Scribbles for Metric Learning in Histological Image Segmentation

Segmentation is a fundamental process in biomedical image analysis that enables various types of analysis. Segmenting organs in histological microscopy images is problematic because the boundaries between regions are ambiguous, the images have various appearances, and the amount of training data is limited. To address these difficulties, supervised learning methods (e.g., convolutional neural networking (CNN)) are insufficient to predict regions accurately because they usually require a large amount of training data to learn the various appearances. In this paper, we propose a semi-automatic segmentation method that effectively uses scribble annotations for metric learning. Deep discriminative metric learning re-trains the representation of the feature space so that the distances between the samples with the same class labels are reduced, while those between ones with different class labels are enlarged. It makes pixel classification easy. Evaluation of the proposed method in a heart region segmentation task demonstrated that it performed better than three other methods.