%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2021/09.16.13.14
%2 sid.inpe.br/sibgrapi/2021/09.16.13.14.37
%T Semantic Segmentation with Multi-Source Domain Adaptation for Radiological Images
%D 2021
%A Oliveira, Hugo Neves de,
%A Araújo, Arnaldo de Albuquerque,
%A Santos, Jefersson Alex dos,
%@affiliation Departamento de Ciência da Computação - UFMG
%@affiliation Departamento de Ciência da Computação - UFMG
%@affiliation Departamento de Ciência da Computação - UFMG
%E Paiva, Afonso,
%E Menotti, David,
%E Baranoski, Gladimir V. G.,
%E Proença, Hugo Pedro,
%E Junior, Antonio Lopes Apolinario,
%E Papa, João Paulo,
%E Pagliosa, Paulo,
%E dos Santos, Thiago Oliveira,
%E e Sá, Asla Medeiros,
%E da Silveira, Thiago Lopes Trugillo,
%E Brazil, Emilio Vital,
%E Ponti, Moacir A.,
%E Fernandes, Leandro A. F.,
%E Avila, Sandra,
%B Conference on Graphics, Patterns and Images, 34 (SIBGRAPI)
%C Gramado, RS, Brazil (virtual)
%8 18-22 Oct. 2021
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K domain generalization, biomedical images, generative adversarial networks, image-to-image translation.
%X Differences in digitization equipment and techniques in radiology may hamper the use of data-driven deep learning approaches. In order to mitigate this limitation, in this work we merge generative image translation networks with supervised semantic segmentation architectures, yielding two semi-supervised methods for domain adaptation in medical images. We compare our methods with traditional baselines in the literature using 3 image domains, 16 datasets and 8 segmentation tasks organized into three sets of experiments. Analysis of the results showed that the proposed methods for Domain Adaptation often reached Jaccard scores of 0.9 or higher in unsupervised or semi-supervised settings. We observe that unsupervised domain adaptation performance is close to the performance of fully supervised adaptation in most cases, bridging an important gap in the efficacy of neural networks between labeled and unlabeled datasets.
%@language en
%3 WTD_SIBGRAPI_2021_Final.pdf