Table 1.

Some of the symbols and their definitions in this chapter.

Symbol	Paraphrase
x i	The i-th training sample
y i	The i-th output samples
X 1, X2	Original data set
P s1	The output probability when the original data is X1 input to the student model
P t2	The output probability when the original data is X2 input to the teacher model
l	Loss value
L 1	Cross-entropy loss function
L 2	Relative entropy loss function
L	Total loss function
g	Grayscale value
X = {x1, x2, ⋯, xn}	The feature point of each pixel on the probability map
Y = {y1, y2, ⋯, yn}	Probability prediction label for each point.
T	Algorithm threshold
GT	Real osteosarcoma area
P os	Predict the area of osteosarcoma
S os	The area of the tumor area of osteosarcoma