Abstract
Radiomics is rapidly advancing in precision diagnostics and cancer treatment. However, there are several challenges that need to be addressed before translation to clinical use. This study presents an ad-hoc weighted statistical framework to explore radiomic biomarkers for a better characterization of the radiogenomic phenotypes in breast cancer. Thirty-six female patients with breast cancer were enrolled in this study. Radiomic features were extracted from MRI and PET imaging techniques for malignant and healthy lesions in each patient. To reduce within-subject bias, the ratio of radiomic features extracted from both lesions was calculated for each patient. Radiomic features were further normalized, comparing the z-score, quantile, and whitening normalization methods to reduce between-subjects bias. After feature reduction by Spearman’s correlation, a methodological approach based on a principal component analysis (PCA) was applied. The results were compared and validated on twenty-seven patients to investigate the tumor grade, Ki-67 index, and molecular cancer subtypes using classification methods (LogitBoost, random forest, and linear discriminant analysis). The classification techniques achieved high area-under-the-curve values with one PC that was calculated by normalizing the radiomic features via the quantile method. This pilot study helped us to establish a robust framework of analysis to generate a combined radiomic signature, which may lead to more precise breast cancer prognosis.
Highlights
Radiomics has been widely used in tumor research
The main goal of this study is to provide a multivariate statistical framework via principal component analysis (PCA) to generate a complex quantitative radiomic signature, which may lead to more precise breast cancer prognosis and help clinicians in decision-making towards personalized medicine
random forest decision trees (RF) was not considered to be the best classification even though it presented higher area under the curve (AUC) than linear discriminant analysis (LDA) because it performed very poorly on the detection of Luminal A patients (24% specificity). This pilot study established a robust framework of analysis to evaluate quantitative imaging biomarkers and to generate a combined radiomic signature for a more precise breast cancer prognosis, investigating the effect of within-subject and between-subjects normalization methods on PCA and downstream analysis
Summary
Radiomics has been widely used in tumor research. The enormous advantage of radiomics is the automatic extraction of high-dimensional features from digitally encrypted medical images that hold information related to tumor pathophysiology, which can later be mined and analyzed for decision support [1,2,3,4].Radiomics can support the characterization of tumor heterogeneity from macroscopic images and may provide insights in precision medicine related to tumor detection and subtype classification along with molecular analyses [4,5,6,7].Breast cancer is the most common malignant tumor in females [8]. The enormous advantage of radiomics is the automatic extraction of high-dimensional features from digitally encrypted medical images that hold information related to tumor pathophysiology, which can later be mined and analyzed for decision support [1,2,3,4]. Radiomics can support the characterization of tumor heterogeneity from macroscopic images and may provide insights in precision medicine related to tumor detection and subtype classification along with molecular analyses [4,5,6,7]. The histologic grade (grades 1, 2, and 3) is used to determine the aggressiveness of a tumor. It provides prognostic information in many tumors, including breast cancer [11]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
