# Employing Weak Annotations for Medical Image Analysis Problems

arXiv: https://arxiv.org/abs/1708.06297 · HTML: https://mlsanity.com/paper/1708.06297/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2017.

## Built on by (most cited first, 7 of 7)

- [Scribble2D5: Weakly-Supervised Volumetric Image Segmentation via Scribble Annotations](https://mlsanity.com/paper/2205.06779/) (2022)
- [ZScribbleSeg: Zen and the Art of Scribble Supervised Medical Image Segmentation](https://mlsanity.com/paper/2301.04882/) (2023)
- [Volumetric Medical Image Segmentation via Scribble Annotations and Shape Priors](https://mlsanity.com/paper/2310.08084/) (2023)
- ["Where does it hurt?" -- Dataset and Study on Physician Intent Trajectories in Doctor Patient Dialogues](https://mlsanity.com/paper/2508.19077/) (2025)
- [The 1st Solution for CARE Liver Task Challenge 2025: Contrast-Aware Semi-Supervised Segmentation with Domain Generalization and Test-Time Adaptation](https://mlsanity.com/paper/2510.04243/) (2025)
- [A Green Solution for Breast Region Segmentation Using Deep Active Learning](https://mlsanity.com/paper/2601.02538/) (2026)
- [ZScribbleSeg: A comprehensive segmentation framework with modeling of efficient annotation and maximization of scribble supervision](https://mlsanity.com/paper/2605.06266/) (2026)

## Abstract (arXiv)

To efficiently establish training databases for machine learning methods, collaborative and crowdsourcing platforms have been investigated to collectively tackle the annotation effort. However, when this concept is ported to the medical imaging domain, reading expertise will have a direct impact on the annotation accuracy. In this study, we examine the impact of expertise and the amount of available annotations on the accuracy outcome of a liver segmentation problem in an abdominal computed tomography (CT) image database. In controlled experiments, we study this impact for different types of weak annotations. To address the decrease in accuracy associated with lower expertise, we propose a method for outlier correction making use of a weakly labelled atlas. Using this approach, we demonstrate that weak annotations subject to high error rates can achieve a similarly high accuracy as state-of-the-art multi-atlas segmentation approaches relying on a large amount of expert manual segmentations. Annotations of this nature can realistically be obtained from a non-expert crowd and can potentially enable crowdsourcing of weak annotation tasks for medical image analysis.