Homology‐based radiomic features for prediction of the prognosis of lung cancer based on CT‐based radiomics

Abstract

Purpose: Radiomics is a new technique that enables noninvasive prognostic prediction by extracting features from medical images. Homology is a concept used in many branches of algebra and topology that can quantify the contact degree. In the present study, we developed homology-based radiomic features to predict the prognosis of non-small-cell lung cancer (NSCLC) patients and then evaluated the accuracy of this prediction method. Methods: Four datasets were used: two to provide training and test data and two for the selection of robust radiomic features. All the datasets were downloaded from The Cancer Imaging Archive (TCIA). In two-dimensional cases, the Betti numbers consist of two values: b 0 (zero-dimensional Betti number), which is the number of isolated components, and b 1 (one-dimensional Betti number), which is the number of one-dimensional or "circular" holes. For homology-based evaluation, computed tomography (CT) images must be converted to binarized images in which each pixel has two possible values: 0 or 1. All CT slices of the gross tumor volume were used for calculating the homology histogram. First, by changing the threshold of the CT value (range: À150 to 300 HU) for all its slices, we developed homology-based histograms for b 0 , b 1 , and b 1 /b 0 using binarized images. All histograms were then summed, and the summed histogram was normalized by the number of slices. 144 homology-based radiomic features were defined from the histogram. To compare the standard radiomic features, 107 radiomic features were calculated using the standard radiomics technique.To clarify the prognostic power, the relationship between the values of the homology-based radiomic features and overall survival was evaluated using LASSO Cox regression model and the Kaplan-Meier method. The retained features with nonzero coefficients calculated by the LASSO Cox regression model were used for fitting the regression model. Moreover, these features were then integrated into a radiomics signature. An individualized rad score was calculated from a linear combination of the selected features, which were weighted by their respective coefficients. Results: When the patients in the training and test datasets were stratified into high-risk and low-risk groups according to the rad scores, the overall survival of the groups was significantly different. The C-index values for the homology-based features (rad score), standard features (rad score), and tumor size were 0.625, 0.603, and 0.607, respectively, for the training datasets and 0.689, 0.668, and 0.667 for the test datasets. This result showed that homology-based radiomic features had slightly higher prediction power than the standard radiomic features. Conclusions: Prediction performance using homology-based radiomic features had a comparable or slightly higher prediction power than standard radiomic features. These findings suggest that homology-based radiomic features may have great potential for improving the prognostic prediction accuracy of CT-based radiomics. In this result, i...

Robust radiogenomics approach to the identification of EGFR mutations among patients with NSCLC from three different countries using topologically invariant Betti numbers

“…Betti numbers (BNs), which are topological invariant in the homology, has been applied to quantify tumor traits in several medical images such as CT, magnetic resonance, and pathological images [13][14][15][16][17]. The topologically invariants in the BNs indicates unchangeable property of objects under continuous deformation [18].…”

Reliability as a Precondition for Trust—Segmentation Reliability Analysis of Radiomic Features Improves Survival Prediction

“…Other groups have worked on smaller datasets and reported comparable results on subsets of the data when using smaller numbers of segmentation outlines [ 18 , 26 , 27 ]. For the NSCLC dataset, Kadoya et al found a C-index of 0.625 for a multivariate radiomic feature model [ 28 ]. In contrast, Fu et al reported a C-Index of 0.67 when applying neural networks on the BRATS dataset [ 29 ], thereby indicating that deep learning-based approaches may achieve higher C-indices.…”

Impact of feature selection methods and subgroup factors on prognostic analysis with CT-based radiomics in non-small cell lung cancer patients

“…Feature Selection 1 (FS1) selects only robust features using test-retest and multiple segmentation [9,24]. The test-retest method uses a dataset created by Zhao et al to evaluate the variability of tumor unidimensional, bidimensional, and volumetric measurements on same-day repeat CT scans [25].…”

“…The test-retest method applies a radiomic analysis of tumors to two images of each patient and excludes features that significantly change over this short time as being less robust. The concordance correlation coefficient (CCC) served to evaluate the agreement between the values of two features, and feature selection was performed with CCC > 0.85 [24,27,28]. The multiple segmentation method uses a dataset created by van Baardwijk et al to investigate whether auto-delineation reduces the interobserver variability compared to manual PET-CT-based GTV delineation [29].…”

“…In addition, the intraclass correlation coefficient (ICC) Fig. 1 Overall scheme served to evaluate the agreement between the values of multiple features, and feature selection was performed with ICC > 0.8 [24,30]. In this study, we used 23 radiomic features selected in a previous study by Kadoya et al, who already performed test-retest and multiple segmentation using the abovementioned dataset and method [24].…”