Table 1: Overall grading accuracies for the supervised machine learning techniques used in our analysis. SVM classifiers clearly achieve significantly higher grading accuracy than the other methods. The data set includes 400 acinar structures.

Learning methodOverall grading accuracy (%)

Linear discriminant analysis80.75
Quadratic discriminant analysis80.00
Naïve Bayes69.75
𝐾 -nearest neighbors79.50
Support vector machines89.00