Association of pre-treatment radiomic features with lung cancer recurrence following stereotactic body radiation therapy

Abstract

The purpose of this work was to investigate the potential relationship between radiomic features extracted from pre-treatment x-ray CT images and clinical outcomes following stereotactic body radiation therapy (SBRT) for non-small-cell lung cancer (NSCLC). Seventy patients who received SBRT for stage-1 NSCLC were retrospectively identified. The tumor was contoured on pre-treatment free-breathing CT images, from which 43 quantitative radiomic features were extracted to collectively capture tumor morphology, intensity, fine-texture, and coarse-texture. Treatment failure was defined based on cancer recurrence, local cancer recurrence, and non-local cancer recurrence following SBRT. The univariate association between each radiomic feature and each clinical endpoint was analyzed using Welch's t-test, and p-values were corrected for multiple hypothesis testing. Multivariate associations were based on regularized logistic regression with a singular value decomposition to reduce the dimensionality of the radiomics data. Two features demonstrated a statistically significant association with local failure: Homogeneity2 (p = 0.022) and Long-Run-High-Gray-Level-Emphasis (p = 0.048). These results indicate that relatively dense tumors with a homogenous coarse texture might be linked to higher rates of local recurrence. Multivariable logistic regression models produced maximum AUC values of 0.72 ± 0.04, 0.83 ± 0.03, and 0.60 ± 0.04, for the recurrence, local recurrence, and non-local recurrence endpoints, respectively. The CT-based radiomic features used in this study may be more associated with local failure than non-local failure following SBRT for stage I NSCLC. This finding is supported by both univariate and multivariate analyses.

Artificial intelligence in radiation oncology treatment planning: a brief overview

“…Radiomics features are a promising additional data type for oncologic outcome prediction and tumor control probability models (76). Multiple manuscripts have been published using radiomics to predict radiation response, in some cases with prediction power outperforming standard clinical variables (77)(78)(79)(80)(81)(82), though not in all (83). Radiomicsbased statistical approaches can predict various radiation normal tissue complication probabilities including radiation pneumonitis, xerostomia, and rectal wall toxicity (84)(85)(86)(87)(88)(89).…”

Application and limitation of radiomics approach to prognostic prediction for lung stereotactic body radiotherapy using breath‐hold CT images with random survival forest: A multi‐institutional study

“…Recent radiomics studies have shown that pretreatment CT-based radiomic features are prognostic for overall survival, LR, or DM. [20][21][22][23] Although several studies have employed a radiomics Medical Physics, 47 (9), September 2020 approach using free-breathing CT images, it is necessary to minimize the impact of tumor motion using the gated or breath-hold CT approach to extract generalizable and robust radiomic features. [24][25][26][27] Most radiomics analyses of LR or DM are performed using the Kaplan-Meier method.…”

“…29 Most studies also have limitations in terms of the small number of patient datasets and single institutions. [20][21][22][23] To date, prognostic prediction in multiple institutions applying a machine learning approach such as random survival forest (RSF) to assess competing risks with optimal hyper-parameter tuning via cross-validation lacks sufficient literature. Random survival forest is a machine learning algorithm that provides high prediction accuracy with nonlinear regression and makes it easier to understand the feature importance as a white box.…”

Comparison of radiomic features in diagnostic CT images with and without contrast enhancement in the delayed phase for NSCLC patients

“…Recently, radiomics has enabled the extraction of a large set of quantitative features from medical images, useful for predicting clinical outcomes in cancer patients [3][4][5]. Radiomic features extracted from treatment planning computed tomography (CT) images may be useful for the prognostic prediction of SBRT for lung cancer [6][7][8][9][10]. Radiomics in lung cancer has also been performed using diagnostic CT images for feature extraction [11][12][13][14][15].…”