Exploratory Study to Identify Radiomics Classifiers for Lung Cancer Histology

Abstract

BackgroundRadiomics can quantify tumor phenotypic characteristics non-invasively by applying feature algorithms to medical imaging data. In this study of lung cancer patients, we investigated the association between radiomic features and the tumor histologic subtypes (adenocarcinoma and squamous cell carcinoma). Furthermore, in order to predict histologic subtypes, we employed machine-learning methods and independently evaluated their prediction performance.MethodsTwo independent radiomic cohorts with a combined size of 350 patients were included in our analysis. A total of 440 radiomic features were extracted from the segmented tumor volumes of pretreatment CT images. These radiomic features quantify tumor phenotypic characteristics on medical images using tumor shape and size, intensity statistics, and texture. Univariate analysis was performed to assess each feature’s association with the histological subtypes. In our multivariate analysis, we investigated 24 feature selection methods and 3 classification methods for histology prediction. Multivariate models were trained on the training cohort and their performance was evaluated on the independent validation cohort using the area under ROC curve (AUC). Histology was determined from surgical specimen.ResultsIn our univariate analysis, we observed that fifty-three radiomic features were significantly associated with tumor histology. In multivariate analysis, feature selection methods ReliefF and its variants showed higher prediction accuracy as compared to other methods. We found that Naive Baye’s classifier outperforms other classifiers and achieved the highest AUC (0.72; p-value = 2.3 × 10−7) with five features: Stats_min, Wavelet_HLL_rlgl_lowGrayLevelRunEmphasis, Wavelet_HHL_stats_median, Wavelet_HLL_stats_skewness, and Wavelet_HLH_glcm_clusShade.ConclusionHistological subtypes can influence the choice of a treatment/therapy for lung cancer patients. We observed that radiomic features show significant association with the lung tumor histology. Moreover, radiomics-based multivariate classifiers were independently validated for the prediction of histological subtypes. Despite achieving lower than optimal prediction accuracy (AUC 0.72), our analysis highlights the impressive potential of non-invasive and cost-effective radiomics for precision medicine. Further research in this direction could lead us to optimal performance and therefore to clinical applicability, which could enhance the efficiency and efficacy of cancer care.

Hybrid Imaging: Instrumentation and Data Processing

“…ML holds also a great potential for dealing with "big data" generated by hybrid imaging methods [280]. For example, ML has been successfully applied in hybrid imaging to predict survival [283], treatment outcome [284], and tumor grading [285]. Furthermore, unsupervised ML allows the identification of breast cancer subtypes [286].…”

Personalizing Medicine Through Hybrid Imaging and Medical Big Data Analysis

“…Accordingly, promising results in the field of treatment outcome [161], therapy response [156,162], survival [163][164][165][166] as well prognostic stratification [167] have been proposed. Several studies perform conventional correlation analysis [156,160,165,168,169], as well as robust machine learning evaluation [10,170,171] of textural features to characterize tumors in vivo. An oncological review of PET-based radiomic approaches concluded that it is a promising method for personalized medicine as it can enhance cancer management [172].…”

Artificial intelligence in radiology

“…Within oncology, multiple efforts have successfully explored radiomics tools for assisting clinical decision making related to the diagnosis and risk stratification of different cancers 15,16 . For example, studies in non-small-cell lung cancer (NSCLC) used radiomics to predict distant metastasis in lung adenocarcinoma 17 and tumour histological subtypes 18 as well as disease recurrence 19 , somatic mutations 20 , gene-expression profiles 21 and overall survival 22 . Such findings have motivated an exploration of the clinical utility of AI-generated biomarkers based on standard-of-care radiographic images 23 — with the ultimate hope of better supporting radiologists in disease diagnosis, imaging quality optimization, data visualization, response assessment and report generation.…”