Skip to content Skip to navigation
Qualifying Exam
9/22/2016 03:00 pm

Active Learning for Scalable Histopathological Image Analysis

Yan Zhu, Dept. of Computer Science

Examination Committee: Prof. Dimitris N. Metaxas (chair), Prof. Vladimir Pavlovic, Prof. Kostas Berkris and Prof. Casimir Kulikowski


Training an effective and scalable system for medical image analysis usually requires a large amount of labeled data, which incurs a tremendous annotation 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.

In this talk, I will talk about a novel batch-mode active learning method which explores and leverages such structured information in annotations of medical images to enforce diversity among the selected data, therefore 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. We’ll conclude the talk and indicate ongoing work in the end.