# A methodology for clinically driven interactive segmentation evaluation

arXiv: https://arxiv.org/abs/2510.09499 · HTML: https://mlsanity.com/paper/2510.09499/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 19 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Builds on (most cited first, 9 of 9)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Metrics reloaded: Recommendations for image analysis validation](https://mlsanity.com/paper/2206.01653/) (2022)
- [SegVol: Universal and Interactive Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2311.13385/) (2023)
- [Analysis of the MICCAI Brain Tumor Segmentation -- Metastases (BraTS-METS) 2025 Lighthouse Challenge: Brain Metastasis Segmentation on Pre- and Post-treatment MRI](https://mlsanity.com/paper/2504.12527/) (2025)
- [PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts](https://mlsanity.com/paper/2404.15028/) (2024)
- [RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation](https://mlsanity.com/paper/2410.11722/) (2024)
- [RadioActive: 3D Radiological Interactive Segmentation Benchmark](https://mlsanity.com/paper/2411.07885/) (2024)

## Built on by (most cited first, 1 of 1)

- [CLoPA: Continual Low Parameter Adaptation of Interactive Segmentation for Medical Image Annotation](https://mlsanity.com/paper/2603.06426/) (2026)

## Abstract (arXiv)

Interactive segmentation is a promising strategy for building robust, generalisable algorithms for volumetric medical image segmentation. However, inconsistent and clinically unrealistic evaluation hinders fair comparison and misrepresents real-world performance. We propose a clinically grounded methodology for defining evaluation tasks and metrics, and built a software framework for constructing standardised evaluation pipelines. We evaluate state-of-the-art algorithms across heterogeneous and complex tasks and observe that (i) minimising information loss when processing user interactions is critical for model robustness, (ii) adaptive-zooming mechanisms boost robustness and speed convergence, (iii) performance drops if validation prompting behaviour/budgets differ from training, (iv) 2D methods perform well with slab-like images and coarse targets, but 3D context helps with large or irregularly shaped targets, (v) performance of non-medical-domain models (e.g. SAM2) degrades with poor contrast and complex shapes.