Locally orderless tensor networks for classifying two- and three-dimensional medical images
This work addresses medical image classification, offering a more efficient tensor network approach, but it is incremental as it builds on existing MPS methods.
The authors tackled the problem of adapting tensor networks for 2D and 3D medical image classification by proposing LoTeNet, which treats small image regions as orderless and aggregates them hierarchically, achieving performance on par or superior to other methods with lesser computational resources.
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.