# Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images

arXiv: https://arxiv.org/abs/2310.19359 · HTML: https://mlsanity.com/paper/2310.19359/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 11 of 11)

- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Scalable Variational Gaussian Process Classification](https://mlsanity.com/paper/1411.2005/) (2014)
- [Multiple Instance Learning: A Survey of Problem Characteristics and Applications](https://mlsanity.com/paper/1612.03365/) (2016)
- [Going Deeper through the Gleason Scoring Scale: An Automatic end-to-end System for Histology Prostate Grading and Cribriform Pattern Detection](https://mlsanity.com/paper/2105.10490/) (2021)
- [Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification](https://mlsanity.com/paper/1612.05968/) (2016)
- [Results and Insights from Diagnostic Questions: The NeurIPS 2020 Education Challenge](https://mlsanity.com/paper/2104.04034/) (2021)
- [Self-learning for weakly supervised Gleason grading of local patterns](https://mlsanity.com/paper/2105.10420/) (2021)
- [Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning](https://mlsanity.com/paper/2302.04061/) (2023)
- [Probabilistic Label Relation Graphs with Ising Models](https://mlsanity.com/paper/1503.01428/) (2015)
- [Multi-label Methods for Prediction with Sequential Data](https://mlsanity.com/paper/1609.08349/) (2016)
- [Probabilistic Regressor Chains with Monte Carlo Methods](https://mlsanity.com/paper/1907.08087/) (2019)

## Built on by (most cited first, 1 of 1)

- [SGPMIL: Sparse Gaussian Process Multiple Instance Learning](https://mlsanity.com/paper/2507.08711/) (2025)

## Abstract (arXiv)

In the last years, the weakly supervised paradigm of multiple instance learning (MIL) has become very popular in many different areas. A paradigmatic example is computational pathology, where the lack of patch-level labels for whole-slide images prevents the application of supervised models. Probabilistic MIL methods based on Gaussian Processes (GPs) have obtained promising results due to their excellent uncertainty estimation capabilities. However, these are general-purpose MIL methods that do not take into account one important fact: in (histopathological) images, the labels of neighboring patches are expected to be correlated. In this work, we extend a state-of-the-art GP-based MIL method, which is called VGPMIL-PR, to exploit such correlation. To do so, we develop a novel coupling term inspired by the statistical physics Ising model. We use variational inference to estimate all the model parameters. Interestingly, the VGPMIL-PR formulation is recovered when the weight that regulates the strength of the Ising term vanishes. The performance of the proposed method is assessed in two real-world problems of prostate cancer detection. We show that our model achieves better results than other state-of-the-art probabilistic MIL methods. We also provide different visualizations and analysis to gain insights into the influence of the novel Ising term. These insights are expected to facilitate the application of the proposed model to other research areas.