Development and Evaluation of an Open-Source Software Package “CGITA” for Quantifying Tumor Heterogeneity with Molecular Images

Abstract

Background. The quantification of tumor heterogeneity with molecular images, by analyzing the local or global variation in the spatial arrangements of pixel intensity with texture analysis, possesses a great clinical potential for treatment planning and prognosis. To address the lack of available software for computing the tumor heterogeneity on the public domain, we develop a software package, namely, Chang-Gung Image Texture Analysis (CGITA) toolbox, and provide it to the research community as a free, open-source project. Methods. With a user-friendly graphical interface, CGITA provides users with an easy way to compute more than seventy heterogeneity indices. To test and demonstrate the usefulness of CGITA, we used a small cohort of eighteen locally advanced oral cavity (ORC) cancer patients treated with definitive radiotherapies. Results. In our case study of ORC data, we found that more than ten of the current implemented heterogeneity indices outperformed SUVmean for outcome prediction in the ROC analysis with a higher area under curve (AUC). Heterogeneity indices provide a better area under the curve up to 0.9 than the SUVmean and TLG (0.6 and 0.52, resp.). Conclusions. CGITA is a free and open-source software package to quantify tumor heterogeneity from molecular images. CGITA is available for free for academic use at http://code.google.com/p/cgita.

Characterization of PET/CT images using texture analysis: the past, the present… any future?

“…Several software distributions have also been made available [53, 54], but there is a need to ensure that all feature calculations are accurately implemented before they can be reliably used for research. Supplementary material section 4 contains a list of several such codes with associated remarks.…”

Assessing the performance of benign and malignant breast lesion classification with bilateral TIC differentiation and other effective features in DCE‐MRI

“…This set included 13 morphological features (roundness, compactness, max 3D diameter,…) to measure the 3D size and shape of the lesion, 31 statistical features (kurtosis, skewness, energy, …) to characterize the pixel intensities, and 53 textural features (gray‐level co‐occurrence matrix [GLCM], gray‐level run length [GLRL], …) to quantify the spatial pattern. These features are commonly employed in conventional analytic schemes …”

90Y-PET/CT Imaging Quantification for Dosimetry in Peptide Receptor Radionuclide Therapy: Analysis and Corrections of the Impairing Factors

“…The computation of tumor heterogeneity can be related to texture analysis that refers to mathematical methods to compute quantitative textural features from 2D or 3D images based on the spatial variation of voxel intensity. 26 In this study the phantom and tumor VOI heterogeneities were calculated and compared in a numerical form. Especially, inhomogeneity and asymmetry of the 3D-PET activity distributions in the VOI of the phantom and target patients were analyzed by the calculation of three different statistical parameters: fractional standard deviation (FSD), Skewness (SK), and Kurtosis (K).…”

“…The image texture elaboration was obtained by using the Chang-Gung Image Texture Analysis (CGITA_GUI) 26 based on Matlab software that is an open office source project hosted on the World Wide Web. Table 1 shows the results relative to the evaluation of CNR and MDA concentration in the phantom.…”

“…The texture analysis on the phantom and on clinical PET-imaging in terms of textural indexes was applied by using a mathematical algorithm that was based on the spatial variation of pixel intensity. 25,26 The aim of this study was to verify the possibility of using the information derived from PET data quantification for optimization of the administered radioactivity and the treatment response monitoring during the course of 90 Y-PRRT.…”