# Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective

arXiv: https://arxiv.org/abs/2407.07841 · HTML: https://mlsanity.com/paper/2407.07841/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 34 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2106.00908/) (2021)
- [Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2011.08939/) (2020)
- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks](https://mlsanity.com/paper/2009.11169/) (2020)
- [Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks](https://mlsanity.com/paper/2107.13048/) (2021)
- [Artificial Intelligence for Digital and Computational Pathology](https://mlsanity.com/paper/2401.06148/) (2023)
- [A graph-transformer for whole slide image classification](https://mlsanity.com/paper/2205.09671/) (2022)
- [Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification](https://mlsanity.com/paper/2307.15254/) (2023)
- [Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification](https://mlsanity.com/paper/2210.03664/) (2022)
- [A General-Purpose Self-Supervised Model for Computational Pathology](https://mlsanity.com/paper/2308.15474/) (2023)
- [Computational Pathology at Health System Scale -- Self-Supervised Foundation Models from Three Billion Images](https://mlsanity.com/paper/2310.07033/) (2023)
- [ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification](https://mlsanity.com/paper/2207.01805/) (2022)
- [DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer](https://mlsanity.com/paper/2107.09405/) (2021)
- [An Aggregation of Aggregation Methods in Computational Pathology](https://mlsanity.com/paper/2211.01256/) (2022)
- [Terabyte-scale Deep Multiple Instance Learning for Classification and Localization in Pathology](https://mlsanity.com/paper/1805.06983/) (2018)
- [Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning](https://mlsanity.com/paper/2303.12214/) (2023)
- [Incorporating intratumoral heterogeneity into weakly-supervised deep learning models via variance pooling](https://mlsanity.com/paper/2206.08885/) (2022)
- [H&E-based Computational Biomarker Enables Universal EGFR Screening for Lung Adenocarcinoma](https://mlsanity.com/paper/2206.10573/) (2022)
- [Kernel Attention Transformer (KAT) for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2206.13156/) (2022)
- [Multi-scale Efficient Graph-Transformer for Whole Slide Image Classification](https://mlsanity.com/paper/2305.15773/) (2023)

## Built on by (most cited first, 10 of 10)

- [Revisiting Automatic Data Curation for Vision Foundation Models in Digital Pathology](https://mlsanity.com/paper/2503.18709/) (2025)
- [Pediatric brain tumor classification using digital histopathology and deep learning: evaluation of SOTA methods on a multi-center Swedish cohort](https://mlsanity.com/paper/2409.01330/) (2024)
- [Extreme Learning Machines for Attention-based Multiple Instance Learning in Whole-Slide Image Classification](https://mlsanity.com/paper/2503.10510/) (2025)
- [Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis](https://mlsanity.com/paper/2506.05184/) (2025)
- [Predict Patient Self-reported Race from Skin Histological Images](https://mlsanity.com/paper/2507.21912/) (2025)
- [Identifying actionable driver mutations in lung cancer using an efficient Asymmetric Transformer Decoder](https://mlsanity.com/paper/2508.02431/) (2025)
- [Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Framework](https://mlsanity.com/paper/2509.20923/) (2025)
- [PathBench-MIL: A Comprehensive AutoML and Benchmarking Framework for Multiple Instance Learning in Histopathology](https://mlsanity.com/paper/2512.17517/) (2025)
- [Reducing Redundancy in Whole-Slide Image Patching for Scalable Indexing and Retrieval](https://mlsanity.com/paper/2606.26157/) (2026)
- [Seeing Beyond the Lesion: Disease Recognition from Reactive CNS Tissue](https://mlsanity.com/paper/2609.02390/) (2026)

## Abstract (arXiv)

Recent advances in artificial intelligence (AI), in particular self-supervised learning of foundation models (FMs), are revolutionizing medical imaging and computational pathology (CPath). A constant challenge in the analysis of digital Whole Slide Images (WSIs) is the problem of aggregating tens of thousands of tile-level image embeddings to a slide-level representation. Due to the prevalent use of datasets created for genomic research, such as TCGA, for method development, the performance of these techniques on diagnostic slides from clinical practice has been inadequately explored. This study conducts a thorough benchmarking analysis of ten slide-level aggregation techniques across nine clinically relevant tasks, including diagnostic assessment, biomarker classification, and outcome prediction. The results yield following key insights: (1) Embeddings derived from domain-specific (histological images) FMs outperform those from generic ImageNet-based models across aggregation methods. (2) Spatial-aware aggregators enhance the performance significantly when using ImageNet pre-trained models but not when using FMs. (3) No single model excels in all tasks and spatially-aware models do not show general superiority as it would be expected. These findings underscore the need for more adaptable and universally applicable aggregation techniques, guiding future research towards tools that better meet the evolving needs of clinical-AI in pathology. The code used in this work is available at urlhttps://github.com/fuchs-lab-public/CPathSABenchmark.