The test images are divided into three subsets. Images with: 11 a) low uncertainty 11 b) medium uncertainty and 11 c) high uncertainty. A dimensionality reduction of the images reveals that the images with low uncertainty (11 a) show clear distinction between the benign and malignant images. These are the images with low uncertainty are easily separable in low dimensions and the machine learning model is confident in classifying these images. Whereas the images with high uncertainty are randomly distributed in three dimensions (11 c). For medium uncertainty images, the images are clustered without a clear distinction of classes. Thus explaining the uncertainty quantified by the machine learning model.