# Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation

arXiv: https://arxiv.org/abs/2107.00583 · HTML: https://mlsanity.com/paper/2107.00583/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 1 Jul 2021.

## Builds on (most cited first, 18 of 18)

- [ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1604.05144/) (2016)
- [TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning](https://mlsanity.com/paper/2003.04696/) (2020)
- [Deep Interactive Object Selection](https://mlsanity.com/paper/1603.04042/) (2016)
- [Deep Extreme Cut: From Extreme Points to Object Segmentation](https://mlsanity.com/paper/1711.09081/) (2017)
- [On Regularized Losses for Weakly-supervised CNN Segmentation](https://mlsanity.com/paper/1803.09569/) (2018)
- [Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning](https://mlsanity.com/paper/1710.04043/) (2017)
- [DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation](https://mlsanity.com/paper/1707.00652/) (2017)
- [Extreme clicking for efficient object annotation](https://mlsanity.com/paper/1708.02750/) (2017)
- [DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks](https://mlsanity.com/paper/1605.07866/) (2016)
- [Constrained-CNN losses for weakly supervised segmentation](https://mlsanity.com/paper/1805.04628/) (2018)
- [Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision](https://mlsanity.com/paper/2004.06816/) (2020)
- [Going to Extremes: Weakly Supervised Medical Image Segmentation](https://mlsanity.com/paper/2009.11988/) (2020)
- [Scribble-based Domain Adaptation via Co-segmentation](https://mlsanity.com/paper/2007.03632/) (2020)
- [Automatic Segmentation of Vestibular Schwannoma from T2-Weighted MRI by Deep Spatial Attention with Hardness-Weighted Loss](https://mlsanity.com/paper/1906.03906/) (2019)
- [Self-Learning to Detect and Segment Cysts in Lung CT Images without Manual Annotation](https://mlsanity.com/paper/1801.08486/) (2018)
- [Manual segmentation versus semi-automated segmentation for quantifying vestibular schwannoma volume on MRI](https://mlsanity.com/paper/2004.14462/) (2020)
- [Permutohedral Attention Module for Efficient Non-Local Neural Networks](https://mlsanity.com/paper/1907.00641/) (2019)
- [Extreme Points Derived Confidence Map as a Cue For Class-Agnostic Segmentation Using Deep Neural Network](https://mlsanity.com/paper/1906.02421/) (2019)

## Built on by (most cited first, 21 of 21)

- [Scribble-Supervised Medical Image Segmentation via Dual-Branch Network and Dynamically Mixed Pseudo Labels Supervision](https://mlsanity.com/paper/2203.02106/) (2022)
- [CrossMoDA 2021 challenge: Benchmark of Cross-Modality Domain Adaptation techniques for Vestibular Schwannoma and Cochlea Segmentation](https://mlsanity.com/paper/2201.02831/) (2022)
- [Source-Free Domain Adaptation for Image Segmentation](https://mlsanity.com/paper/2108.03152/) (2021)
- [PA-Seg: Learning from Point Annotations for 3D Medical Image Segmentation using Contextual Regularization and Cross Knowledge Distillation](https://mlsanity.com/paper/2208.05669/) (2022)
- [Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions](https://mlsanity.com/paper/2303.12484/) (2023)
- [Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotations](https://mlsanity.com/paper/2205.06779/) (2022)
- [Weakly-Supervised 3D Medical Image Segmentation using Geometric Prior and Contrastive Similarity](https://mlsanity.com/paper/2302.02125/) (2023)
- [SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI](https://mlsanity.com/paper/2306.16714/) (2023)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [LNQ 2023 challenge: Benchmark of weakly-supervised techniques for mediastinal lymph node quantification](https://mlsanity.com/paper/2408.10069/) (2024)
- [Annotation by Clicks: A Point-Supervised Contrastive Variance Method for Medical Semantic Segmentation](https://mlsanity.com/paper/2212.08774/) (2022)
- [3D Vascular Segmentation Supervised by 2D Annotation of Maximum Intensity Projection](https://mlsanity.com/paper/2402.12128/) (2024)
- [Extreme Point Supervised Instance Segmentation](https://mlsanity.com/paper/2405.20729/) (2024)
- [From Sparse to Precise: A Practical Editing Approach for Intracardiac Echocardiography Segmentation](https://mlsanity.com/paper/2303.11041/) (2023)
- [Leveraging point annotations in segmentation learning with boundary loss](https://mlsanity.com/paper/2311.03537/) (2023)
- [OOD-SEG: Exploiting out-of-distribution detection techniques for learning image segmentation from sparse multi-class positive-only annotations](https://mlsanity.com/paper/2411.09553/) (2024)
- [Volumetric Medical Image Segmentation via Scribble Annotations and Shape Priors](https://mlsanity.com/paper/2310.08084/) (2023)
- [EAUWSeg: Eliminating annotation uncertainty in weakly-supervised medical image segmentation](https://mlsanity.com/paper/2501.01658/) (2025)
- [DEPT: Deep Extreme Point Tracing for Ultrasound Image Segmentation](https://mlsanity.com/paper/2503.15260/) (2025)
- [Label tree semantic losses for rich multi-class medical image segmentation](https://mlsanity.com/paper/2507.15777/) (2025)
- [Uncertainty-Aware Extreme Point Tracing for Weakly Supervised Ultrasound Image Segmentation](https://mlsanity.com/paper/2510.15666/) (2025)

## Abstract (arXiv)

We introduce textitInExtremIS, a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks at the boundary of the objects of interest. Our fully-automatic method is trained end-to-end and does not require any test-time annotations. From the extreme points, 3D bounding boxes are extracted around objects of interest. Then, deep geodesics connecting extreme points are generated to increase the amount of "annotated" voxels within the bounding boxes. Finally, a weakly supervised regularised loss derived from a Conditional Random Field formulation is used to encourage prediction consistency over homogeneous regions. Extensive experiments are performed on a large open dataset for Vestibular Schwannoma segmentation. textitInExtremIS obtained competitive performance, approaching full supervision and outperforming significantly other weakly supervised techniques based on bounding boxes. Moreover, given a fixed annotation time budget, textitInExtremIS outperforms full supervision. Our code and data are available online.