis of the tumor and tumor-free surrounding lung facilitates non-invasive identification of clinically-relevant mutations in lung adenocarcinoma. Comprehensive analysis of targetable mutations (50-gene-panel) and CANARY analysis of the preoperative (≤3 months) high resolution CT (HRCT) was performed for 118 pulmonary nodules of the adenocarcinoma spectrum surgically resected between 2006-2010. Logistic regression with stepwise variable selection was used to determine predictors of mutations. We identified 140 mutations in 106 of 118 nodules. TP53 (n = 48), KRAS (n = 47) and EGFR (n = 15) were the most prevalent. The combination of Y (Yellow) and G (Green) exemplars, fibrosis within the surrounding lung and smoking status were the best discriminators for an EGFR mutation (AUC 0.77 and 0.87, respectively). None of the EGFR mutants expressing TP53 (n = 5) had a good prognosis based on CANARY features. No quantitative features were significantly associated with KRAS mutations. Our exploratory analysis indicates that quantitative CT analysis of a nodule and surrounding lung may noninvasively predict the presence of EGFR mutations in pulmonary nodules of the adenocarcinoma spectrum.

Multiplexed imaging for diagnosis and therapy

Complex molecular and metabolic phenotypes depict cancers as a constellation of different diseases with common themes. Precision imaging of such phenotypes requires flexible and tunable modalities capable of identifying phenotypic fingerprints by using a restricted number of parameters while ensuring sensitivity to dynamic biological regulation. Common phenotypes can be detected by in vivo imaging technologies, and effectively define the emerging standards for disease classification and patient stratification in radiology. However, for the imaging data to accurately represent a complex fingerprint, the individual imaging parameters need to be measured and analysed in relation to their wider spatial and molecular context. In this respect, targeted palettes of molecular imaging probes facilitate the detection of heterogeneity in oncogene-driven alterations and their response to treatment, and lead to the expansion of rational-design elements for the combination of imaging experiments. In this Review, we evaluate criteria for conducting multiplexed imaging, and discuss its opportunities for improving patient diagnosis and the monitoring of therapy.

Associations between radiologist-defined semantic and automatically computed radiomic features in non-small cell lung cancer

Tumor phenotypes captured in computed tomography (CT) images can be described qualitatively and quantitatively using radiologist-defined "semantic" and computer-derived "radiomic" features, respectively. While both types of features have shown to be promising predictors of prognosis, the association between these groups of features remains unclear. We investigated the associations between semantic and radiomic features in CT images of 258 non-small cell lung adenocarcinomas. The tumor imaging phenotypes were described using 9 qualitative semantic features that were scored by radiologists, and 57 quantitative radiomic features that were automatically calculated using mathematical algorithms. Of the 9 semantic features, 3 were rated on a binary scale (cavitation, air bronchogram, and calcification) and 6 were rated on a categorical scale (texture, border definition, contour, lobulation, spiculation, and concavity). 32-41 radiomic features were associated with the binary semantic features (AUC = 0.56-0.76). The relationship between all radiomic features and the categorical semantic features ranged from weak to moderate (|Spearmen's correlation| = 0.002-0.65). There are associations between semantic and radiomic features, however the associations were not strong despite being significant. Our results indicate that radiomic features may capture distinct tumor phenotypes that fail to be perceived by naked eye that semantic features do not describe and vice versa.

Somatic Mutations Drive Distinct Imaging Phenotypes in Lung Cancer

Tumors are characterized by somatic mutations that drive biological processes ultimately reflected in tumor phenotype. With regard to radiographic phenotypes, generally unconnected through present understanding to the presence of specific mutations, artificial intelligence methods can automatically quantify phenotypic characters by using predefined, engineered algorithms or automatic deep-learning methods, a process also known as radiomics. Here we demonstrate how imaging phenotypes can be connected to somatic mutations through an integrated analysis of independent datasets of 763 lung adenocarcinoma patients with somatic mutation testing and engineered CT image analytics. We developed radiomic signatures capable of distinguishing between tumor genotypes in a discovery cohort (n = 353) and verified them in an independent validation cohort (n = 352). All radiomic signatures significantly outperformed conventional radiographic predictors (tumor volume and maximum diameter). We found a radiomic signature related to radiographic heterogeneity that successfully discriminated between EGFR⁺ and EGFR^- cases (AUC = 0.69). Combining this signature with a clinical model of EGFR status (AUC = 0.70) significantly improved prediction accuracy (AUC = 0.75). The highest performing signature was capable of distinguishing between EGFR⁺ and KRAS⁺ tumors (AUC = 0.80) and, when combined with a clinical model (AUC = 0.81), substantially improved its performance (AUC = 0.86). A KRAS⁺/KRAS^- radiomic signature also showed significant albeit lower performance (AUC = 0.63) and did not improve the accuracy of a clinical predictor of KRAS status. Our results argue that somatic mutations drive distinct radiographic phenotypes that can be predicted by radiomics. This work has implications for the use of imaging-based biomarkers in the clinic, as applied noninvasively, repeatedly, and at low cost. Cancer Res; 77(14); 3922-30. ©2017 AACR.

Harnessing Integrative Omics to Facilitate Molecular Imaging of the Human Epidermal Growth Factor Receptor Family for Precision Medicine

Cancer is a growing problem worldwide. The cause of death in cancer patients is often due to treatment-resistant metastatic disease. Many molecularly targeted anticancer drugs have been developed against 'oncogenic driver' pathways. However, these treatments are usually only effective in properly selected patients. Resistance to molecularly targeted drugs through selective pressure on acquired mutations or molecular rewiring can hinder their effectiveness. This review summarizes how molecular imaging techniques can potentially facilitate the optimal implementation of targeted agents. Using the human epidermal growth factor receptor (HER) family as a model in (pre)clinical studies, we illustrate how molecular imaging may be employed to characterize whole body target expression as well as monitor drug effectiveness and the emergence of tumor resistance. We further discuss how an integrative omics discovery platform could guide the selection of 'effect sensors' - new molecular imaging targets - which are dynamic markers that indicate treatment effectiveness or resistance.

Prediction of EGFR and KRAS mutation in non-small cell lung cancer using quantitative 18F FDG-PET/CT metrics

This study investigated the relationship between epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma viral oncogene homolog (KRAS) mutations in non-small-cell lung cancer (NSCLC) and quantitative FDG-PET/CT parameters including tumor heterogeneity. 131 patients with NSCLC underwent staging FDG-PET/CT followed by tumor resection and histopathological analysis that included testing for the EGFR and KRAS gene mutations. Patient and lesion characteristics, including smoking habits and FDG uptake parameters, were correlated to each gene mutation. Never-smoker (P < 0.001) or low pack-year smoking history (p = 0.002) and female gender (p = 0.047) were predictive factors for the presence of the EGFR mutations. Being a current or former smoker was a predictive factor for the KRAS mutations (p = 0.018). The maximum standardized uptake value (SUV_max) of FDG uptake in lung lesions was a predictive factor of the EGFR mutations (p = 0.029), while metabolic tumor volume and total lesion glycolysis were not predictive. Amongst several tumor heterogeneity metrics included in our analysis, inverse coefficient of variation (1/COV) was a predictive factor (p < 0.02) of EGFR mutations status, independent of metabolic tumor diameter. Multivariate analysis showed that being a never-smoker was the most significant factor (p < 0.001) for the EGFR mutations in lung cancer overall. The tumor heterogeneity metric 1/COV and SUV_max were both predictive for the EGFR mutations in NSCLC in a univariate analysis. Overall, smoking status was the most significant factor for the presence of the EGFR and KRAS mutations in lung cancer.

Radiological and Clinical Features associated with Epidermal Growth Factor Receptor Mutation Status of Exon 19 and 21 in Lung Adenocarcinoma

The exon 19 and 21 in Epidermal Growth Factor Receptor (EGFR) mutation are the most common subtype of lung adenocarcinoma, and the strongest predictive biomarker for progression-free survival and tumor response. Although some studies have shown differences in radiological features between cases with and without EFGR mutations, they lacked necessary stratification. This article is to evaluate the association of CT features between the wild type and the subtype (exon 19 and 21) of EGFR mutations in patients with lung adenocarcinoma. Of the 721 finally included patients, 132 were positive for EGFR mutation in exon 19, 140 were positive for EGFR mutation in exon 21, and 449 were EGFR wild type. EGFR mutation in exon 19 was associated with a small-maximum diameter (28.51 ± 14.07) (p < 0.0001); sex (p < 0.0001); pleural retraction (p = 0.0034); and the absence of fibrosis (p < 0.0001), while spiculated margins (p = 0.0095), subsolid density (p < 0.0001) and no smoking (p < 0.0001) were associated with EGFR mutation in exon 21. Receiver Operating Characteristic (ROC) curves suggested that the maximum Area Under the Curve (AUC) was related to the female gender (AUC = 0.636) and the absence of smoking (AUC = 0.681). This study demonstrated the radiological and clinical features could be used to prognosticate EGFR mutation subtypes in exon 19 and 21.

Relationship of Radiometabolic Biomarkers to KRAS Mutation Status and ALK Rearrangements in Cases of Lung Adenocarcinoma

Purpose Rapid diagnosis of genetic mutations is important for targeted therapies such as EGFR tyrosine kinase inhibitors. KRAS mutation and ALK rearrangement are also important in determining treatment. The purpose of our study was to evaluate the diagnostic value of 18F-FDG PET to predict KRAS mutation and ALK rearrangement in order to determine the frequency of these genetic markers in our lung adenocarcinoma cases and contribute to forthcoming meta-analysis studies. Methods A total of 218 patients with lung adenocarcinoma (EGFR analyzed) who were seen at our clinic between 2012 and 2014 were included in the study. The results of the 18 F-FDG-PET scans for each patient were retrospectively recorded with the associated medical documents. ALK rearrangements were analyzed in 166 of the 218 patients, while 50 of the 218 patients were analyzed for KRAS mutational status. SPSS 15.0 for Windows was used for statistical analysis. Results FDG avidity was higher in cases with KRAS mutations and ALK rearrangements than those without, but the difference was not significant. ALK rearrangements were more common in younger, female, and nonsmoking patients with lung adenocarcinoma. Conclusions The small numbers of KRAS mutations and ALK rearrangements are the limitation of this study for evaluation of diagnostic imaging. The frequency of these genetic alterations was as reported in the literature. We believe that our work will contribute to future meta-analysis.

Radiomic-Based Pathological Response Prediction from Primary Tumors and Lymph Nodes in NSCLC

INTRODUCTION

Noninvasive biomarkers that capture the total tumor burden could provide important complementary information for precision medicine to aid clinical decision making. We investigated the value of radiomic data extracted from pretreatment computed tomography images of the primary tumor and lymph nodes in predicting pathological response after neoadjuvant chemoradiation before surgery.

METHODS

A total of 85 patients with resectable locally advanced (stage II-III) NSCLC (median age 60.3 years, 65% female) treated from 2003 to 2013 were included in this institutional review board-approved study. Radiomics analysis was performed on 85 primary tumors and 178 lymph nodes to discriminate between pathological complete response (pCR) and gross residual disease (GRD). Twenty nonredundant and stable features (10 from each site) were evaluated by using the area under the curve (AUC) (all p values were corrected for multiple hypothesis testing). Classification performance of each feature set was evaluated by random forest and nested cross validation.

RESULTS

Three radiomic features (describing primary tumor sphericity and lymph node homogeneity) were significantly predictive of pCR with similar performances (all AUC = 0.67, p < 0.05). Two features (quantifying lymph node homogeneity) were predictive of GRD (AUC range 0.72-0.75, p < 0.05) and performed significantly better than the primary features (AUC = 0.62). Multivariate analysis showed that for pCR, the radiomic features set alone had the best-performing classification (median AUC = 0.68). Furthermore, for GRD classification, the combination of radiomic and clinical data significantly outperformed all other feature sets (median AUC = 0.73).

CONCLUSION

Lymph node phenotypic information was significantly predictive for pathological response and showed higher classification performance than radiomic features obtained from the primary tumor.