Figure 4 AUCs of SVM applied to kinetic and morphological features, separately.
The proposed MCS combines the results of two classifiers trained with dynamic and morphological features separately.
The proposed MCS combines the results of two classifiers trained and tested using dynamic and morphological features separately.
In our previous studies [18, 20] we analysed the performance of several classifiers (multilayer perceptron, support vector machine, Bayes classifier decision tree), in conjunction with dynamic and morphological features, separately using a ROI manual selection slice by slice.
In conclusion, we proposed an MCS to classify breast lesions on DCE-MRI combining the results of two classifiers tested with morphological features and dynamic information separately.
Overall survival (OS) and cause-specific survival (CSS) following diagnosis were estimated based on the Kaplan Meier method, overall and separately for morphological features.
The proposed MCS combines the results of two classifiers trained separately with dynamic and morphological features, respectively (Fig. 2).
For each ROI, totally forty four features, including six histogram, MRF, three Tamura, seven GLRLN and twenty two GLCM features are extracted separately along with five morphological features.
However, our results proved that, although a single classifier trained separately with dynamic and morphological features achieves a low overall accuracy, the MCS could optimise the correct classification rate: dynamic features with the decision tree gave 60% accuracy, morphological features with the Bayes classifier gave 80% accuracy, and the MCS gave 91.7% accuracy.
Recent studies have attempted to take advantage of morphological features and dynamic information: dynamic and morphological data, generally separately, have been used both for segmentation of volume of interests (VOIs) [7, 8, 9, 10, 11] and for lesion classification [6, 7, 8, 9, 10, 11, 12, 13, 14, 15].
Multiple clones in the same tumor mass, which can often be distinguished by morphological features, would yield more information if they could be microdissected and analyzed separately.
