Table 4.

Deep learning approaches for quantification of brain lesions

Authors	Aim	CNN Style	Dim	Accuracy	Dataset
Havaei et al. 2016 [26]	Tumor segmentation	Patch-wise	2D	DSC 0.88 (complete), 0.79 (core), 0.73 (enhancing)	BRATS-2013
S. Pereira et al. 2016 [22]	Tumor segmentation	Patch-wise	2D	DSC 0.88 (complete), 0.83 (core), 0.77 (enhancing)	BRATS-2013
Zhao and Jia 2015 [53]	Tumor segmentation	Patch-wise	2D	Overall accuracy 0.81	BRATS-2013
Kamnitsas et al. 2016 [21]	Tumor segmentation	Patch-wise	3D	DSC 0.9 (complete), 0.75 (core), 0.73 (enhancing)	BRATS-2015
Dvorak et al. 2015 [54]	Tumor segmentation	Patch-wise	2D	DSC 0.83 (complete), 0.75 (core), 0.77 (enhancing)	BRATS-2014
Brosch et al. 2016 [31]	MS segmentation	Semantic-wise	3D	DSC 0.68 (ISBI); DSC 0.84 (MICCAI)	MICCAI 2008-ISBI 2015
Dou et al. 2016 [32]	Cerebral microbleed detection	Cascaded (semantic/patch-wise)	3D	Sensitivity 98.29%	Private data (320 subjects)
Maier et al. 2015 [55]	Ischemic stroke detection	Patch-wise	2D	DSC 0.67 ± 0.18; HD 29.64 ± 24.6	Private data (37 subjects)
Akkus et al. 2016 [29]	Tumor genomic prediction	Patch-wise	2D	0.93 (sensitivity), 0.82 (specificity), and 0.88 (accuracy)	Private data (159 subjects)