Research Paper Volume 13, Issue 9 pp 12833—12848

Predicting intraventricular hemorrhage growth with a machine learning-based, radiomics-clinical model

Representative illustration of new IVH, IVH expansion, and manual region of interest (ROI) segmentation. Images (A, B) are non-contrast CT images (axial view) of a 54-year-old male who experienced a new IVH. There was no baseline IVH (A), but the hematoma broke into ventricles on the follow-up CT (B). Images (C, D) are non-contrast CT images (axial view) of a 68-year-old female who experienced IVH expansion; (C) shows an initial IVH with a volume of 2.53 mL; follow-up CT (D) shows that the volume of IVH increased to 22.31 mL within 72 h.

Figure 5. Representative illustration of new IVH, IVH expansion, and manual region of interest (ROI) segmentation. Images (A, B) are non-contrast CT images (axial view) of a 54-year-old male who experienced a new IVH. There was no baseline IVH (A), but the hematoma broke into ventricles on the follow-up CT (B). Images (C, D) are non-contrast CT images (axial view) of a 68-year-old female who experienced IVH expansion; (C) shows an initial IVH with a volume of 2.53 mL; follow-up CT (D) shows that the volume of IVH increased to 22.31 mL within 72 h.