File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Deep Reinforcement Active Learning for Medical Image Classification

TitleDeep Reinforcement Active Learning for Medical Image Classification
Authors
KeywordsActive learning
Deep reinforcement learning
Medical image classification
Issue Date2020
PublisherSpringer. The Proceedings' web site is located at https://link.springer.com/conference/miccai
Citation
23rd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2020), Lima, Peru, 4-8 October 2020. In Martel, AL ... er al (eds.). Proceedings, Part 1, p. 33-42 How to Cite?
AbstractIn this paper, we propose a deep reinforcement learning algorithm for active learning on medical image data. Although deep learning has achieved great success on medical image processing, it relies on a large number of labeled data for training, which is expensive and time-consuming. Active learning, which follows a strategy to select and annotate informative samples, is an effective approach to alleviate this issue. However, most existing methods of active learning adopt a hand-design strategy, which cannot handle the dynamic procedure of classifier training. To address this issue, we model the procedure of active learning as a Markov decision process, and propose a deep reinforcement learning algorithm to learn a dynamic policy for active learning. To achieve this, we employ the actor-critic approach, and apply the deep deterministic policy gradient algorithm to train the model. We conduct experiments on two kinds of medical image data sets, and the results demonstrate that our method is able to learn better strategy compared with the existing hand-design ones.
Persistent Identifierhttp://hdl.handle.net/10722/293886
ISBN
Series/Report no.Lecture Notes in Computer Science (LNCS) ; v. 12261

 

DC FieldValueLanguage
dc.contributor.authorWang, J-
dc.contributor.authorYan, Y-
dc.contributor.authorZhang, Y-
dc.contributor.authorCao, G-
dc.contributor.authorYang, M-
dc.contributor.authorNg, KP-
dc.date.accessioned2020-11-23T08:23:15Z-
dc.date.available2020-11-23T08:23:15Z-
dc.date.issued2020-
dc.identifier.citation23rd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2020), Lima, Peru, 4-8 October 2020. In Martel, AL ... er al (eds.). Proceedings, Part 1, p. 33-42-
dc.identifier.isbn9783030597092-
dc.identifier.urihttp://hdl.handle.net/10722/293886-
dc.description.abstractIn this paper, we propose a deep reinforcement learning algorithm for active learning on medical image data. Although deep learning has achieved great success on medical image processing, it relies on a large number of labeled data for training, which is expensive and time-consuming. Active learning, which follows a strategy to select and annotate informative samples, is an effective approach to alleviate this issue. However, most existing methods of active learning adopt a hand-design strategy, which cannot handle the dynamic procedure of classifier training. To address this issue, we model the procedure of active learning as a Markov decision process, and propose a deep reinforcement learning algorithm to learn a dynamic policy for active learning. To achieve this, we employ the actor-critic approach, and apply the deep deterministic policy gradient algorithm to train the model. We conduct experiments on two kinds of medical image data sets, and the results demonstrate that our method is able to learn better strategy compared with the existing hand-design ones.-
dc.languageeng-
dc.publisherSpringer. The Proceedings' web site is located at https://link.springer.com/conference/miccai-
dc.relation.ispartof23rd International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2020) Proceedings, Part I-
dc.relation.ispartofseriesLecture Notes in Computer Science (LNCS) ; v. 12261-
dc.subjectActive learning-
dc.subjectDeep reinforcement learning-
dc.subjectMedical image classification-
dc.titleDeep Reinforcement Active Learning for Medical Image Classification-
dc.typeConference_Paper-
dc.identifier.emailYan, Y: ygyan@hku.hk-
dc.identifier.emailNg, KP: michael.ng@hku.hk-
dc.identifier.authorityNg, KP=rp02578-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-030-59710-8_4-
dc.identifier.hkuros319002-
dc.identifier.issuePart 1-
dc.identifier.spage33-
dc.identifier.epage42-
dc.publisher.placeCham-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats