matRadiomics: A Novel and Complete Radiomics Framework, from Image Visualization to Predictive Model

Abstract

Radiomics aims to support clinical decisions through its workflow, which is divided into: (i) target identification and segmentation, (ii) feature extraction, (iii) feature selection, and (iv) model fitting. Many radiomics tools were developed to fulfill the steps mentioned above. However, to date, users must switch different software to complete the radiomics workflow. To address this issue, we developed a new free and user-friendly radiomics framework, namely matRadiomics, which allows the user: (i) to import and inspect biomedical images, (ii) to identify and segment the target, (iii) to extract the features, (iv) to reduce and select them, and (v) to build a predictive model using machine learning algorithms. As a result, biomedical images can be visualized and segmented and, through the integration of Pyradiomics into matRadiomics, radiomic features can be extracted. These features can be selected using a hybrid descriptive–inferential method, and, consequently, used to train three different classifiers: linear discriminant analysis, k-nearest neighbors, and support vector machines. Model validation is performed using k-fold cross-Validation and k-fold stratified cross-validation. Finally, the performance metrics of each model are shown in the graphical interface of matRadiomics. In this study, we discuss the workflow, architecture, application, future development of matRadiomics, and demonstrate its working principles in a real case study with the aim of establishing a reference standard for the whole radiomics analysis, starting from the image visualization up to the predictive model implementation.

An exploratory study of CT radiomics using differential network feature selection for WHO/ISUP grading and progression-free survival prediction of clear cell renal cell carcinoma

“…Differences in scanner models should be verified as the dataset collected comes from two scanners. Thus, principal component analysis (PCA) was performed on the extracted features to plot data in the space of reduced dimensions ( 26 ). Visual inspection of Supplement Figure 1 suggests the absence of batch effects.…”

CT-based machine learning radiomics predicts CCR5 expression level and survival in ovarian cancer

“…Before feature selection, data were centered and scaled, implemented by the preProcess function from the R caret (Classification And Regression Training) package. As explained and reported in previous research [ 34 ], a Principal Component Analysis (PCA) was performed on the extracted features to plot data in a space of reduced dimensions (Supplemental Figure 8 ). The radiomics features of the two devices were similar.…”

“…Manufacturer: GE, SIEMENS X-ray tube current: median 259.0 mA X-ray tube voltage: median 120 kVp Slice thickness: median 5.0mm Exposure_Times: median 828ms Pixel spacing: median 0.742×0.742mm2 Contrast: Optiray 350, Isovue 370 Before feature selection, data were centered and scaled, implemented by the preProcess function from the R caret (Classification And Regression Training) package. As explained and reported in previous research [34], a Principal Component Analysis (PCA) was performed on the extracted features to plot data in a space of reduced dimensions (Supplemental Figure 8). The radiomics features of the two devices were similar.…”

Demystifying Supervised Learning in Healthcare 4.0: A New Reality of Transforming Diagnostic Medicine

“…Since these techniques involve the injection of certain radioactive elements such as FGD, tissues with high metabolic rates are highlighted. This helps in the easier detection of cancer cells [ 132 ]. These features can be better explained with software such as Pyradiomics [ 133 ] and LifeX [ 134 ].…”