Welcome to the UPF Digital Repository

Test time transform prediction for open set histopathological image recognition

Show simple item record

dc.contributor.author Galdran, Adrian
dc.contributor.author Hewitt, Katherine J.
dc.contributor.author Ghaffari Laleh, Narmin
dc.contributor.author Kather, Jakob N.
dc.contributor.author Carneiro, Gustavo
dc.contributor.author González Ballester, Miguel Ángel, 1973-
dc.date.accessioned 2023-03-07T08:09:24Z
dc.date.issued 2022
dc.identifier.citation Galdran A, Hewitt KJ, Ghaffari Laleh N, Kather JN, Carneiro G, González Ballester MA. Test time transform prediction for open set histopathological image recognition. In: Wang L, Dou Q, Fletcher PT, Speidel S, Li S, editors. Medical Image Computing and Computer Assisted Intervention (MICCAI 2022): 25th International Conference; 2022 Sep 18-22; Sentosa Island, Singapore. Cham: Springer; 2022. p. 263-72. DOI: 10.1007/978-3-031-16434-7_26
dc.identifier.issn 0302-9743
dc.identifier.uri http://hdl.handle.net/10230/56078
dc.description Comunicació presentada a 25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2022), celebrat del 18 al 22 de setembre de 2022 a Sentosa, Singapur.
dc.description.abstract Tissue typology annotation in Whole Slide histological images is a complex and tedious, yet necessary task for the development of computational pathology models. We propose to address this problem by applying Open Set Recognition techniques to the task of jointly classifying tissue that belongs to a set of annotated classes, e.g. clinically relevant tissue categories, while rejecting in test time Open Set samples, i.e. images that belong to categories not present in the training set. To this end, we introduce a new approach for Open Set histopathological image recognition based on training a model to accurately identify image categories and simultaneously predict which data augmentation transform has been applied. In test time, we measure model confidence in predicting this transform, which we expect to be lower for images in the Open Set. We carry out comprehensive experiments in the context of colorectal cancer assessment from histological images, which provide evidence on the strengths of our approach to automatically identify samples from unknown categories. Code is released at https://github.com/agaldran/t3po.
dc.description.sponsorship This work was partially supported by a Marie Sklodowska-Curie Global Fellowship (No. 892297) and by Australian Research Council grants (DP180103232 and FT190100525).
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher Springer
dc.relation.ispartof Wang L, Dou Q, Fletcher PT, Speidel S, Li S, editors. Medical Image Computing and Computer Assisted Intervention (MICCAI 2022): 25th International Conference; 2022 Sep 18-22; Sentosa Island, Singapore. Cham: Springer; 2022. p. 263-72.
dc.relation.isreferencedby https://github.com/agaldran/t3po
dc.rights © Springer This is a author's accepted manuscript of: Galdran A, Hewitt KJ, Ghaffari Laleh N, Kather JN, Carneiro G, González Ballester MA. Test time transform prediction for open set histopathological image recognition. In: Wang L, Dou Q, Fletcher PT, Speidel S, Li S, editors. Medical Image Computing and Computer Assisted Intervention (MICCAI 2022): 25th International Conference; 2022 Sep 18-22; Sentosa Island, Singapore. Cham: Springer; 2022. p. 263–72. The final version is available online at: http://dx.doi.org/10.1007/978-3-031-16434-7_26
dc.title Test time transform prediction for open set histopathological image recognition
dc.type info:eu-repo/semantics/conferenceObject
dc.identifier.doi http://dx.doi.org/10.1007/978-3-031-16434-7_26
dc.subject.keyword Histopathological image analysis
dc.subject.keyword Open Set Recognition
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/892297
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/acceptedVersion

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

In collaboration with Compliant to Partaking