“…Many feature extraction algorithms based on the GLCM have been proposed in the literature. For example, the GLCM model has been recently extended to three-dimensional space through the volumetric GLCM (VGLCM) [Tsai et al, 2007;Su et al, 2014;Su et al, 2015], which is specifically designed for multispectral or hyperspectral imagery. In addition to the classical GLCM, other techniques to extract spatial information have been proposed and tested in the literature, including Markov random fields [Lorette et al, 2000;Zhao et al, 2007], Gabor filters [Clausi and Deng, 2005;Bianconi and Fernández, 2007], fractals [Parrinello and Vaughan, 2002], Moran's I [Su et al, 2008] or wavelet [Myint et al, 2004;Huang and Zhang, 2012].…”
“…Many feature extraction algorithms based on the GLCM have been proposed in the literature. For example, the GLCM model has been recently extended to three-dimensional space through the volumetric GLCM (VGLCM) [Tsai et al, 2007;Su et al, 2014;Su et al, 2015], which is specifically designed for multispectral or hyperspectral imagery. In addition to the classical GLCM, other techniques to extract spatial information have been proposed and tested in the literature, including Markov random fields [Lorette et al, 2000;Zhao et al, 2007], Gabor filters [Clausi and Deng, 2005;Bianconi and Fernández, 2007], fractals [Parrinello and Vaughan, 2002], Moran's I [Su et al, 2008] or wavelet [Myint et al, 2004;Huang and Zhang, 2012].…”
“…This study therefore developed a systematic approach to extract high-order volumetric texture features based on 3D-GLCM (Tsai et al 2007) and GLCTF (Gray Level Co-occurrence Tensor Field) (Tsai and Lai 2013) computations for FW LiDAR data and integrate these spatial measures into waveform-based features for point cloud classification to improve land-cover identification. Several issues are addressed innovatively in this research, including (1) using a second derivative algorithm to detect echoes for extracting single-and multi-echo features derived from the Gaussian fitting function; (2) regularization of dense point clouds as a data cube for volumetric texture feature extraction; (3) comparing different waveform and texture feature combinations to evaluate the effectiveness of volumetric texture measures for FW LiDAR point cloud land-cover classification.…”
Section: Fw Lidar Processing and Analysismentioning
confidence: 99%
“…To address this issue, Tsai et al (2007) proposed a 3D semi-variance analysis to determine the appropriate kernel sizes for volumetric data sets. Semivariance, ( ) d c , describes the spatial variance using a unit pair of pixels or voxels with a lag of d in 2D or 3D space, defined as…”
“…As demonstrated in Tsai et al (2007), 3D-GL-CM utilizes second-order GLCM statistics but the process is performed in a 3D data cube. However, GLCTF extends the conventional GLCM to the third-order texture measure as a tensor field and requires voxel triplets for computation (Tsai and Lai 2013).…”
“…(11) to (14). More detailed description and discussions about the GLCTF computation, semi-variance analysis and texture measures can be found in various references (e.g., Clausi 2002;Tsai et al 2007;Warner 2011;Tsai and Lai 2013).…”
Full-Waveform (FW) Light Detection and Ranging (LiDAR) systems record the complete waveforms of backscattered laser signals, thus providing greater potential for extracting additional features and deriving physical properties from reflected laser signals. This study explores the feasibility of extracting volumetric texture features from airborne FW LiDAR point cloud data along with echo-based LiDAR features to improve land-cover classification. A second derivative algorithm is used to detect signal echoes and extract single-and multi-echo features from FW LiDAR data derived from Gaussian fitting function. The dense point clouds are further regularized to construct a data cube for volumetric texture extractions using 3D-GLCM (Gray Level Co-occurrence Matrix) and Gray Level Co-occurrence Tensor Field (GLCTF) algorithms coupled with second and third order texture descriptors. Different feature combinations of traditional and echo-based LiDAR features and texture measures are collected for supervised land-cover classification using a Random Forests classifier. The experimental results indicate that the echo-based features may be useful for distinguishing general land-cover types with acceptable accuracy but may not be adequate for detailed classifications, such as discriminating different vegetation cover types. Incorporating volumetric texture features can improve the classification of relatively more detailed land-cover types with an approximate 10 and 14% increase in the overall accuracy and Kappa coefficient, respectively.
Purpose: To explore the association between magnetic resonance imaging (MRI), including Haralick textural features, and biochemical recurrence following prostate cancer radiotherapy. Materials and Methods: In all, 74 patients with peripheral zone localized prostate adenocarcinoma underwent pretreatment 3.0T MRI before external beam radiotherapy. Median follow-up of 47 months revealed 11 patients with biochemical recurrence. Prostate tumors were segmented on T 2 -weighted sequences (T 2 -w) and contours were propagated onto the coregistered apparent diffusion coefficient (ADC) images. We extracted 140 image features from normalized T 2 -w and ADC images corresponding to first-order (n 5 6), gradient-based (n 5 4), and second-order Haralick textural features (n 5 130). Four geometrical features (tumor diameter, perimeter, area, and volume) were also computed. Correlations between Gleason score and MRI features were assessed. Cox regression analysis and random survival forests (RSF) were performed to assess the association between MRI features and biochemical recurrence. Results: Three T 2 -w and one ADC Haralick textural features were significantly correlated with Gleason score (P < 0.05). Twenty-eight T 2 -w Haralick features and all four geometrical features were significantly associated with biochemical recurrence (P < 0.05). The most relevant features were Haralick features T 2 -w contrast, T 2 -w difference variance, ADC median, along with tumor volume and tumor area (C-index from 0.76 to 0.82; P < 0.05). By combining these most powerful features in an RSF model, the obtained C-index was 0.90. Conclusion: T 2 -w Haralick features appear to be strongly associated with biochemical recurrence following prostate cancer radiotherapy. Level of Evidence: 3
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.