LVAERMIL: enhancing multiple instance learning robustness via latent variational autoencoders
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.
Related
- Variational Autoencoders for Medical Image Segmentation: A Review
- Meta-Variational Autoencoders: A Framework for Learning to Construct, Adapt, and Optimize Variational Autoencoders
- PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoders
- Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders
- Calibrated term presence modelling for CCUS patent abstracts: a case study with variational autoencoders and retrieval baselines
BibTeX
@article{saezmaldonado2026lvaermil,
title = {{LVAERMIL: enhancing multiple instance learning robustness via latent variational autoencoders}},
author = {Francisco Javier Sáez-Maldonado and Luz García and Lee A. D. Cooper and Jeffery A. Goldstein and Rafael Molina and Aggelos K. Katsaggelos},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-76226-0},
url = {https://www.nature.com/articles/s41598-026-76226-0},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - LVAERMIL: enhancing multiple instance learning robustness via latent variational autoencoders
AU - Francisco Javier Sáez-Maldonado
AU - Luz García
AU - Lee A. D. Cooper
AU - Jeffery A. Goldstein
AU - Rafael Molina
AU - Aggelos K. Katsaggelos
PY - 2026
DA - 2026/10/24
JO - Scientific Reports
DO - 10.1038/s41598-026-76226-0
UR - https://www.nature.com/articles/s41598-026-76226-0
AB - 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.
SN - 2045-2322
ER -