Novel Image Analysis Approach Quantifies Morphological Characteristics of 3D Breast Culture Acini with Varying Metastatic Potentials

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 method	Overall grading accuracy (%)
Linear discriminant analysis	80.75
Quadratic discriminant analysis	80.00
Naïve Bayes	69.75
𝐾-nearest neighbors	79.50
Support vector machines	89.00