The impact of radiomics libraries and gray level discretization on the discovery of immunotherapy biomarkers in NSCLC patients.

OBJECTIVE: The influence of radiomics pipeline and the grey-level discretization on the discovery of immunotherapy biomarkers is still a poorly understood topic. This study is aimed at identifying robust features by comparing two radiomics libraries and their association with clinical outcomes in non-small cell lung cancer (NSCLC) patients treated with immune checkpoint inhibitors (ICIs). METHODS: A retrospective cohort of 164 NSCLC patients administered with ICIs was used in this study. Radiomic features were extracted from the pre-treatment CT scans. Univariate models were used to assess the association of radiomics features with progression free survival (PFS), PD-L1 and CD8 cell counts. We also examined the impact of gray-level discretization on feature robustness by evaluating the association of features with clinical endpoints. RESULTS: We extracted 1224, 441 radiomic features using Pyradiomics and RaCat, respectively, out of which 75 were common between them. We showed that the directionality of association between features and clinical endpoints is specific to the radiomic library used. Overall, more Pyradiomics and RaCat features were statistically associated with PFS, and PD-L1, respectively. We found intensity-based features to be more agnostic to the gray-level discretization parameters. Among features that showed significant correlation with PFS with varying gray-level discretization parameters, 45% were intensity-based, compared to PD-L1, and CD8. CONCLUSIONS: This study highlights the heterogeneity of radiomics libraries and the gray level discretization parameters that will impact the feature selection and predictive model development. Importantly, our work highlights the significance of selecting features that are agnostic to radiomics libraries for clinical translation. ADVANCES IN KNOWLEDGE: Our study emphasizes the need to select stable CT-derived handcrafted features to build immunotherapy biomarkers, which is a necessary precursor for multi-institutional validation of imaging biomarkers.

Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics.

BACKGROUND: Immune checkpoint inhibitors (ICIs) have emerged as one of the most promising first-line therapeutics in the management of non-small cell lung cancer (NSCLC). However, only a subset of these patients responds to ICIs, highlighting the clinical need to develop better predictive and prognostic biomarkers. This study will leverage pre-treatment imaging profiles to develop survival risk models for NSCLC patients treated with first-line immunotherapy. METHODS: Advanced NSCLC patients (n = 149) were retrospectively identified from two institutions who were treated with first-line ICIs. Radiomics features extracted from pretreatment imaging scans were used to build the predictive models for progression-free survival (PFS) and overall survival (OS). A compendium of five feature selection methods and seven machine learning approaches were utilized to build the survival risk models. The concordance index (C-index) was used to evaluate model performance. RESULTS: From our results, we found several combinations of machine learning algorithms and feature selection methods to achieve similar performance. K-nearest neighbourhood (KNN) with ReliefF (RL) feature selection was the best-performing model to predict PFS (C-index = 0.61 and 0.604 in discovery and validation cohorts), while XGBoost with Mutual Information (MI) feature selection was the best-performing model for OS (C-index = 0.7 and 0.655 in discovery and validation cohorts). CONCLUSION: The results of this study highlight the importance of implementing an appropriate feature selection method coupled with a machine learning strategy to develop robust survival models. With further validation of these models on external cohorts when available, this can have the potential to improve clinical decisions by systematically analyzing routine medical images.

The Cross-Scale Association between Pathomics and Radiomics Features in Immunotherapy-Treated NSCLC Patients: A Preliminary Study.

BACKGROUND: Recent advances in cancer biomarker development have led to a surge of distinct data modalities, such as medical imaging and histopathology. To develop predictive immunotherapy biomarkers, these modalities are leveraged independently, despite their orthogonality. This study aims to explore the cross-scale association between radiological scans and digitalized pathology images for immunotherapy-treated non-small cell lung cancer (NSCLC) patients. METHODS: This study involves 36 NSCLC patients who were treated with immunotherapy and for whom both radiology and pathology images were available. A total of 851 and 260 features were extracted from CT scans and cell density maps of histology images at different resolutions. We investigated the radiopathomics relationship and their association with clinical and biological endpoints. We used the Kolmogorov-Smirnov (KS) method to test the differences between the distributions of correlation coefficients with the two imaging modality features. Unsupervised clustering was done to identify which imaging modality captures poor and good survival patients. RESULTS: Our results demonstrated a significant correlation between cell density pathomics and radiomics features. Furthermore, we also found a varying distribution of correlation values between imaging-derived features and clinical endpoints. The KS test revealed that the two imaging feature distributions were different for PFS and CD8 counts, while similar for OS. In addition, clustering analysis resulted in significant differences in the two clusters generated from the radiomics and pathomics features with respect to patient survival and CD8 counts. CONCLUSION: The results of this study suggest a cross-scale association between CT scans and pathology H&E slides among ICI-treated patients. These relationships can be further explored to develop multimodal immunotherapy biomarkers to advance personalized lung cancer care.

Gene expression signature predicts radiation sensitivity in cell lines using the integral of dose-response curve.

BACKGROUND: Although substantial efforts have been made to build molecular biomarkers to predict radiation sensitivity, the ability to accurately stratify the patients is still limited. In this study, we aim to leverage large-scale radiogenomics datasets to build genomic predictors of radiation response using the integral of the radiation dose-response curve. METHODS: Two radiogenomics datasets consisting of 511 and 60 cancer cell lines were utilized to develop genomic predictors of radiation sensitivity. The intrinsic radiation sensitivity, defined as the integral of the dose-response curve (AUC) was used as the radioresponse variable. The biological determinants driving AUC and SF2 were compared using pathway analysis. To build the predictive model, the largest and smallest datasets consisting of 511 and 60 cancer cell lines were used as the discovery and validation cohorts, respectively, with AUC as the response variable. RESULTS: Utilizing a compendium of three pathway databases, we illustrated that integral of the radiobiological model provides a more comprehensive characterization of molecular processes underpinning radioresponse compared to SF2. Furthermore, more pathways were found to be unique to AUC than SF2-30, 288 and 38 in KEGG, REACTOME and WIKIPATHWAYS, respectively. Also, the leading-edge genes driving the biological pathways using AUC were unique and different compared to SF2. With regards to radiation sensitivity gene signature, we obtained a concordance index of 0.65 and 0.61 on the discovery and validation cohorts, respectively. CONCLUSION: We developed an integrated framework that quantifies the impact of physical radiation dose and the biological effect of radiation therapy in interventional pre-clinical model systems. With the availability of more data in the future, the clinical potential of this signature can be assessed, which will eventually provide a framework to integrate genomics into biologically-driven precision radiation oncology.

Imaging-Based Biomarkers Predict Programmed Death-Ligand 1 and Survival Outcomes in Advanced NSCLC Treated With Nivolumab and Pembrolizumab: A Multi-Institutional Study.

Background: Although the immune checkpoint inhibitors, nivolumab and pembrolizumab, were found to be promising in patients with advanced NSCLC, some of them either do not respond or have recurrence after an initial response. It is still unclear who will benefit from these therapies, and, hence, there is an unmet clinical need to build robust biomarkers. Methods: Patients with advanced NSCLC (N = 323) who were treated with pembrolizumab or nivolumab were retrospectively identified from two institutions. Radiomics features extracted from baseline pretreatment computed tomography scans along with the clinical variables were used to build the predictive models for overall survival (OS), progression-free survival (PFS), and programmed death-ligand 1 (PD-L1). To develop the imaging and integrative clinical-imaging predictive models, we used the XGBoost learning algorithm with ReliefF feature selection method and validated them in an independent cohort. The concordance index for OS, PFS, and area under the curve for PD-L1 was used to evaluate model performance. Results: We developed radiomics and the ensemble radiomics-clinical predictive models for OS, PFS, and PD-L1 expression. The concordance indices of the radiomics model were 0.60 and 0.61 for predicting OS and PFS and area under the curve was 0.61 for predicting PD-L1 in the validation cohort, respectively. The combined radiomics-clinical model resulted in higher performance with 0.65, 0.63, and 0.68 to predict OS, PFS, and PD-L1 in the validation cohort, respectively. Conclusions: We found that pretreatment computed tomography imaging along with clinical data can aid as predictive biomarkers for PD-L1 and survival end points. These imaging-driven approaches may prove useful to expand the therapeutic options for nonresponders and improve the selection of patients who would benefit from immune checkpoint inhibitors.

A Radiomics-Clinical Model Predicts Overall Survival of Non-Small Cell Lung Cancer Patients Treated with Immunotherapy: A Multicenter Study.

BACKGROUND: Immune checkpoint inhibitors (ICIs) are a great breakthrough in cancer treatments and provide improved long-term survival in a subset of non-small cell lung cancer (NSCLC) patients. However, prognostic and predictive biomarkers of immunotherapy still remain an unmet clinical need. In this work, we aim to leverage imaging data and clinical variables to develop survival risk models among advanced NSCLC patients treated with immunotherapy. METHODS: This retrospective study includes a total of 385 patients from two institutions who were treated with ICIs. Radiomics features extracted from pretreatment CT scans were used to build predictive models. The objectives were to predict overall survival (OS) along with building a classifier for short- and long-term survival groups. We employed the XGBoost learning method to build radiomics and integrated clinical-radiomics predictive models. Feature selection and model building were developed and validated on a multicenter cohort. RESULTS: We developed parsimonious models that were associated with OS and a classifier for short- and long-term survivor groups. The concordance indices (C-index) of the radiomics model were 0.61 and 0.57 to predict OS in the discovery and validation cohorts, respectively. While the area under the curve (AUC) values of the radiomic models for short- and long-term groups were found to be 0.65 and 0.58 in the discovery and validation cohorts. The accuracy of the combined radiomics-clinical model resulted in 0.63 and 0.62 to predict OS and in 0.77 and 0.62 to classify the survival groups in the discovery and validation cohorts, respectively. CONCLUSIONS: We developed and validated novel radiomics and integrated radiomics-clinical survival models among NSCLC patients treated with ICIs. This model has important translational implications, which can be used to identify a subset of patients who are not likely to benefit from immunotherapy. The developed imaging biomarkers may allow early prediction of low-group survivors, though additional validation of these radiomics models is warranted.

Radiomics approaches to predict PD-L1 and PFS in advanced non-small cell lung patients treated with immunotherapy: a multi-institutional study.

With the increasing use of immune checkpoint inhibitors (ICIs), there is an urgent need to identify biomarkers to stratify responders and non-responders using programmed death-ligand (PD-L1) expression, and to predict patient-specific outcomes such as progression free survival (PFS). The current study is aimed to determine the feasibility of building imaging-based predictive biomarkers for PD-L1 and PFS through systematically evaluating a combination of several machine learning algorithms with different feature selection methods. A retrospective, multicenter study of 385 advanced NSCLC patients amenable to ICIs was undertaken in two academic centers. Radiomic features extracted from pretreatment CT scans were used to build predictive models for PD-L1 and PFS (short-term vs. long-term survivors). We first employed the LASSO methodology followed by five feature selection methods and seven machine learning approaches to build the predictors. From our analyses, we found several combinations of feature selection methods and machine learning algorithms to achieve a similar performance. Logistic regression with ReliefF feature selection (AUC = 0.64, 0.59 in discovery and validation cohorts) and SVM with Anova F-test feature selection (AUC = 0.64, 0.63 in discovery and validation datasets) were the best-performing models to predict PD-L1 and PFS. This study elucidates the application of suitable feature selection approaches and machine learning algorithms to predict clinical endpoints using radiomics features. Through this study, we identified a subset of algorithms that should be considered in future investigations for building robust and clinically relevant predictive models.