Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey

Table 3

Comparison of the performance of deep learning-based survival prediction methods.

Publication	Type of images	Proposed methods		Comparison baseline
		Method	Results	Method	Results
Liu et al. [52]	MRI	CNN + RF	ACC = 0.9545	CHF	ACC = 0.9091
Paul et al. [54]	Contrast-enhanced CT	CNN + SUFRA + RF	AUC = 0.935	TQF + DT	AUC = 0.712

Notes. MRI = magnetic resonance imaging; CNN = convolutional neural network; RF = random forest; ACC = accuracy; CHF = conventional histogram feature; CT = computer tomography; SUFRA = symmetric uncertainty feature ranking algorithm [60]; AUC = area under the receiver operating characteristic curve; TQF = traditional quantitative features; DT = decision tree.