摘要：There has been recent substantial interest in extracting sub-visual features from medical images for improved disease characterization compared to what might be achievable via visual inspection alone. Features such as Haralick and Gabor can provide a multi-scale representation of the original image by extracting measurements across differently sized neighborhoods. While these multi-scale features are effective, on large-scale digital pathological images, the process of extracting these features is computationally expensive. Moreover for different problems, different scales and neighborhood sizes may be more or less important and thus a large number of features extracted might end up being redundant. In this paper, we present a Discriminative Scale learning (DiScrn) approach that attempts to automatically identify the distinctive scales at which features are able to best separate cancerous from non-cancerous regions on both radiologic and digital pathology tissue images. To evaluate the efficacy of our approach, our approach was employed to detect presence and extent of prostate cancer on a total of 60 MRI and digitized histopathology images. Compared to a multi-scale feature analysis approach invoking features across all scales, DiScrn achieved 66% computational efficiency while also achieving comparable or even better classifier performance.
