Radiomics of Lung Nodules: A Multi-Institutional Study of Robustness and Agreement of Quantitative Imaging Features
| Autor: | Jayashree Kalpathy-Cramer, Lubomir M. Hadjiiski, Jessica C. Sieren, Sandy Napel, Johanna Uthoff, Brandon Driscoll, Dmitry B. Goldgof, Sebastian Echegaray, Yoganand Balagurunathan, Pechin Lo, Artem Mamomov, Robert J. Gillies, Samantha K. N. Dilger, Binsheng Zhao, Dmitry Cherezov, Michael F. McNitt-Gray, Kenny H. Cha, Lin Lu, Ivan Yeung, Daniel L. Rubin |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2016 |
| Předmět: |
Pathology
medicine.medical_specialty Computer science Concordance Physics::Medical Physics ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Stability (learning theory) Article imaging features 030218 nuclear medicine & medical imaging Correlation 03 medical and health sciences 0302 clinical medicine Wavelet Margin (machine learning) medicine Radiology Nuclear Medicine and imaging Segmentation Graphical model radiomics reproducibility lung cancer Cancer business.industry Pattern recognition Good Health and Well Being ComputingMethodologies_PATTERNRECOGNITION Feature (computer vision) 030220 oncology & carcinogenesis Computer Science::Computer Vision and Pattern Recognition Biomedical Imaging Artificial intelligence business |
| Zdroj: | Tomography : a journal for imaging research Tomography Volume 2 Issue 4 Pages 430-437 Tomography (Ann Arbor, Mich.), vol 2, iss 4 Tomography; Volume 2; Issue 4; Pages: 430-437 |
| ISSN: | 2379-1381 |
| Popis: | Radiomics is to provide quantitative descriptors of normal and abnormal tissues during classification and prediction tasks in radiology and oncology. Quantitative Imaging Network members are developing radiomic “feature” sets to characterize tumors, in general, the size, shape, texture, intensity, margin, and other aspects of the imaging features of nodules and lesions. Efforts are ongoing for developing an ontology to describe radiomic features for lung nodules, with the main classes consisting of size, local and global shape descriptors, margin, intensity, and texture-based features, which are based on wavelets, Laplacian of Gaussians, Law's features, gray-level co-occurrence matrices, and run-length features. The purpose of this study is to investigate the sensitivity of quantitative descriptors of pulmonary nodules to segmentations and to illustrate comparisons across different feature types and features computed by different implementations of feature extraction algorithms. We calculated the concordance correlation coefficients of the features as a measure of their stability with the underlying segmentation 68% of the 830 features in this study had a concordance CC of ≥0.75. Pairwise correlation coefficients between pairs of features were used to uncover associations between features, particularly as measured by different participants. A graphical model approach was used to enumerate the number of uncorrelated feature groups at given thresholds of correlation. At a threshold of 0.75 and 0.95, there were 75 and 246 subgroups, respectively, providing a measure for the features' redundancy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|