Abstract

This paper proposes a novel pseudo-labeling method for medical im- age segmentation that can perform learning on “individual images” to select ef- fective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learn- ing), which uses only positive and unlabeled data for binary classification prob- lems, to obtain the appropriate metric for discriminating foreground and back- ground regions on each unlabeled image. Our PU learning makes us easy to select pseudo-labels for various background regions. The experimental results show the effectiveness of our method.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/ADSMI2024_150.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to Open Review

Open Review Page: Not Available

BibTex

@InProceedings{YamTak_Adaptive_MICCAISAT2026,
        author = { Yamane, Takehiro AND Tsuge, Itaru AND Saito, Susumu AND Bise, Ryoma},
        title = { { Adaptive Pseudo Label Selection for Individual Unlabeled Data by Positive and Unlabeled Learning } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 17276},
        month = {pending},
        page = {pending}
}


back to top