Machine learning (ML) plays an important role in the medical imaging field, including medical image analysis and computeraided\r\ndiagnosis, because objects such as lesions and organs may not be represented accurately by a simple equation; thus, medical\r\npattern recognition essentially require ââ?¬Å?learning from examples.ââ?¬Â One of the most popular uses of ML is classification of objects\r\nsuch as lesions into certain classes (e.g., abnormal or normal, or lesions or nonlesions) based on input features (e.g., contrast\r\nand circularity) obtained from segmented object candidates. Recently, pixel/voxel-based ML (PML) emerged in medical image\r\nprocessing/analysis, which use pixel/voxel values in images directly instead of features calculated from segmented objects as input\r\ninformation; thus, feature calculation or segmentation is not required. Because the PML can avoid errors caused by inaccurate\r\nfeature calculation and segmentation which often occur for subtle or complex objects, the performance of the PML can potentially\r\nbe higher for such objects than that of common classifiers (i.e., feature-based MLs). In this paper, PMLs are surveyed to make clear\r\n(a) classes of PMLs, (b) similarities and differences within (among) different PMLs and those between PMLs and feature-based\r\nMLs, (c) advantages and limitations of PMLs, and (d) their applications in medical imaging.
Loading....