Skip to main content
. 2022 Aug 17;13:137. doi: 10.1186/s13244-022-01276-7

Fig. 3.

Fig. 3

Predicted vs. target Dice values of the baseline CatBoost model, which only uses clinical variables to predict segmentation quality. The dotted line indicates perfect x = y predictions. The predictions of this model tend to only vary minimally (very close to the naïve model), suggesting that the clinical variables are not indicative of segmentation performance