LNCS 8675 - Scalable Histopathological Image Analysis via.pdfVIP

Scalable Histopathological Image Analysis via Active Learning 1 2 3 1 Yan Zhu , Shaoting Zhang , Wei Liu , and Dimitris N. Metaxas 1 Department of Computer Science, Rutgers University, Piscataway, NJ, USA 2 Department of Computer Science, University of North Carolina at Charlotte, NC, USA 3 IBM T.J. Watson Research Center, NY, USA Abstract. Training an effective and scalable system for medical image analysis usually requires a large amount of labeled data, which incurs a tremendous an- notation burden for pathologists. Recent progress in active learning can alleviate this issue, leading to a great reduction on the labeling cost without sacrificing the predicting accuracy too much. However, most existing active learning meth- ods disregard the “structured information” that may exist in medical images (e.g., data from individual patients), and make a simplifying assumption that unlabeled data is independently and identically distributed. Both may not be suitable for real-world medical images. In this paper, we propose a novel batch-mode active learning method which explores and leverages such structured information in an- notations of medical images to enforce diversity among the selected data, there- fore maximizing the information gain. We formulate the active learning problem as an adaptive submodular function maximization problem subject to a partition matroid constraint, and further present an efficient greedy algorithm to achieve a good solution with a theoretically proven bound. We demonstrate the efficacy of our algorithm on thousands of histopathological images of breast microscopic tissues. 1 Introduct