Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.077561
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Multiple Point MedSAM Prompting for Enhanced Medical Image Segmentation

Wasfieh Nazzal1, Ezequiel López-Rubio1,2,3, Miguel A. Molina-Cabello1,2,3, Karl Thurnhofer-Hemsi1,2,3,*
1 Departamento de Lenguajes y Ciencias de la Computación, Universidad de Málaga, Bulevar Louis Pasteur, 35, Málaga, Spain
2 ITIS Software, Universidad de Málaga, C/Arquitecto Francisco Peñalosa 18, Málaga, Spain
3 Biomedic Research Institute of Málaga, IBIMA Plataforma BIONAND. C/Doctor Miguel Díaz Recio, 28, Málaga, Spain
* Corresponding Author: Karl Thurnhofer-Hemsi. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.077561

Received 11 December 2025; Accepted 26 January 2026; Published online 19 February 2026

Abstract

Automatic and accurate medical image segmentation remains a fundamental task in computer-aided diagnosis and treatment planning. Recent advances in foundation models, such as the medical-focused Segment Anything Model (MedSAM), have demonstrated strong performance but face challenges in many medical applications due to anatomical complexity and a limited domain-specific prompt. This work introduces a methodology that enhances segmentation robustness and precision by automatically generating multiple informative point prompts, rather than relying on single inputs. The proposed approach randomly samples sets of spatially distributed point prompts based on image features, enabling MedSAM to better capture fine-grained anatomical structures and boundaries. During inference, probability maps are aggregated to reduce local misclassifications without additional model training. Extensive experiments on various computed tomography (CT) and magnetic resonance imaging (MRI) datasets demonstrate improvements in Dice Similarity Coefficient (DSC) and Normalized Surface Dice (NSD) metrics compared to baseline SAM and Scribble Prompt models. A semi-automatic point sampling version based on the ground truth segmentations yielded enhanced results, achieving up to 92.1% DSC and 86.6% NSD, with significant gains in delineating complex organs such as the pancreas, colon, kidney, and brain tumours. The main novelty of our method consists of effectively combining the results of multiple point prompts into the medical segmentation pipeline so that single-point prompt methods are outperformed. Overall, the proposed model offers a straightforward yet effective approach to improve medical image segmentation performance while maintaining computational efficiency.

Keywords

Medical image segmentation; deep learning; test-time augmentation; point prompt

  • 328

    View

  • 181

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link