Locally orderless tensor networks for classifying two- and three-dimensional medical images

Research output: Contribution to journalConference articlepeer-review

Documents

  • Fulltext

    Submitted manuscript, 4.75 MB, PDF document

Tensor networks are factorisations of high rank tensors into networks of lower rank tensors and have primarily been used to analyse quantum many-body problems. Tensor networks have seen a recent surge of interest in relation to supervised learning tasks with a focus on image classification. In this work, we improve upon the matrix product state (MPS) tensor networks that can operate on one-dimensional vectors to be useful for working with 2D and 3D medical images. We treat small image regions as orderless, squeeze their spatial information into feature dimensions and then perform MPS operations on these locally orderless regions. These local representations are then aggregated in a hierarchical manner to retain global structure. The proposed locally orderless tensor network (LoTeNet) is compared with relevant methods on three datasets. The architecture of LoTeNet is fixed in all experiments and we show it requires lesser computational resources to attain performance on par or superior to the compared methods.
Original languageEnglish
JournalThe Journal of Machine Learning for Biomedical Imaging
Volume5
Issue numberSI
Pages (from-to)1-21
ISSN2766-905X
Publication statusPublished - 2021
EventMIDL 2020 : International Conference on Medical Imaging with Deep Learning - Montreal, Canada
Duration: 6 Jul 20208 Jul 2020

Conference

ConferenceMIDL 2020 : International Conference on Medical Imaging with Deep Learning
CountryCanada
CityMontreal
Period06/07/202008/07/2020

ID: 249297561