Fig. 2: Nuclear pleomorphism predictions quantized into different numbers of categories, sorted from low pleomorphism to high in each category, from left to right.
From: Deep learning for fully-automated nuclear pleomorphism scoring in breast cancer
In a, patches were quantized into three categories, which was in line with the three-category classification in routine clinical practice, whereas in b, the patches were quantized into five categories to demonstrate the continuity of the nuclear pleomorphism spectrum from the predictions of the AI algorithm.
