Learning histopathological regions of interest by fusing bottom-up and top-down information

Computer assisted diagnosis of basal cell carcinoma using Z-transform features

“…These descriptors are used by a SVM to discriminate between cancerous and healthy tissue. Authors in [27] proposed a graph-based method along with a Bayesian strategy to identify the regions of interest in histopathological images of basal cell carcinoma. Unsupervised feature learning (UFL) methods are used in [28][29][30] for basal cell carcinoma detection.…”

“…The problem of basal cell carcinoma detection is addressed in [26][27][28][29][30]. In [26], cells nuclei are segmented by maximally stable extreme regions (MSER) approach and then, color descriptors are extracted from the segmented regions at different scales.…”

Training a cell-level classifier for detecting basal-cell carcinoma by combining human visual attention maps with low-level handcrafted features

“…While four pathologists were part of the experiment, results of previous works suggest that including more pathologists has the potential of improving these results even more. 31 …”

“…In such an approach, the idea is to identify and characterize the most frequently visited areas, since very likely they contain relevant diagnosis information. In a previous work, 31 a Bayesian framework predicted regions an expert might visit based on the visual data and previous visits of other experts, attempting to improve the cache performance for different navigation tasks. This approach begins by learning a set of candidate relevant regions using salient information coming from visual features such as color, shape, and orientation.…”