Table 1.

Summary of advantages and disadvantages of the approaches for lung boundary detection algorithms in CXR images

Algorithm	Advantages	Disadvantages
Rule-Based Methods	Easy to implement	Produce rough solutions
[23–25]	Sets sequential steps	Generally used as initialization of robust approaches
	Lower computational complexity	Poor generalization capability
Pixel classification		Based on low-level features
[11]		Lack of shape constraints
Deformable Models	Provides shape flexibility	Do not perform well at widely varying shapes
[30–33]	Combines both low-level features and general shape of the lung	Require proper initialization for a successful converge
[22, 34, 35]		The possibility of trapping at local minimum due to bone intensity
Hybrid Methods	Best part of the schemes are combined	Might require long training process
[11, 36, 45]	Similar accuracy as in inter-observer accuracy
Deep Learning Methods	Similar accuracy as in inter-observer performance	Long training process
[39, 41, 43]		Needs large set of annotated data
		Higher computational complexity