LVAERMIL:通过潜在变分自编码器提升多实例学习鲁棒性
LVAERMIL: enhancing multiple instance learning robustness via latent variational autoencoders
研究提出 LVAERMIL,一种利用潜在空间变分自编码器学习实例分布、检测并剔除全切片图像中分布外 patch 的概率模块,以提升多实例学习(MIL)模型对污染的鲁棒性。在将两种数据集分别混入四种外来组织和两种扫描仪伪影的评估中,LVAERMIL 使 8 个 SOTA MIL 模型保持或提升准确率,污染比例高时更明显。
- Article
- Open access
- Published: 24 October 2026
- Francisco Javier Sáez-Maldonado ORCID: orcid.org/0009-0003-7838-58791,2,
- Luz García3,
- Lee A. D. Cooper4,5,6,
- Jeffery A. Goldstein6,
- Rafael Molina1 &
- …
- Aggelos K. Katsaggelos7
Scientific Reports (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Multiple Instance Learning (MIL) has become widely used in medical imaging classification, where precisely annotated data is scarce. MIL methods treat whole slide images as bags of instances (the patches), and only bag labels are required for training. Recently, MIL methods have shown extraordinary results in both classification and tumor localization benchmark tasks. However, in real-world scenarios, slides may be contaminated by tissue from other specimens or artifacts that can extrapolate MIL models and produce medical errors. This presents a challenge for widespread use of MIL in pathology labs. In this work, we propose Latent-VAE-Robust-MIL (LVAERMIL), a novel probabilistic module that learns the instance-level data distribution using a Variational Autoencoder trained on the latent space produced by a feature extractor. This enables the detection of out-of-distribution patches and their elimination from MIL bags, improving the robustness of any MIL model to whole slide image contaminants. The extensive evaluation performed by contaminating two datasets using four foreign tissues and using two scanner-induced artifacts shows that LVAERMIL maintains or improves the accuracy of the eight state-of-the-art MIL models on contaminated datasets, especially when the amount of contamination in the slides is high.
Acknowledgments
This work was supported by Grants PID2022-140189OB-C22 and PID2025-171570OB-I00, both funded by MICIU/AEI/10.13039/501100011033 and by NextGenerationEU/PRTR. Also, it was partially funded by Junta de Andalucía/Consejería de Universidad, Investigación e Innovación/Proyecto P21_0005.
Author information
Authors and Affiliations
Department of Computer Science and Artificial Intelligence, University of Granada, Granada, Spain
Francisco Javier Sáez-Maldonado & Rafael Molina
Research Centre for Information and Communication Technologies (CITIC), University of Granada, Granada, Spain
Francisco Javier Sáez-Maldonado
Department of Signal Theory, Telematics, and Communications, University of Granada, Granada, Spain
Luz García
Center for Computational Imaging and Signal Analytics, Northwestern University, Chicago, IL, USA
Lee A. D. Cooper
Chan Zuckerberg Biohub, Chicago, IL, USA
Lee A. D. Cooper
Department of Pathology, Northwestern University, Chicago, IL, USA
Lee A. D. Cooper & Jeffery A. Goldstein
Department of Electrical and Computer Engineering, Northwestern University, Chicago, IL, USA
Aggelos K. Katsaggelos
Authors
- Francisco Javier Sáez-Maldonado
- Luz García
- Lee A. D. Cooper
- Jeffery A. Goldstein
- Rafael Molina
- Aggelos K. Katsaggelos
Corresponding author
Correspondence to Francisco Javier Sáez-Maldonado.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Sáez-Maldonado, F.J., García, L., Cooper, L.A.D. et al. LVAERMIL: enhancing multiple instance learning robustness via latent variational autoencoders. Sci Rep (2026). https://doi.org/10.1038/s41598-026-76226-0
Received: 18 January 2026
Accepted: 12 October 2026
Published: 24 October 2026
DOI: https://doi.org/10.1038/s41598-026-76226-0
Keywords
来源:Nature 健康护理主题 · nature.com