Skip to main content
Fig. 2 | BMC Medical Imaging

Fig. 2

From: 18F‑FDG PET/CT based radiomics features improve prediction of prognosis: multiple machine learning algorithms and multimodality applications for multiple myeloma

Fig. 2

A heatmap illustrates correlation coefficient among the finalized features from PET, CT, and clinical parameters. #PET_FEATURE_1: wavelet.LLL_firstorder_10Percentile. #PET_FEATURE_2: exponential_glcm_InverseVariance. #PET_FEATURE_3: lbp.2D_firstorder_InterquartileRange. #PET_FEATURE_4: lbp.3D.k_glcm_MCC. #PET_FEATURE_5: original_shape_MajorAxisLength. #CT_FEATURE_1: original_shape_MinorAxisLength. #CT_FEATURE_2: original_ngtdm_Busyness. #CT_FEATURE_3: exponential_glszm_SmallAreaLowGrayLevelEmphasis. #CT_FEATURE_4: wavelet.HLH_gldm_SmallDependenceEmphasis

Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us