# LIMIS: Towards Language-based Interactive Medical Image Segmentation

Source: [LIMIS: Towards Language-based Interactive Medical Image Segmentation](<https://www.sota2.com/research/paper/68fa754f1e209131cea67085>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:31:06.502Z

Authors: Lena Heinemann, Alexander Jaus, Zdravko Marinov, Moon Kim, Maria Francesca Spadea, Jens Kleesiek, Rainer Stiefelhagen

Published: 2024-10-22T12:13:47.000Z

## Abstract

Within this work, we introduce LIMIS: The first purely language-based interactive medical image segmentation model. We achieve this by adapting Grounded SAM to the medical domain and designing a language-based model interaction strategy that allows radiologists to incorporate their knowledge into the segmentation process. LIMIS produces high-quality initial segmentation masks by leveraging medical foundation models and allows users to adapt segmentation masks using only language, opening up interactive segmentation to scenarios where physicians require using their hands for other tasks. We evaluate LIMIS on three publicly available medical datasets in terms of performance and usability with experts from the medical domain confirming its high-quality segmentation masks and its interactive usability.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.16939>)

[PDF](<https://arxiv.org/pdf/2410.16939.pdf>)
