# TUMLS: Trustful Fully Unsupervised Multi-Level Segmentation for Whole Slide Images of Histology

arXiv: https://arxiv.org/abs/2504.12718 · HTML: https://mlsanity.com/paper/2504.12718/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 52 references that are in the map.
- First posted on arXiv 17 Apr 2025.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Medical Transformer: Gated Axial-Attention for Medical Image Segmentation](https://mlsanity.com/paper/2102.10662/) (2021)
- [Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation](https://mlsanity.com/paper/1908.10454/) (2019)
- [Deep Multiview Clustering by Contrasting Cluster Assignments](https://mlsanity.com/paper/2304.10769/) (2023)
- [Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models](https://mlsanity.com/paper/2103.00429/) (2021)
- [Multi-Resolution Networks for Semantic Segmentation in Whole Slide Images](https://mlsanity.com/paper/1807.09607/) (2018)
- [ScanNet: A Fast and Dense Scanning Framework for Metastatic Breast Cancer Detection from Whole-Slide Images](https://mlsanity.com/paper/1707.09597/) (2017)
- [GRU-Net: Gaussian Attention Aided Dense Skip Connection Based MultiResUNet for Breast Histopathology Image Segmentation](https://mlsanity.com/paper/2406.08604/) (2024)
- [Unsupervisedly Training GANs for Segmenting Digital Pathology with Automatically Generated Annotations](https://mlsanity.com/paper/1805.10059/) (2018)
- [Unsupervised Mutual Transformer Learning for Multi-Gigapixel Whole Slide Image Classification](https://mlsanity.com/paper/2305.02032/) (2023)
- [DU-Net based Unsupervised Contrastive Learning for Cancer Segmentation in Histology Images](https://mlsanity.com/paper/2206.08791/) (2022)

## Abstract (arXiv)

Digital pathology, augmented by artificial intelligence (AI), holds significant promise for improving the workflow of pathologists. However, challenges such as the labor-intensive annotation of whole slide images (WSIs), high computational demands, and trust concerns arising from the absence of uncertainty estimation in predictions hinder the practical application of current AI methodologies in histopathology. To address these issues, we present a novel trustful fully unsupervised multi-level segmentation methodology (TUMLS) for WSIs. TUMLS adopts an autoencoder (AE) as a feature extractor to identify the different tissue types within low-resolution training data. It selects representative patches from each identified group based on an uncertainty measure and then does unsupervised nuclei segmentation in their respective higher-resolution space without using any ML algorithms. Crucially, this solution integrates seamlessly into clinicians workflows, transforming the examination of a whole WSI into a review of concise, interpretable cross-level insights. This integration significantly enhances and accelerates the workflow while ensuring transparency. We evaluated our approach using the UPENN-GBM dataset, where the AE achieved a mean squared error (MSE) of 0.0016. Additionally, nucleus segmentation is assessed on the MoNuSeg dataset, outperforming all unsupervised approaches with an F1 score of 77.46% and a Jaccard score of 63.35%. These results demonstrate the efficacy of TUMLS in advancing the field of digital pathology.