Cited 0 time in webofscience Cited 6 time in scopus

Multiple Instance Learning with Center Embeddings for Histopathology Classification

Title
Multiple Instance Learning with Center Embeddings for Histopathology Classification
Authors
Chikontwe, PhilipKim, MeejeongNam, SoojeongGo, HeounjeongPark, Sang Hyun
DGIST Authors
Park, Sang Hyun
Issue Date
2020-10-05
Citation
International Conference on Medical Image Computing and Computer Assisted Interventions, 519-528
Type
Conference
ISBN
9783030597214
ISSN
0302-9743
Abstract
Histopathology image analysis plays an important role in the treatment and diagnosis of cancer. However, analysis of whole slide images (WSI) with deep learning is challenging given that the duration of pixel-level annotations is laborious and time consuming. To address this, recent methods have considered WSI classification as a Multiple Instance Learning (MIL) problem often with a multi-stage process for learning instance and slide level features. Currently, most methods focus on either instance-selection or instance prediction-aggregation that often fails to generalize and ignores instance relations. In this work, we propose a MIL-based method to jointly learn both instance- and bag-level embeddings in a single framework. In addition, we propose a center loss that maps embeddings of instances from the same bag to a single centroid and reduces intra-class variations. Consequently, our model can accurately predict instance labels and leverages robust hierarchical pooling of features to obtain bag-level features without sacrificing accuracy. Experimental results on curated colon datasets show the effectiveness of the proposed methods against recent state-of-the-art methods. © 2020, Springer Nature Switzerland AG.
URI
http://hdl.handle.net/20.500.11750/12873
DOI
10.1007/978-3-030-59722-1_50
Publisher
Springer Science and Business Media Deutschland GmbH
Related Researcher
  • Author Park, Sang Hyun Medical Image & Signal Processing Lab
  • Research Interests 컴퓨터비전, 인공지능, 의료영상처리
Files:
There are no files associated with this item.
Collection:
Department of Robotics EngineeringMedical Image & Signal Processing Lab2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE