# Leveraging Weak Supervision for Cell Localization in Digital Pathology Using Multitask Learning and Consistency Loss

arXiv: https://arxiv.org/abs/2412.15392 · HTML: https://mlsanity.com/paper/2412.15392/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 49 references that are in the map.
- First posted on arXiv 19 Dec 2024.

## Builds on (most cited first, 15 of 15)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [HoVer-Net: Simultaneous Segmentation and Classification of Nuclei in Multi-Tissue Histology Images](https://mlsanity.com/paper/1812.06499/) (2018)
- [Mutual Consistency Learning for Semi-supervised Medical Image Segmentation](https://mlsanity.com/paper/2109.09960/) (2021)
- [Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Images](https://mlsanity.com/paper/2007.05448/) (2020)
- [One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification](https://mlsanity.com/paper/2203.00077/) (2022)
- [PseudoEdgeNet: Nuclei Segmentation only with Point Annotations](https://mlsanity.com/paper/1906.02924/) (2019)
- [Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models](https://mlsanity.com/paper/2103.00429/) (2021)
- [Weakly Supervised Multi-Task Learning for Cell Detection and Segmentation](https://mlsanity.com/paper/1910.12326/) (2019)
- [Nuclei Segmentation with Point Annotations from Pathology Images via Self-Supervised Learning and Co-Training](https://mlsanity.com/paper/2202.08195/) (2022)
- [Deeply-Supervised Density Regression for Automatic Cell Counting in Microscopy Images](https://mlsanity.com/paper/2011.03683/) (2020)
- [Quick Annotator: an open-source digital pathology based rapid image annotation tool](https://mlsanity.com/paper/2101.02183/) (2021)
- [ConCORDe-Net: Cell Count Regularized Convolutional Neural Network for Cell Detection in Multiplex Immunohistochemistry Images](https://mlsanity.com/paper/1908.00907/) (2019)
- [Point-supervised Single-cell Segmentation via Collaborative Knowledge Sharing](https://mlsanity.com/paper/2304.10671/) (2023)
- [Scribble-supervised Cell Segmentation Using Multiscale Contrastive Regularization](https://mlsanity.com/paper/2306.14136/) (2023)

## Abstract (arXiv)

Cell detection and segmentation are integral parts of automated systems in digital pathology. Encoder-decoder networks have emerged as a promising solution for these tasks. However, training of these networks has typically required full boundary annotations of cells, which are labor-intensive and difficult to obtain on a large scale. However, in many applications, such as cell counting, weaker forms of annotations--such as point annotations or approximate cell counts--can provide sufficient supervision for training. This study proposes a new mixed-supervision approach for training multitask networks in digital pathology by incorporating cell counts derived from the eyeballing process--a quick visual estimation method commonly used by pathologists. This study has two main contributions: (1) It proposes a mixed-supervision strategy for digital pathology that utilizes cell counts obtained by eyeballing as an auxiliary supervisory signal to train a multitask network for the first time. (2) This multitask network is designed to concurrently learn the tasks of cell counting and cell localization, and this study introduces a consistency loss that regularizes training by penalizing inconsistencies between the predictions of these two tasks. Our experiments on two datasets of hematoxylin-eosin stained tissue images demonstrate that the proposed approach effectively utilizes the weakest form of annotation, improving performance when stronger annotations are limited. These results highlight the potential of integrating eyeballing-derived ground truths into the network training, reducing the need for resource-intensive annotations.