Involvement of Machine Learning for Breast Cancer Image Classification: A Survey

Table 21

Semisupervised algorithm for breast image classification.

Reference	Descriptor	Image type	Number of images	Key finding
Cordeiro et al. [166]	Zernike moments have been used for the feature extraction.	—	685	Semisupervised Fuzzy GrowCut algorithm utilized.; For the fatty-tissue classification this method achieved 91.28% Accuracy.
Cordeiro et al. [167]	—	Mammogram	322	Semisupervised Fuzzy GrowCut as well as the Fuzzy GrowCut algorithm utilized for tumors, region segmentation.
Nawel et al. [168]	—	—	—	Semisupervised Support Vector Machine (S3VM) utilized.; This experiment shows impressive results on the DDSM database.
Zemmal et al. [169]	—	DDSM	—	Transductive semisupervised learning technique using (TSVM) utilized for classification along with different features.
Zemmal et al. [170]	—	—	200	Semisupervised Support Vector Machine (S3VM) utilized with various kernels.
Zemmal et al. [171]	GLCM Hu moments Central Moments	Mammogram	—	Transductive Semisupervised learning technique used for image classification.; This experiment shows impressive results on DDSM database.
Peikari et al. [172]	Mean, Mode, Standard Deviation, Media, Skewness, Kurtosis	Histopathological	322	The Ordering Points to Identify the Clustering Structure (OPTICS) method utilized for image classification [173].