Shan Huang1, Yuan Li1, Ke Shi1, Yi Zhang1, Ying-kun Guo2, and Zhi-gang Yang1
1Radiology, West China Hospital, Chengdu, China, 2Radiology, West China Second University Hospital, Chengdu, China
1Radiology, West China Hospital, Chengdu, China, 2Radiology, West China Second University Hospital, Chengdu, China
Texture analysis was feasible and reproducible for
detecting myocardial tissue alterations on T2-weighted images. Our radiomics
model had a great performance in differentiating between CA and HCM patients,
which was comparable to LGE.
Figure1 Feature selection and dimension reduction process.
ICC: intraclass correlation coefficient, LASSO: the least absolute shrinkage and selection operator.
Figure 2 Correlogram of the relationship among the selected texture features.
Smaller and/or lighter circles represent lower correlation. On the contrary, larger and/or darker circles indicate higher correlation. GLRLM: gray level run length matrix, GLDM: gray level dependence matrix, GLCM: gray level co-occurrence matrix; LRE: Long Run Emphasis; SRE: Short Run Emphasis; SDHGLE: Small Dependence High Gray Level Emphasis; LDE: Large Dependence Emphasis; H: high wavelet filter; L: low wavelet filter