Skip to main content
. 2023 Jun 19;128(8):989–998. doi: 10.1007/s11547-023-01657-y

Fig. 3.

Fig. 3

True negative (a, correctly classified lipoma), false positive (b, lipoma misdiagnosed as ALT) and true positive (c, correctly classified ALT) according to both radiomics-based machine learning and qualitative assessment performed by the radiologist. In (a), correctly classified lipoma shows homogeneous signal with complete fat suppression. Intralesional septations are seen in correctly classified ALT (c) but also lipoma misdiagnosed as ALT (b). Fat-suppressed T2-weighted sequences were used only for qualitative assessment performed by the radiologist. Radiomics-based machine learning analysis included T1- and T2-weighted sequences without fat suppression