Fig. 3 | Scientific Reports

Fig. 3

From: Machine learning method based on radiomics help differentiate posterior pituitary tumors from pituitary neuroendocrine tumors and craniopharyngioma

Fig. 3

The most predictive features. The top half of the image is a heat map of the nine most predictive features. The values of the features were normalized using min–max normalization, and are represented by white to blue (0–1). In the bottom half of the image shows the difference between of these features between the posterior pituitary tumors (PPTs) and the non- posterior pituitary tumors (NPPTs).

Back to article page