Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network

Table 1

A summary of brain tumor segmentation methods based on traditional machine learning. Only methods using MRI data were included in this table.

Number	Publication	Database	Summary of method	Performance
1	Corso et al. [5]	20 cases of in vivo brain tumors; T1, T1-C, T2, FLAIR	A hybrid method combining an affinity-based segmentation method with a generative model	0.62–0.69 (Jaccard)
2	Hamamci et al. [6]	Synthetic data from Utah + in vivo data from Harvard	A cellular automata method combining a probability framework	0.72 (DICE complete tumor)
3	Mehmood et al. [7]	BrainWeb data + in vivo brain tumors; T1, T1-weighted, T2, T2-weighted	A novel saliency model for lesion localization and an N-cut graph segmentation model for classification	83%~95% (classification accuracy)
4	Havaei et al. [8]	MICCAI-BRATS 2013 dataset	Hand-crafted features + a support vector machine	0.86 (DICE complete tumor)
5	Usman and Rajpoot [9]	MICCAI-BRATS 2013 dataset	Automated wavelet-based features + a random forest classifier	0.88 (DICE complete tumor)
6	Tustison et al. [10]	MICCAI-BRATS 2013 dataset	Combine a random forest model with a framework of regularized probabilistic segmentation	0.88 (DICE complete tumor)
7	Zikic et al. [11]	40 multichannel MR images, including DTI	Decision forests using context-aware spatial features for automatic segmentation of high-grade gliomas	GT: 0.89; NE: 0.70	AC: 0.84; E: 0.72
				(10/30 tests)
8	Pinto et al. [12]	MICCAI-BRATS 2013 dataset	Using appearance- and context-based features to feed an extremely randomized forest	0.83 (DICE complete tumor)
9	Bauer et al. [13]	10 multispectral patient datasets	Combines support vector machine classification with conditional random fields	GT: 0.84; AC: 0.84	NE: 0.70; E: 0.72
				(Intrapatient regularized)