Computer-Aided Diagnosis Systems for Lung Cancer: Challenges and Methodologies

Table 6

Summary of lung nodule segmentation approaches from PET images. For each study, the table summarizes the number of the patients enrolled in the study and the type of the nodule delineation approach with respect to the methodology, the approach dimension, and the automation level.

Study	Patients	Delineation approach	Dim	AL
Kiffer et al. [187]	15	Coregistration	2D	A
Munley et al. [188]	35	Manual registration	NA	NA
Nestle et al. [189]	34	Visual	NA	NA
Mah et al. [190]	30	Thresholding	3D	A
Erdi et al. [191]	11	Thresholding	NA	A
Bradley et al. [192]	26	Thresholding	2D	A
Deniaud-Alexandre et al. [193]	101	Visual	NA	NA
Van Der Wel et al. [194]	21	Visual	NA	NA
Ashamalla et al. [195]	19	Thresholding	NA	A
Hatt et al. [196]	NA	Fuzzy hidden Markov chain	NA	A
Hatt et al. [197]	NA	Fuzzy classification	3D	A
Avazpour et al. [198]	11	Region growing	2D	A
Hatt et al. [199]	38	Fuzzy classification	NA	A

*Note that Dim denotes the approach dimension (2D, 3D), AL denotes automation level (A: automatic, UI: user interactive), and NA stands for nonapplicable.