# Weakly supervised segmentation from extreme points

arXiv: https://arxiv.org/abs/1910.01236 · HTML: https://mlsanity.com/paper/1910.01236/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2019.

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

- [MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning](https://mlsanity.com/paper/2104.12166/) (2021)
- [Deep Interactive Segmentation of Medical Images: A Systematic Review and Taxonomy](https://mlsanity.com/paper/2311.13964/) (2023)
- [LNQ 2023 challenge: Benchmark of weakly-supervised techniques for mediastinal lymph node quantification](https://mlsanity.com/paper/2408.10069/) (2024)
- [Dense Regression Activation Maps For Lesion Segmentation in CT scans of COVID-19 patients](https://mlsanity.com/paper/2105.11748/) (2021)
- [Beyond Pixel-Wise Supervision for Medical Image Segmentation: From Traditional Models to Foundation Models](https://mlsanity.com/paper/2404.13239/) (2024)
- [Weakly Supervised Volumetric Image Segmentation with Deformed Templates](https://mlsanity.com/paper/2106.03987/) (2021)
- [Interactive Segmentation for Diverse Gesture Types Without Context](https://mlsanity.com/paper/2307.10518/) (2023)
- [Extreme Point Supervised Instance Segmentation](https://mlsanity.com/paper/2405.20729/) (2024)
- [S4M: 4-points to Segment Anything](https://mlsanity.com/paper/2503.05534/) (2025)
- [Expectation-Maximization Regularized Deep Learning for Weakly Supervised Tumor Segmentation for Glioblastoma](https://mlsanity.com/paper/2101.08757/) (2021)

## Abstract (arXiv)

Annotation of medical images has been a major bottleneck for the development of accurate and robust machine learning models. Annotation is costly and time-consuming and typically requires expert knowledge, especially in the medical domain. Here, we propose to use minimal user interaction in the form of extreme point clicks in order to train a segmentation model that can, in turn, be used to speed up the annotation of medical images. We use extreme points in each dimension of a 3D medical image to constrain an initial segmentation based on the random walker algorithm. This segmentation is then used as a weak supervisory signal to train a fully convolutional network that can segment the organ of interest based on the provided user clicks. We show that the network's predictions can be refined through several iterations of training and prediction using the same weakly annotated data. Ultimately, our method has the potential to speed up the generation process of new training datasets for the development of new machine learning and deep learning-based models for, but not exclusively, medical image analysis.